CN117218132B - Whole furnace tube service life analysis method, device, computer equipment and medium - Google Patents
Whole furnace tube service life analysis method, device, computer equipment and medium Download PDFInfo
- Publication number
- CN117218132B CN117218132B CN202311486937.XA CN202311486937A CN117218132B CN 117218132 B CN117218132 B CN 117218132B CN 202311486937 A CN202311486937 A CN 202311486937A CN 117218132 B CN117218132 B CN 117218132B
- Authority
- CN
- China
- Prior art keywords
- furnace tube
- score
- scoring
- model
- image
- 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
- 238000004458 analytical method Methods 0.000 title claims description 14
- 238000012549 training Methods 0.000 claims abstract description 126
- 230000003647 oxidation Effects 0.000 claims abstract description 80
- 238000007254 oxidation reaction Methods 0.000 claims abstract description 80
- 238000003466 welding Methods 0.000 claims abstract description 39
- 238000000034 method Methods 0.000 claims abstract description 32
- 238000003754 machining Methods 0.000 claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000002372 labelling Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 8
- 230000004927 fusion Effects 0.000 claims description 8
- 230000009194 climbing Effects 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 235000009537 plain noodles Nutrition 0.000 claims 2
- 230000000007 visual effect Effects 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000956 alloy Substances 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004939 coking Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000003337 fertilizer Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005272 metallurgy Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000010301 surface-oxidation reaction Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Radiation Pyrometers (AREA)
Abstract
The invention relates to the technical field of visual processing, in particular to a method, a device, computer equipment and a medium for analyzing the service life of an integral furnace tube, wherein the method comprises the following steps: acquiring first images of the outer surface areas of N furnace tubes and second images of machining smooth surface areas on two sides of a welding line; dividing each first image into a plurality of first blocks, marking a first score of the oxidation degree of each first block to obtain a first training sample, dividing each second image into a plurality of second blocks, marking a second score of the oxidation degree of each second region to obtain a second training sample; obtaining a first scoring model based on the first training sample and the first training model, and obtaining a second scoring model based on the second training sample and the second training model; acquiring a first target image and a second target image of an integral furnace tube with service life to be scored; and obtaining a scoring result of the whole furnace tube with the service life to be scored based on the first scoring model and the second scoring model, and comprehensively and accurately judging the influence degree of the high temperature on the furnace tube.
Description
Technical Field
The invention relates to the technical field of visual processing, in particular to a method, a device, computer equipment and a medium for analyzing the service life of an integral furnace tube.
Background
The stability of a high temperature industrial furnace, which is the most core and important equipment in the industries of petrochemical, refining, chemical fertilizer, metallurgy and the like, directly determines the risk level of safe production.
The high-temperature industrial furnace mainly comprises a furnace tube made of high-temperature alloy materials and a hearth, wherein the furnace tube is used as a high-temperature medium reaction vessel and needs to bear high temperature (900-1200 ℃) for a long time, and the furnace tube is one of main reasons for failure of the furnace tube due to the actions of various factors such as surface oxidation, inner surface carburization, coking in the tube, thermal fatigue, thermal shock and the like. In order to evaluate the remaining life of the furnace tube, a high temperature service process of the furnace tube is required to be known, wherein the service high temperature and the high temperature service time are mainly involved.
At present, part of enterprises are provided with on-line detection equipment such as a thermocouple and an infrared thermometer for furnace tubes. The thermocouple can only measure the temperature of a local certain point in real time; the infrared thermometer is affected by high-temperature smoke, and the fluctuation of measured data is large. During the shutdown maintenance of an industrial furnace, data concerning the high-temperature service process of each region of the furnace tube is incomplete due to the limitations of the data, resulting in difficulty in accurately preparing a plan for maintenance and replacement of the furnace tube. Moreover, many enterprises are not equipped with the related devices. During the shutdown maintenance period, the high-temperature service process of the furnace tube is analyzed, no related technology exists at present, and how to comprehensively and accurately judge the influence degree of the high temperature on the furnace tube is a technical problem to be solved urgently at present.
Disclosure of Invention
In view of the foregoing, the present invention provides a method, apparatus, computer device and medium for analyzing overall furnace tube lifetime that overcomes or at least partially solves the foregoing problems.
In a first aspect, the present invention provides a method for analyzing the lifetime of an integral furnace, where the integral furnace is formed by welding a plurality of sections of furnace, and the integral furnace includes a furnace outer surface area and machined smooth surface areas on two sides of a weld, and the method includes:
acquiring first images of N furnace tube outer surface areas and second images of machining smooth surface areas on two sides of welding seams of N furnace tubes;
dividing each first image into a plurality of first blocks, marking a first score of oxidation degree for each first block, dividing each second image into a plurality of second blocks, marking a second score of oxidation degree for each second block, taking the first block marked with the first score as a first training sample, and taking the second block marked with the second score as a second training sample;
obtaining a first scoring model based on the first training sample and the first training model, and obtaining a second scoring model based on the second training sample and the second training model;
acquiring a first target image of an outer surface area of the whole furnace tube of the service life to be scored and a second target image of machining smooth surface areas on two sides of a welding line;
obtaining a scoring result of the whole furnace tube with the service life to be scored based on the first target image and the first scoring model and the second target image and the second scoring model;
and determining the residual life of the whole furnace tube with the life to be scored based on the scoring result.
Further, the acquiring the first images of the outer surface areas of the N furnace tubes and the second images of the machined light surface areas on two sides of the weld seam of the N furnace tubes includes:
and a plurality of image acquisition devices arranged on the climbing robot are used for acquiring first images of the outer surface areas of the N whole furnace tubes and second images of machining smooth surface areas on two sides of the welding seam of the furnace tube in the circumferential direction and the longitudinal direction of the N whole furnace tubes.
Further, the segmenting each first image into a plurality of first blocks, labeling a first score of oxidation degree for each first block, segmenting each second image into a plurality of second blocks, labeling a second score of oxidation degree for each second block, taking the first block labeled with the first score as a first training sample, and taking the second block labeled with the second score as a second training sample, including:
dividing each first image into a plurality of first blocks according to a preset rule, and marking each first block with a first score of oxidation degree according to a first division standard of oxidation degree, wherein the oxidation degree score in the first division standard is determined according to relative oxidation degree;
dividing each second image into a plurality of second areas according to a preset rule, and marking each second block with a second score of the oxidation degree according to a second division standard of the oxidation degree, wherein the oxidation degree score in the second division standard is determined according to the relative oxidation degree, and the first division standard is different from the second division standard;
the first region marked with the first score is used as a first training sample, and the second block marked with the second score is used as a second training sample.
Further, the obtaining a first scoring model based on the first training sample and the first training model, and obtaining a second scoring model based on the second training sample and the second training model, includes:
inputting the first training sample into the first training model, and extracting a first characteristic;
performing similarity processing on the first features to obtain first target features, wherein the first target similarity of the first target features meets a first preset similarity;
feature fusion is carried out on the first target feature and the first feature to obtain a first output result of the first training model, and continuous training is carried out until a first scoring model is obtained;
inputting the second training sample into the second training model, and extracting a second characteristic;
performing similarity processing on the second features to obtain second target features, wherein second target similarity of the second target features meets second preset similarity;
and carrying out feature fusion on the second target features and the second features to obtain a second output result of the second training model, and continuously training until a second scoring model is obtained.
Further, the obtaining the scoring result of the overall furnace tube with the lifetime to be scored based on the first target image and the first scoring model and the second target image and the second scoring model includes:
inputting the first target image into a first scoring model, wherein the first scoring model outputs the score of each first block on the outer surface of the integral furnace tube;
determining a first scoring result of each of the four high circumferential orientation regions on the overall furnace tube based on the score of each first block;
inputting the second target image into a second scoring model, and outputting the score of each second block of the machined smooth surface areas on two sides of each weld joint of the whole furnace tube by the second scoring model;
determining second scoring results of four facing areas in the circumferential direction of the machined smooth surface areas on two sides of each weld joint on the whole furnace tube based on the score of each second block;
and obtaining the scoring result of the integral furnace tube with the service life to be scored based on the first scoring result and the second scoring result.
Further, the determining the remaining life of the overall furnace tube with the life to be scored based on the scoring result comprises:
based on the scoring result of the integral furnace tube, determining an orientation region with the highest scoring result on each height of the integral furnace tube, namely a region with the highest oxidation degree;
and determining the residual service life of the whole furnace tube with the service life to be scored based on the area with the highest oxidation degree.
In a second aspect, the present invention further provides an integral furnace tube lifetime analysis device, where the integral furnace tube is formed by welding a plurality of sections of furnace tubes, and the integral furnace tube includes a furnace tube outer surface area and machining light surface areas on two sides of a welding seam, and the integral furnace tube comprises:
the first acquisition module is used for acquiring first images of the outer surface areas of the N furnace tubes and second images of machined smooth surface areas on two sides of welding seams of the N furnace tubes;
the labeling module is used for dividing each first image into a plurality of first blocks, labeling a first score of oxidation degree for each first block, dividing each second image into a plurality of second blocks, labeling a second score of oxidation degree for each second block, taking the first block labeled with the first score as a first training sample, and taking the second block labeled with the second score as a second training sample;
the first obtaining module is used for obtaining a first scoring model based on the first training sample and the first training model and obtaining a second scoring model based on the second training sample and the second training model;
the second acquisition module is used for acquiring a first target image of the outer surface area of the whole furnace tube with the service life to be scored and a second target image of machined smooth surface areas at two sides of the welding line;
the second obtaining module is used for obtaining the scoring result of the integral furnace tube with the service life to be scored based on the first target image and the first scoring model and the second target image and the second scoring model;
and the determining module is used for determining the residual life of the whole furnace tube with the life to be scored based on the scoring result.
In a third aspect, the present invention also provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method steps described in the first aspect when the program is executed.
In a fourth aspect, the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method steps described in the first aspect.
One or more technical solutions in the embodiments of the present invention at least have the following technical effects or advantages:
the invention provides a life analysis method of an integral furnace tube, which is formed by welding a plurality of sections of furnace tubes, wherein the integral furnace tube comprises a furnace tube outer surface area and machined smooth surface areas at two sides of a welding line, and comprises the following steps: acquiring first images of N furnace tube outer surface areas and second images of machining smooth surface areas on two sides of welding seams of N furnace tubes; dividing each first image into a plurality of first blocks, marking a first score of oxidation degree for each first block, dividing each second image into a plurality of second blocks, marking a second score of oxidation degree for each second region, taking the first block marked with the first score as a first training sample, and taking the second block marked with the second score as a second training sample; obtaining a first scoring model based on the first training sample and the first training model, and obtaining a second scoring model based on the second training sample and the second training model; acquiring a first target image of an outer surface area of the whole furnace tube of the service life to be scored and a second target image of machining smooth surface areas on two sides of a welding line; based on the first target image and the first scoring model as well as the second target image and the second scoring model, scoring results of the whole furnace tube with the service life to be scored are obtained, and the oxidation degrees of different areas are determined by respectively carrying out visual analysis on the outer surface of the furnace tube and the machined light surfaces on two sides of the welding seam, so that the residual service life of the whole furnace tube is finally obtained, and the degree of the furnace tube affected by high temperature is comprehensively and accurately evaluated.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also throughout the drawings, like reference numerals are used to designate like parts. In the drawings:
FIG. 1 is a schematic flow chart showing the steps of a method for analyzing the lifetime of an integral furnace tube in an embodiment of the invention;
FIG. 2 is a schematic diagram showing the structure of an integral furnace tube in an embodiment of the invention;
FIG. 3 is a schematic diagram of labeling a first score with a first image in an embodiment of the invention;
FIG. 4 is a schematic diagram of labeling a second score with a second image in an embodiment of the invention;
FIG. 5 shows a schematic structural diagram of a first training model and a second training model in an embodiment of the present invention;
FIG. 6 is a graph showing a first scoring result curve of the outer surface of the integral furnace tube in the same orientation region at different heights in different periods according to the embodiment of the present invention;
FIG. 7 is a graph showing a first scoring result curve of four orientation regions of different heights of the outer surface of the integral furnace tube at the same time in an embodiment of the present invention;
FIG. 8 is a schematic diagram showing a structure of an overall furnace tube lifetime analysis device in an embodiment of the invention;
FIG. 9 is a schematic diagram of a computer device for implementing a method for analyzing overall furnace lifetime in an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Example 1
The embodiment of the invention provides a method for analyzing the service life of an integral furnace tube, which is shown in fig. 1 and comprises the following steps:
s101, acquiring first images of the outer surface areas of N furnace tubes and second images of machined smooth surface areas on two sides of welding seams of the N furnace tubes;
s102, dividing each first image into a plurality of first blocks, marking a first score of oxidation degree for each first block, dividing each second image into a plurality of second blocks, marking a second score of oxidation degree for each second block, taking the first block marked with the first score as a first training sample, and taking the second block marked with the second score as a second training sample;
s103, obtaining a first scoring model based on the first training sample and the first training model, and obtaining a second scoring model based on the second training sample and the second training model;
s104, acquiring a first target image of an outer surface area of the whole furnace tube of the service life to be scored and a second target image of machining smooth surface areas on two sides of a welding line;
s105, obtaining a scoring result of the whole furnace tube with the service life to be scored based on the first target image and the first scoring model and the second target image and the second scoring model;
and S106, determining the residual life of the whole furnace tube with the life to be scored based on the scoring result.
Firstly, the whole furnace tube is formed by welding 2-3 furnace tubes, a welding line is formed between every two adjacent furnace tubes, and in the method, the outer surface area of each furnace tube and the machining surface areas on two sides of the welding line are respectively analyzed to obtain a first scoring result aiming at the outer surface area of the furnace tube and a second scoring result aiming at the machining surface areas on two sides of the welding line.
The following describes in detail the analysis of the oxidation degree of each region:
s101, acquiring first images of the outer surface areas of N furnace tubes and second images of machined smooth surface areas on two sides of welding seams of the N furnace tubes. Specifically, as shown in fig. 2, an example of an integral furnace tube is taken, wherein the region of the outer surface of the furnace tube is indicated by 201, and the machined regions on two sides of the weld joint are indicated by 202.
And obtaining N groups of images by acquiring images of two areas corresponding to the N furnace tubes, wherein each group of images comprises a first image and a second image.
Next, S102 is executed, where each first image is segmented into a plurality of first blocks, and a first score of the oxidation degree is marked for each first block; and dividing each second image into a plurality of second blocks, marking a second score of the oxidation degree for each second block, taking the first block marked with the first score as a first training sample, and taking the second block marked with the second score as a second training sample.
In a specific embodiment, each first image is segmented into a plurality of first blocks according to a preset rule, and each first block is marked with a first score of oxidation degree according to a first division standard of oxidation degree, wherein the oxidation degree score in the first division standard is determined according to the relative oxidation degree.
As shown in fig. 3, the number marked in a first block is the first score corresponding to the first block. The preset rule is to divide the first image equally into a plurality of rectangular areas, and of course, the first image may also be divided equally into regular hexagons and the like, which is not limited herein.
And then dividing each second image into a plurality of second areas according to a preset rule, marking each second area with a second score of the oxidation degree according to a second division standard of the oxidation degree, wherein the oxidation degree score in the second division standard is determined according to the relative oxidation degree, and the first division standard is different from the second division standard.
The first image and the second image correspond to different material areas of the furnace tube respectively, so that the evaluation standards of the oxidation degree are different. As shown in fig. 4, the number marked in a second image is the second score corresponding to the second region.
And finally, taking the first region marked with the first score as a first training sample, and taking the second region marked with the second score as a second training sample.
After obtaining the first training sample and the second training sample, S103 is executed, a first scoring model is obtained based on the first training sample and the first training model, and a second scoring model is obtained based on the second training sample and the second training model.
The first training model and the second training model may each employ a CNN model, an RNN model, an LSTM model, or the like.
Specifically, inputting a first training sample into a first training model, and extracting a first characteristic; performing similarity processing on the first features to obtain first target features, wherein the first target similarity of the first target features meets a first preset similarity;
feature fusion is carried out on the first target feature and the first feature to obtain a first output result of the first training model, and continuous training is carried out until a first scoring model is obtained;
inputting the second training sample into a second training model, and extracting second characteristics; performing similarity processing on the second features to obtain second target features, wherein second target similarity of the second target features meets second preset similarity;
and carrying out feature fusion on the second target features and the second features to obtain a second output result of the second training model, and continuously training until a second scoring model is obtained.
The first training model and the second training model have structures as shown in fig. 5, including an encoder, a memory bank, and a decoder, and when the first training samples are input into the first training model,extracting a first feature from a first training sample through an encoder, wherein the extracted F1 feature and the extracted F4 feature are subjected to similarity processing to obtain a first target feature, namely F1 ‘ Characterization sum F4 ’ The feature, the first target similarity of the first target feature satisfies a first preset similarity. And fusing the first target feature with the first feature, finally obtaining a first output result through decoding of a decoder (decoding layer), and continuously training the first target feature, wherein the parameters in the first training model are adjusted in each training process until a first scoring model is obtained. Similarly, the second scoring model is also obtained as described above. Thereby yielding a second scoring model.
After the first scoring model and the second scoring model are obtained, S104 is executed, and a first target image of the outer surface area of the whole furnace tube of the service life to be scored and a second target image of machined light surface areas on two sides of the welding line are obtained.
First, the first target image may have a plurality of images, and the second target image may have a plurality of images.
The first target image may also be segmented and the second target image may be segmented according to the process of S102 before the first scoring model and the second scoring model are applied. And (2) inputting the multiple segmented regional images into a first scoring model or a second scoring model respectively, and executing S105 to obtain scoring results of the whole furnace tube with the service life to be scored based on the first target image and the first scoring model and the second target image and the second scoring model.
Specifically, inputting a first target image into a first scoring model, wherein the first scoring model outputs the score of each first block on the outer surface of the whole furnace tube;
based on the score of each first block, determining a first scoring result of each of the four high circumferential orientation areas on the whole furnace tube. The first scoring result of each facing region may be obtained by averaging the scores of all the first blocks at the same height of the facing region.
As shown in fig. 6, the first scoring results corresponding to different heights in the same orientation region (east side) for the whole furnace tube at different times (new furnace tube time, one year of use, two years of use, and three years of use). It can be seen that with the increase of time, the oxidation degree of the same orientation region gradually increases, and the oxidation degree is particularly obvious for 2 m-7 m.
As shown in FIG. 7, the first scoring results corresponding to different heights of the whole furnace tube in different orientation areas in the same period are shown. It can be seen that for the whole furnace tube used for three years, the oxidation degree of the western side of the whole furnace tube is smaller, the oxidation degrees of the southern side and the north side are equivalent, the oxidation degree of the eastern side is higher, and the oxidation degree is more obvious between 2m and 7 m.
Inputting a second target image into a second scoring model, and outputting the score of each second block of the machined smooth surface areas on two sides of each weld joint of the whole furnace tube by the second scoring model;
and determining second scoring results of four facing areas in the circumferential direction of the machined smooth surface areas at two sides of each welding seam on the whole furnace tube based on the score of each second block. The second scoring result for each facing region may be obtained by averaging the scores of all the first blocks at the same height of the facing region.
The second scoring result is discontinuous for the four facing areas circumferentially on both sides of each weld machined plain area. The method can be combined with the illustration of the first scoring result obtained by the first scoring model, and the correctness of the second scoring result of the second scoring model is judged, namely, if the curve formed by the discrete data of the second scoring result is the same as or similar to the curve change trend as shown in fig. 6 or fig. 7, namely, the first scoring result corresponding to the height of the welding position of the adjacent furnace tube is similar to the second scoring result, the two scoring models are determined to be accurate.
And obtaining the scoring result of the whole furnace tube with the service life to be scored based on the first scoring result and the second scoring result.
The first scoring model can score the oxidation degree of each block on the outer surface of the furnace tube, and the second scoring model can score the oxidation degree of each block on the machined light surface area on two sides of the weld.
Finally, S106 is executed, and the residual life of the whole furnace tube with the life to be scored is determined based on the scoring result. Specifically, based on the scoring result of the integral furnace tube, determining an orientation area with the highest scoring result on each height of the integral furnace tube, namely an area with the highest oxidation degree; and determining the residual life of the whole furnace tube with the life to be scored based on the area with the highest oxidation degree.
For example, it can be determined from fig. 7 that the direction region with the highest scoring result at each height of the overall furnace tube is the eastern side, and that the oxidation degree is greater in the middle section, that is, the section of 2 to 7m, than in the other sections, and therefore, the remaining lifetime of the overall furnace tube with the lifetime to be scored is determined based on the region with the highest oxidation degree.
If the oxidation degree of the eastern side of the integral furnace tube is high, the residual service life of the corresponding integral furnace tube is shorter; if the oxidation degree of the eastern side of the integral furnace tube is not high, the residual life of the corresponding integral furnace tube is long.
One or more technical solutions in the embodiments of the present invention at least have the following technical effects or advantages:
the invention provides a life analysis method of an integral furnace tube, which is formed by welding a plurality of sections of furnace tubes, wherein the integral furnace tube comprises a furnace tube outer surface area and machined smooth surface areas at two sides of a welding line, and comprises the following steps: acquiring first images of N furnace tube outer surface areas and second images of machining smooth surface areas on two sides of welding seams of N furnace tubes; dividing each first image into a plurality of first blocks, marking a first score of oxidation degree for each first block, dividing each second image into a plurality of second blocks, marking a second score of oxidation degree for each second region, taking the first block marked with the first score as a first training sample, and taking the second block marked with the second score as a second training sample; obtaining a first scoring model based on the first training sample and the first training model, and obtaining a second scoring model based on the second training sample and the second training model; acquiring a first target image of an outer surface area of the whole furnace tube of the service life to be scored and a second target image of machining smooth surface areas on two sides of a welding line; based on the first target image and the first scoring model as well as the second target image and the second scoring model, scoring results of the whole furnace tube with the service life to be scored are obtained, and the oxidation degrees of different areas are determined by respectively carrying out visual analysis on the outer surface of the furnace tube and the machined light surfaces on two sides of the welding seam, so that the residual service life of the whole furnace tube is finally obtained, and the degree of the furnace tube affected by high temperature is comprehensively and accurately evaluated.
Example two
Based on the same inventive concept, the embodiment of the invention also provides a whole furnace tube service life analysis device, wherein the whole furnace tube is formed by welding a plurality of sections of furnace tubes, and comprises a furnace tube outer surface area and two sides of a welding seam machining light surface area, as shown in fig. 8, and the whole furnace tube comprises:
a first obtaining module 801, configured to obtain a first image of an outer surface area of N furnace tubes and a second image of machined smooth areas on two sides of a weld seam of the N furnace tubes;
the labeling module 802 is configured to segment each first image into a plurality of first blocks, label each first block with a first score of oxidation degree, segment each second image into a plurality of second blocks, label each second block with a second score of oxidation degree, use the first block labeled with the first score as a first training sample, and use the second block labeled with the second score as a second training sample;
a first obtaining module 803, configured to obtain a first scoring model based on the first training sample and the first training model, and obtain a second scoring model based on the second training sample and the second training model;
a second obtaining module 804, configured to obtain a first target image of an outer surface area of the overall furnace tube for the lifetime to be scored and a second target image of machined smooth surface areas on two sides of the weld;
a second obtaining module 805, configured to obtain a scoring result of the overall furnace tube of the lifetime to be scored based on the first target image and the first scoring model and the second target image and the second scoring model;
a determining module 806, configured to determine a remaining lifetime of the overall furnace tube of the lifetime to be scored based on the scoring result.
In an alternative embodiment, the first acquiring module 801 is configured to acquire, by using a plurality of image capturing devices provided on the climbing robot, a first image of an outer surface area of the furnace tube and a second image of machined light surface areas on two sides of a weld seam of the furnace tube for the circumferential direction and the longitudinal direction of the N integral furnace tubes.
In an alternative embodiment, the labeling module 802 is configured to:
dividing each first image into a plurality of first blocks according to a preset rule, and marking each first block with a first score of oxidation degree according to a first division standard of oxidation degree, wherein the oxidation degree score in the first division standard is determined according to relative oxidation degree;
dividing each second image into a plurality of second areas according to a preset rule, and marking each second block with a second score of the oxidation degree according to a second division standard of the oxidation degree, wherein the oxidation degree score in the second division standard is determined according to the relative oxidation degree, and the first division standard is different from the second division standard;
the first region marked with the first score is used as a first training sample, and the second block marked with the second score is used as a second training sample.
In an alternative embodiment, the first obtaining module 803 is configured to:
inputting the first training sample into the first training model, and extracting a first characteristic;
performing similarity processing on the first features to obtain first target features, wherein the first target similarity of the first target features meets a first preset similarity;
feature fusion is carried out on the first target feature and the first feature to obtain a first output result of the first training model, and continuous training is carried out until a first scoring model is obtained;
inputting the second training sample into the second training model, and extracting a second characteristic;
performing similarity processing on the second features to obtain second target features, wherein second target similarity of the second target features meets second preset similarity;
and carrying out feature fusion on the second target features and the second features to obtain a second output result of the second training model, and continuously training until a second scoring model is obtained.
In an alternative embodiment, the second obtaining module 805 is configured to:
inputting the first target image into a first scoring model, wherein the first scoring model outputs the score of each first block on the outer surface of the integral furnace tube;
determining a first scoring result of each of the four high circumferential orientation regions on the overall furnace tube based on the score of each first block;
inputting the second target image into a second scoring model, and outputting the score of each second block of the machined smooth surface areas on two sides of each weld joint of the whole furnace tube by the second scoring model;
determining second scoring results of four facing areas in the circumferential direction of the machined smooth surface areas on two sides of each weld joint on the whole furnace tube based on the score of each second block;
and obtaining the scoring result of the integral furnace tube with the service life to be scored based on the first scoring result and the second scoring result.
In an alternative embodiment, the determining module 806 is configured to:
based on the scoring result of the integral furnace tube, determining an orientation area with the highest scoring result on each height of the integral furnace tube, namely an area with the highest oxidation degree;
and determining the residual service life of the whole furnace tube with the service life to be scored based on the area with the highest oxidation degree.
Example III
Based on the same inventive concept, an embodiment of the present invention provides a computer device, as shown in fig. 9, including a memory 904, a processor 902, and a computer program stored in the memory 904 and capable of running on the processor 902, where the processor 902 implements the steps of the above-mentioned overall furnace lifetime analysis method when executing the program.
Where in FIG. 9 a bus architecture (represented by bus 900), bus 900 may include any number of interconnected buses and bridges, with bus 900 linking together various circuits, including one or more processors, represented by processor 902, and memory, represented by memory 904. Bus 900 may also link together various other circuits such as peripheral devices, voltage regulators, power management circuits, etc., as are well known in the art and, therefore, will not be described further herein. The bus interface 906 provides an interface between the bus 900 and the receiver 901 and the transmitter 903. The receiver 901 and the transmitter 903 may be the same element, i.e. a transceiver, providing a unit for communicating with various other apparatus over a transmission medium. The processor 902 is responsible for managing the bus 900 and general processing, while the memory 904 may be used to store data used by the processor 902 in performing operations.
Example IV
Based on the same inventive concept, embodiments of the present invention provide a computer readable storage medium having a computer program stored thereon, which when executed by a processor, implements the steps of the above-described overall furnace tube lifetime analysis method.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a construction of such a system is apparent from the description above. In addition, the present invention is not directed to any particular programming language. It will be appreciated that the teachings of the present invention described herein may be implemented in a variety of programming languages, and the above description of specific languages is provided for disclosure of enablement and best mode of the present invention.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed invention requires more features than are expressly recited in each embodiment. Rather, as each embodiment reflects, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in a specific implementation, any of the claimed embodiments may be used in any combination.
Various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in the overall furnace tube life analysis device, computer apparatus, according to embodiments of the present invention. The present invention can also be implemented as an apparatus or device program (e.g., a computer program and a computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present invention may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names.
Claims (9)
1. The utility model provides a whole furnace tube life-span analysis method, whole furnace tube is formed by the welding of multisection furnace tube, and whole furnace tube includes furnace tube surface area and weld both sides machine tooling plain noodles region, its characterized in that includes:
acquiring first images of N furnace tube outer surface areas and second images of machining smooth surface areas on two sides of welding seams of N furnace tubes;
dividing each first image into a plurality of first blocks, marking a first score of oxidation degree for each first block, dividing each second image into a plurality of second blocks, marking a second score of oxidation degree for each second block, taking the first block marked with the first score as a first training sample, and taking the second block marked with the second score as a second training sample;
obtaining a first scoring model based on the first training sample and the first training model, and obtaining a second scoring model based on the second training sample and the second training model;
acquiring a first target image of an outer surface area of the whole furnace tube of the service life to be scored and a second target image of machining smooth surface areas on two sides of a welding line;
obtaining a scoring result of the whole furnace tube with the service life to be scored based on the first target image and the first scoring model and the second target image and the second scoring model;
and determining the residual life of the whole furnace tube with the life to be scored based on the scoring result.
2. The method of claim 1, wherein the acquiring a first image of the N furnace tube exterior surface regions and a second image of the N furnace tube weld two-sided machined plain regions comprises:
and a plurality of image acquisition devices arranged on the climbing robot are used for acquiring first images of the outer surface areas of the N whole furnace tubes and second images of machining smooth surface areas on two sides of the welding seam of the furnace tube in the circumferential direction and the longitudinal direction of the N whole furnace tubes.
3. The method of claim 1, wherein the segmenting each first image into a plurality of first tiles and labeling each first tile with a first score for the degree of oxidation, segmenting each second image into a plurality of second tiles and labeling each second tile with a second score for the degree of oxidation, taking the first tile labeled with the first score as a first training sample and the second tile labeled with the second score as a second training sample comprises:
dividing each first image into a plurality of first blocks according to a preset rule, and marking each first block with a first score of oxidation degree according to a first division standard of oxidation degree, wherein the oxidation degree score in the first division standard is determined according to relative oxidation degree;
dividing each second image into a plurality of second areas according to a preset rule, and marking each second block with a second score of the oxidation degree according to a second division standard of the oxidation degree, wherein the oxidation degree score in the second division standard is determined according to the relative oxidation degree, and the first division standard is different from the second division standard;
the first region marked with the first score is used as a first training sample, and the second block marked with the second score is used as a second training sample.
4. The method of claim 1, wherein the obtaining a first scoring model based on the first training sample and the first training model, and obtaining a second scoring model based on the second training sample and the second training model, comprises:
inputting the first training sample into the first training model, and extracting a first characteristic;
performing similarity processing on the first features to obtain first target features, wherein the first target similarity of the first target features meets a first preset similarity;
feature fusion is carried out on the first target feature and the first feature to obtain a first output result of the first training model, and continuous training is carried out until a first scoring model is obtained;
inputting the second training sample into the second training model, and extracting a second characteristic;
performing similarity processing on the second features to obtain second target features, wherein second target similarity of the second target features meets second preset similarity;
and carrying out feature fusion on the second target features and the second features to obtain a second output result of the second training model, and continuously training until a second scoring model is obtained.
5. The method of claim 1, wherein the obtaining the scoring result of the overall furnace tube for the lifetime to be scored based on the first target image and the first scoring model and the second target image and the second scoring model comprises:
inputting the first target image into a first scoring model, wherein the first scoring model outputs the score of each first block on the outer surface of the integral furnace tube;
determining a first scoring result of each of the four high circumferential orientation regions on the overall furnace tube based on the score of each first block;
inputting the second target image into a second scoring model, and outputting the score of each second block of the machined smooth surface areas on two sides of each weld joint of the whole furnace tube by the second scoring model;
determining second scoring results of four facing areas in the circumferential direction of the machined smooth surface areas on two sides of each weld joint on the whole furnace tube based on the score of each second block;
and obtaining the scoring result of the integral furnace tube with the service life to be scored based on the first scoring result and the second scoring result.
6. The method of claim 1, wherein the determining the remaining lifetime of the overall furnace tube for the lifetime to be scored based on the scoring result comprises:
based on the scoring result of the integral furnace tube, determining an orientation area with the highest scoring result on each height of the integral furnace tube, namely an area with the highest oxidation degree;
and determining the residual service life of the whole furnace tube with the service life to be scored based on the area with the highest oxidation degree.
7. The utility model provides an integral furnace tube life-span analytical equipment, integral furnace tube is formed by the welding of multisection furnace tube, just integral furnace tube includes furnace tube surface area and welding seam both sides machine tooling plain noodles region, its characterized in that includes:
the first acquisition module is used for acquiring first images of the outer surface areas of the N furnace tubes and second images of machined smooth surface areas on two sides of welding seams of the N furnace tubes;
the labeling module is used for dividing each first image into a plurality of first blocks, labeling a first score of oxidation degree for each first block, dividing each second image into a plurality of second blocks, labeling a second score of oxidation degree for each second block, taking the first block labeled with the first score as a first training sample, and taking the second block labeled with the second score as a second training sample;
the first obtaining module is used for obtaining a first scoring model based on the first training sample and the first training model and obtaining a second scoring model based on the second training sample and the second training model;
the second acquisition module is used for acquiring a first target image of the outer surface area of the whole furnace tube with the service life to be scored and a second target image of machined smooth surface areas at two sides of the welding line;
the second obtaining module is used for obtaining the scoring result of the integral furnace tube with the service life to be scored based on the first target image and the first scoring model and the second target image and the second scoring model;
and the determining module is used for determining the residual life of the whole furnace tube with the life to be scored based on the scoring result.
8. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method steps of any of claims 1 to 6 when the program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method steps of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311486937.XA CN117218132B (en) | 2023-11-09 | 2023-11-09 | Whole furnace tube service life analysis method, device, computer equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311486937.XA CN117218132B (en) | 2023-11-09 | 2023-11-09 | Whole furnace tube service life analysis method, device, computer equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117218132A CN117218132A (en) | 2023-12-12 |
| CN117218132B true CN117218132B (en) | 2024-01-19 |
Family
ID=89039396
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311486937.XA Active CN117218132B (en) | 2023-11-09 | 2023-11-09 | Whole furnace tube service life analysis method, device, computer equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117218132B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104502459A (en) * | 2014-12-08 | 2015-04-08 | 中国特种设备检测研究院 | Acoustic emission-based method for diagnosing furnace tube |
| WO2022077917A1 (en) * | 2020-10-14 | 2022-04-21 | 平安科技（深圳）有限公司 | Instance segmentation model sample screening method and apparatus, computer device and medium |
| CN116429269A (en) * | 2023-01-19 | 2023-07-14 | 中国石油化工股份有限公司 | Infrared intelligent analysis system for ethylene cracking furnace tube |
| CN116702463A (en) * | 2023-06-01 | 2023-09-05 | 上海发电设备成套设计研究院有限责任公司 | Method, device, equipment and storage medium for predicting residual life of heating surface pipe |
-
2023
- 2023-11-09 CN CN202311486937.XA patent/CN117218132B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104502459A (en) * | 2014-12-08 | 2015-04-08 | 中国特种设备检测研究院 | Acoustic emission-based method for diagnosing furnace tube |
| WO2022077917A1 (en) * | 2020-10-14 | 2022-04-21 | 平安科技（深圳）有限公司 | Instance segmentation model sample screening method and apparatus, computer device and medium |
| CN116429269A (en) * | 2023-01-19 | 2023-07-14 | 中国石油化工股份有限公司 | Infrared intelligent analysis system for ethylene cracking furnace tube |
| CN116702463A (en) * | 2023-06-01 | 2023-09-05 | 上海发电设备成套设计研究院有限责任公司 | Method, device, equipment and storage medium for predicting residual life of heating surface pipe |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117218132A (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Aust et al. | Comparative analysis of human operators and advanced technologies in the visual inspection of aero engine blades | |
| JP7085067B2 (en) | Corrosion generation prediction model under heat insulating material and plant maintenance support device | |
| US11982998B2 (en) | Manufacturing monitoring assistance device, manufacturing monitoring assistance method, and manufacturing monitoring assistance program | |
| CN117218132B (en) | Whole furnace tube service life analysis method, device, computer equipment and medium | |
| Pereira et al. | Quality assessment and process management of welded joints in metal construction—A review | |
| Aust et al. | Evaluation of influence factors on the visual inspection performance of aircraft engine blades | |
| Gbagba et al. | Advances in Machine Learning Techniques Used in Fatigue Life Prediction of Welded Structures | |
| Radionov et al. | Method for forecasting the remaining useful life of a furnace transformer based on online monitoring data | |
| Gros et al. | Theory and implementation of NDT data fusion | |
| García González et al. | Analysis of Tube-to-Tubesheet Welding in Carbon Steel Heat Exchangers of a Double Plate Header Box | |
| Gujre et al. | Machine learning algorithms for failure prediction and yield improvement during electric resistance welded tube manufacturing | |
| Hagarová et al. | Effect of flue gases’ corrosive components on the degradation process of evaporator tubes | |
| Naranjo et al. | A scoping review of pipeline maintenance methodologies based on industry 4.0 | |
| Thayer | Enabling the Fourth Industrial Revolution (4IR) and the role of NDE and monitoring | |
| Adams et al. | Correlating variations in the dynamic resistance signature to weld strength in resistance spot welding using principal component analysis | |
| Jamrozik | Contextual reliability discounting in welding process diagnostic based on DSmT | |
| JP2954613B2 (en) | Plant life diagnosis support equipment | |
| Yasuda et al. | Fatigue crack detection system based on IoT and statistical analysis | |
| Katunin et al. | Monitoring of hidden corrosion growth in aircraft structures based on D-Sight inspections and image processing | |
| CN117218113B (en) | Furnace tube oxidation degree analysis method, device, computer equipment and medium | |
| Al-Subaiei et al. | Industry 4.0 smart predictive maintenance in the oil industry to enable near-zero downtime in operations | |
| Uliasz et al. | Automatic Evaluation of the Robotic Production Process for an Aircraft Jet Engine Casing | |
| Wärmefjord et al. | A measure of the information loss for inspection point reduction | |
| Marić et al. | Quality Analysis of AISI 321 Welds of Bellow Compensators Used in Shipbuilding | |
| Pilić et al. | Innovative approach of damage mechanism identification for energy equipment–A case study of oil refinery |
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 |