CN117635617A - Rapid calculation processing method and system based on high-entropy alloy data - Google Patents
Rapid calculation processing method and system based on high-entropy alloy data Download PDFInfo
- Publication number
- CN117635617A CN117635617A CN202410108174.3A CN202410108174A CN117635617A CN 117635617 A CN117635617 A CN 117635617A CN 202410108174 A CN202410108174 A CN 202410108174A CN 117635617 A CN117635617 A CN 117635617A
- Authority
- CN
- China
- Prior art keywords
- rust
- sampling
- night
- circle
- entropy alloy
- 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.)
- Granted
Links
- 239000000956 alloy Substances 0.000 title claims abstract description 118
- 229910045601 alloy Inorganic materials 0.000 title claims abstract description 118
- 238000004364 calculation method Methods 0.000 title claims abstract description 33
- 238000003672 processing method Methods 0.000 title claims abstract description 23
- 238000005070 sampling Methods 0.000 claims abstract description 215
- 238000000576 coating method Methods 0.000 claims abstract description 86
- 239000011248 coating agent Substances 0.000 claims abstract description 83
- 238000001931 thermography Methods 0.000 claims abstract description 67
- 238000012545 processing Methods 0.000 claims abstract description 36
- 238000000034 method Methods 0.000 claims abstract description 25
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 claims description 191
- 230000009466 transformation Effects 0.000 claims description 57
- 239000013598 vector Substances 0.000 claims description 54
- 230000000422 nocturnal effect Effects 0.000 claims description 41
- 239000011159 matrix material Substances 0.000 claims description 39
- 238000003384 imaging method Methods 0.000 claims description 30
- 238000011282 treatment Methods 0.000 claims description 21
- 230000002265 prevention Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 6
- 238000005260 corrosion Methods 0.000 abstract description 21
- 230000000694 effects Effects 0.000 abstract description 6
- 230000007797 corrosion Effects 0.000 description 16
- 230000006870 function Effects 0.000 description 8
- 238000005286 illumination Methods 0.000 description 8
- 238000012544 monitoring process Methods 0.000 description 7
- 238000003062 neural network model Methods 0.000 description 6
- 238000013461 design Methods 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 230000003203 everyday effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000002354 daily effect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 239000006104 solid solution Substances 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000005536 corrosion prevention Methods 0.000 description 1
- 239000013078 crystal Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 239000003112 inhibitor Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000007261 regionalization Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000004381 surface treatment Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000008719 thickening Effects 0.000 description 1
- 238000011269 treatment regimen Methods 0.000 description 1
Abstract
The invention provides a rapid calculation processing method and a rapid calculation processing system based on high-entropy alloy data, which belong to the field of data processing, divide the surface of a high-entropy alloy coating into a plurality of sampling circles, acquire images of each sampling circle in day and night and infrared thermal imaging of each sampling circle in a plurality of days, calculate a day image time sequence and a night image time sequence corresponding to the sampling circles, and a day thermal imaging time sequence and a night thermal imaging time sequence, and mark the sampling circles to be optimized on the surface of the high-entropy alloy coating. The method can more accurately determine the area to be processed, more quickly utilize statistical characteristics, improve the anti-corrosion effect and avoid unnecessary processing of all sampling circles.
Description
Technical Field
The invention belongs to the field of data processing, and particularly relates to a rapid calculation processing method and system based on high-entropy alloy data.
Background
The high-entropy alloy coating is widely applied to the surfaces of various large buildings, and the surface of the high-entropy alloy coating has strong corrosion resistance in theory, however, in practice, especially in tropical and subtropical monsoon climates such as two broad areas and Hainan areas, the temperature difference between day and night is large, and the temperature or the rising or falling variation of each part on the surface of the high-entropy alloy coating is different due to the difference of the sun angle, the different irradiated parts and the different irradiation time and intensity, even if the variation amplitude of each region on the surface of the heating or cooling is also greatly different. Especially, the original surface area of a large building is very large, the facing azimuth angle difference is also large, and uneven cold and hot shrinkage and expansion of each part causes the surface of the high-entropy alloy coating to generate inconspicuous stretching tearing, so that the corrosion rust becomes organic and multiplicable. However, the probability of occurrence of corrosion rust on the surface of the high-entropy alloy coating to the part is very difficult to observe in time by naked eyes, and the monitoring of the diurnal temperature variation fluctuation degree of the high-entropy alloy coating by combining image detection with infrared thermal imaging is needed to perform rust prevention treatment on the sampling circle to be optimized more quickly.
In solving the problem of corrosion rust of high-entropy alloy coatings under specific climatic conditions, conventional high-entropy alloy coating corrosion protection techniques currently generally rely on chemical coatings or surface treatments, such as the application of corrosion inhibitors. However, these methods may perform poorly under prolonged exposure to severe weather conditions, and it is difficult to cope with the corrosion rust problems of high-entropy alloy coatings caused by diurnal temperature fluctuations. Some of the prior art uses a fixed cycle test method, such as a test performed once a year or quarter. Such methods may not be able to discover corrosion rust problems caused by climate change in time, lacking in real-time and quick response. While some techniques only focus on one monitoring factor of the coating surface, such as temperature or light conditions, they fail to take full advantage of multi-factor analysis. This can lead to an incomplete understanding of the coating properties, affecting the accuracy of the corrosion protection treatment. Still other methods do not take into account the differential regionalization of large building surfaces, such as a high-entropy alloy coating binding force detection device described in patent publication No. CN217819935U, and although the ability to detect the binding force of the high-entropy alloy coating can be detected by applying pressure step by step, the lack of knowledge of the corrosive rust conditions of various parts of the coating surface can result in insufficient targeted control of actual problems. The prior art lacks precision in terms of corrosion protection treatment, may treat the entire surface extensively, wastes resources and may affect the appearance and performance of the coating.
Disclosure of Invention
The invention aims to provide a rapid calculation processing method and a rapid calculation processing system based on high-entropy alloy data, which are used for solving one or more technical problems in the prior art and at least providing a beneficial selection or creation condition.
The monitoring of the time sequence of the day and night images and the temperature fluctuation degree is introduced, and the performance of the high-entropy alloy coating under specific climatic conditions can be comprehensively, real-time and rapidly known by calculating the day rust transformation ratio vector and the night rust transformation ratio vector. Through differential regional analysis and accurate anti-corrosion treatment strategies, the defects of the prior art are hopefully overcome, and the anti-corrosion performance of the high-entropy alloy coating is improved.
In order to achieve the above object, according to an aspect of the present invention, there is provided a rapid calculation processing method based on high-entropy alloy data, the method comprising the steps of:
dividing the surface of the high-entropy alloy coating into a plurality of sampling circles, acquiring images of each sampling circle in day and night and infrared thermal imaging of each sampling circle in a plurality of days, and marking the sampling circles to be optimized on the surface of the high-entropy alloy coating by calculating a day image time sequence and a night image time sequence, a day thermal imaging time sequence and a night thermal imaging time sequence which correspond to the sampling circles.
The method comprises the steps of dividing the surface of the high-entropy alloy coating into a plurality of sampling circles, then, in a plurality of days, carrying out image shooting and infrared thermal imaging shooting on the surface of the high-entropy alloy coating day and night, respectively, obtaining images of each sampling circle and infrared thermal imaging thereof day and night, and calculating through an image recognition depth neural network model according to a day image time sequence and a night image time sequence, a day thermal imaging time sequence and a night thermal imaging time sequence corresponding to the sampling circle, so as to mark the sampling circle to be optimized on the surface of the high-entropy alloy coating, and carrying out rust prevention treatment on the sampling circle to be optimized. However, the data set required by calculation through the image recognition deep neural network model has large scale and long training time, and the method may not be sufficient for rapidly calculating, processing and marking the sampling circle to be optimized on the surface of the high-entropy alloy coating on a zero basis; but if the data has been prepared and the image recognition deep neural network model has been pre-trained, the process can quickly calculate the sample circle to be optimized on the high entropy alloy coating surface. The high-entropy alloy coating surface can be the surface of the outer wall of a building such as a stadium, an airport terminal, a library and the like. The high entropy alloy coating surface may be curved or planar.
Further, in the process of dividing the high-entropy alloy coating surface into a plurality of sampling circles, the coincidence area is allowed to exist between the sampling circles, the coincidence circle centers do not exist between the sampling circles, and all the sampling circles can completely cover the high-entropy alloy coating surface.
In some embodiments, the random sampling function of the image preprocessing module in the image processing open source tool can be used to select the centers of a plurality of different sampling circles, and the number of the sampling circles is repeatedly increased until all the sampling circles can completely cover the surface of the high-entropy alloy coating. In some embodiments, the radius of each sample circle is equal. In each day, the division of the sampling circles is unchanged, and the same sampling circle in each day continuously keeps a corresponding and consistent relation.
There are two images of day and night and two infrared thermal images of day and night each day. On the basis of the images and the infrared thermal imaging, dividing two images and two infrared thermal imaging of each day according to sampling circles, and respectively dividing the images and the infrared thermal imaging into a part of day and night images and a part of infrared thermal imaging of each day and night corresponding to each sampling circle.
Further, images of each sampling circle, which are respectively day and night, and infrared thermal imaging thereof are sequenced according to the time sequence of the date and the time, so as to obtain a day image time sequence and a night image time sequence, a day thermal imaging time sequence and a night thermal imaging time sequence which correspond to each sampling circle;
the elements in the diurnal image time sequence are called diurnal images, the elements in the night image time sequence are called night images, the elements in the diurnal imaging time sequence are called diurnal imaging, the elements in the night imaging time sequence are called night imaging, and the diurnal image, the night image, the diurnal imaging and the night imaging are all pixels of a round part of a corresponding sampling circle and the values thereof cut from a complete image matrix of the original high-entropy alloy coating surface, but for convenience in calculation, the diurnal image, the night image, the diurnal imaging and the night imaging are all placed in an image matrix with the minimum circumscribed rectangle size, because the circle is inconvenient to process in image preprocessing, redundant parts outside the sampling circle in the image matrix with the minimum circumscribed rectangle size are filled by uniformly using the values which do not affect the calculation of the values of the pixel values in the sampling circle.
The size of the image matrix, the sequence numbers of the rows and the columns in the image matrix and the positions of the rows and the columns are kept consistent, and the images and the infrared thermal imaging are stored in the form of data of the image matrix.
Further, a diurnal rust ratio vector and a nocturnal rust ratio vector of each sampling circle are calculated according to a diurnal image time sequence and a nocturnal image time sequence corresponding to each sampling circle:
preferably, for the night image time sequence corresponding to each sampling circle, except for the first night image, the rust value ratio of each remaining night image relative to the first night image is calculated and used as the night rust transformation ratio corresponding to the first night image, and for the first night image, the night rust transformation ratio corresponding to the first night image is the rust value ratio of the first night image relative to the first day image corresponding to the sampling circle, and the array obtained by the night rust transformation ratio values of each night image in the night image time sequence corresponding to each sampling circle is used as the night rust transformation ratio vector of the sampling circle. Thus, a diurnal rust ratio vector and a nocturnal rust ratio vector of each sampling circle are obtained. The purpose of designing and calculating the diurnal rust transformation ratio vector and the nocturnal rust transformation ratio vector of each sampling circle is to fully utilize the diurnal image time sequence, and the diurnal rust transformation ratio vector and the nocturnal rust transformation ratio vector are calculated to obtain the performance of each sampling circle under different illumination conditions. By calculating the diurnal rust transformation ratio vector and the nocturnal rust transformation ratio vector, the system can comprehensively understand the performance of the high-entropy alloy coating under different illumination conditions around the clock. Considering the fact that the temperature difference between day and night is large in tropical and subtropical monsoon climate, the design can more accurately capture the change of the surface of the coating under different temperature conditions. And because of the huge area of the surface of a large building and different azimuth angles, uneven cold and hot expansion of each part can cause the difficult-to-detect tensile tearing of the surface of the high-entropy alloy coating. By obtaining the diurnal rust transformation ratio vector and the nocturnal rust transformation ratio vector of each sampling circle, the system can accurately analyze the corrosion rust transformation probability of different areas on the surface of the coating, and further can pertinently perform rust prevention treatment. The system can timely discover potential corrosion rust problems by monitoring the time sequence of the day and night images in real time. And by combining with temperature monitoring, the method can respond more quickly and take optimization measures, so that the corrosion resistance of the high-entropy alloy coating can be timely protected. By fully utilizing the time sequence of the day and night images and calculating the day rust transformation ratio vector and the night rust transformation ratio vector, the performance of the high-entropy alloy coating under specific climatic conditions can be comprehensively, accurately and rapidly known, so that the rust prevention treatment is rapidly optimized, and the durability and the performance of the coating are improved.
Further, the method for calculating the rust surface sign value ratio comprises the following steps: the rust aspect ratio is a value that can be used for one image matrix relative to another image matrix to represent the change in the degree of rust occurring on the surface of the high-entropy alloy coating, and is calculated from the data characteristics of the two image matrices.
Preferably, the ratio of rust surface values of one image matrix to another image matrix is calculated, in order to reduce the calculation step and increase the calculation speed, the values of each row and column position of the one image matrix are removed by removing points from the values of each row and column position of the other image matrix, a matrix formed by the ratio of the values of each row and column position is obtained, and the mode of the values of elements on a diagonal line in the matrix formed by the ratio is used as the ratio of the rust surface values.
Further, a hot-face rust ratio vector is calculated according to a diurnal thermal imaging time sequence and a nocturnal thermal imaging time sequence corresponding to each sampling circle:
and the diurnal thermal imaging time sequence and the nocturnal thermal imaging time sequence corresponding to each sampling circle are aligned with each other according to the dimension, and the proportion value of the characteristic value of the diurnal thermal imaging of each day corresponding to the sampling circle relative to the characteristic value of the diurnal thermal imaging of the same day is calculated as the hot surface rust ratio of the same day of the sampling circle, and an array formed by the hot surface rust ratios of each day of the sampling circle is normalized to be called as a hot surface rust ratio vector.
In some embodiments, the alignment of the day and night data of the same day according to the dimensions may be performed, the feature values of the night thermal imaging and the feature values of the day thermal imaging may be calculated by using feature values of an image matrix, for example, each numerical value or an average value thereof on a diagonal line, and the ratio values between the feature values may be obtained by dividing the feature values of the two feature values after respectively performing the exponential processing.
Further, by calculating the diurnal rust real value, the nocturnal rust real value and the hot surface rust real value of the sampling circle, the sampling circle to be optimized on the surface of the high-entropy alloy coating is marked, and rust prevention treatment is carried out on the sampling circle to be optimized, specifically:
calculating an expected value of a diurnal rust transformation ratio vector of each sampling circle to serve as a diurnal rust transformation value of the sampling circle, calculating an expected value of a nocturnal rust transformation ratio vector of each sampling circle to serve as a nocturnal rust transformation value of the sampling circle, and calculating an expected value of a hot surface rust transformation ratio vector of each sampling circle to serve as a hot surface rust transformation value of the sampling circle;
calculating the proportion value of the mode of the diurnal rust variable value of each sampling circle relative to the diurnal rust variable value of all the sampling circles to be used as the diurnal rust variable value of the sampling circle, calculating the proportion value of the night rust variable value of each sampling circle relative to the mode of the night rust variable value of all the sampling circles to be used as the night rust variable value of the sampling circle, and calculating the proportion value of the hot face rust variable value of each sampling circle relative to the mode of the hot face rust variable value of all the sampling circles to be used as the hot face rust variable value of the sampling circle.
If the sampling circle exists, the constraint condition is satisfied: and if the diurnal rust real value of the sampling circle is larger than the hot surface rust real value of the sampling circle, and if the nocturnal rust real value of the sampling circle is larger than the hot surface rust real value of the sampling circle, marking the sampling circle meeting the constraint condition as a sampling circle to be optimized on the surface of the high-entropy alloy coating, and carrying out rust prevention treatment on the sampling circle to be optimized.
The invention also provides a rapid computing processing system based on the high-entropy alloy data, which comprises: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements steps in the rapid computing processing method based on high-entropy alloy data when the computer program is executed to control rapid computing processing based on high-entropy alloy data, the rapid computing processing system based on high-entropy alloy data can be run in a computing device such as a desktop computer, a notebook computer, a mobile phone, a palm computer and a cloud data center, and the executable system can include, but is not limited to, a processor, a memory, a server cluster, and the processor executes the computer program to run in units of the following systems:
the data sampling unit is used for dividing the surface of the high-entropy alloy coating into a plurality of sampling circles, and acquiring images of each sampling circle in day and night and infrared thermal imaging of each sampling circle;
the computing processing unit is used for computing a diurnal image time sequence and a night image time sequence corresponding to the sampling circle, and a diurnal imaging time sequence and a night imaging time sequence;
and the optimizing marking unit is used for marking a sampling circle to be optimized on the surface of the high-entropy alloy coating.
The beneficial effects of the invention are as follows: the invention provides a rapid calculation processing method and a rapid calculation processing system based on high-entropy alloy data, wherein the surface of a high-entropy alloy coating is divided into a plurality of sampling circles, images of each sampling circle in day and night and infrared thermal imaging thereof are acquired respectively, day image time sequences and night image time sequences corresponding to the sampling circles, and day thermal imaging time sequences and night thermal imaging time sequences are calculated, and the sampling circles to be optimized on the surface of the high-entropy alloy coating are marked. The method can more accurately determine the area to be processed, more quickly utilize statistical characteristics, improve the anti-corrosion effect and avoid unnecessary processing of all sampling circles.
Drawings
The above and other features of the present invention will become more apparent from the detailed description of the embodiments thereof given in conjunction with the accompanying drawings, in which like reference characters designate like or similar elements, and it is apparent that the drawings in the following description are merely some examples of the present invention, and other drawings may be obtained from these drawings without inventive effort to those of ordinary skill in the art, in which:
FIG. 1 is a flow chart of a fast calculation processing method based on high-entropy alloy data;
FIG. 2 is a system block diagram of a fast computing processing system based on high entropy alloy data.
Detailed Description
The conception, specific structure, and technical effects produced by the present invention will be clearly and completely described below with reference to the embodiments and the drawings to fully understand the objects, aspects, and effects of the present invention. It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other.
In the description of the present invention, a number means one or more, a number means two or more, and greater than, less than, exceeding, etc. are understood to not include the present number, and above, below, within, etc. are understood to include the present number. The description of the first and second is for the purpose of distinguishing between technical features only and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
Fig. 1 is a flowchart of a fast calculation processing method based on high-entropy alloy data according to the present invention, and a fast calculation processing method and system based on high-entropy alloy data according to an embodiment of the present invention are described below with reference to fig. 1.
The invention provides a rapid calculation processing method based on high-entropy alloy data, which specifically comprises the following steps:
dividing the surface of the high-entropy alloy coating into a plurality of sampling circles, and acquiring images of each sampling circle in day and night and infrared thermal imaging of each sampling circle;
calculating a diurnal image time sequence and a night image time sequence, a diurnal imaging time sequence and a night imaging time sequence which correspond to the sampling circles;
marking out a sampling circle to be optimized on the surface of the high-entropy alloy coating.
In some embodiments, the surface of the high-entropy alloy coating is divided into a plurality of sampling circles, then, image shooting and infrared thermal imaging shooting are carried out on the surface of the high-entropy alloy coating day and night respectively every day and day in a plurality of days to obtain images of each sampling circle and infrared thermal imaging thereof respectively day and night, and then, calculation is carried out through an image recognition depth neural network model according to a day image time sequence and a night image time sequence and a day thermal imaging time sequence corresponding to the sampling circle, so that the sampling circle to be optimized on the surface of the high-entropy alloy coating is marked, and rust prevention treatment is carried out on the sampling circle to be optimized. However, the data set required by calculation through the image recognition deep neural network model has large scale and long training time, and the method may not be sufficient for rapidly calculating, processing and marking the sampling circle to be optimized on the surface of the high-entropy alloy coating on a zero basis; however, if the data is already prepared and the image recognition deep neural network model is already pre-trained, the sample circle to be optimized on the high-entropy alloy coating surface can be quickly calculated and marked
Wherein the high-entropy alloy is an alloy of a crystal with five or more elements, each element having an atomic fraction of 5% to 35%, and each element atom occupies one lattice point, and may include, but is not limited to, an alloy of a face-centered cubic solid solution structure represented by cocrcufni, an alloy of a body-centered cubic solid solution structure represented by A1 cocrfni, and the like. The high-entropy alloy coating surface can be the surface of the outer wall of a building such as a stadium, airport terminal, library, etc. The surface area of the high-entropy alloy coating can be 10-100 square meters. The high entropy alloy coating surface may be curved or planar.
Further, in the process of dividing the high-entropy alloy coating surface into a plurality of sampling circles, the coincidence area is allowed to exist between the sampling circles, the coincidence circle centers do not exist between the sampling circles, and all the sampling circles can completely cover the high-entropy alloy coating surface.
In some embodiments, the center of a plurality of different sampling circles can be selected by using a random sampling function of an image preprocessing module in an image processing open source tool (such as opencv, etc.), and the number of the sampling circles is repeatedly increased until all the sampling circles can completely cover the surface of the high-entropy alloy coating. In some embodiments, the radius of each sample circle is equal. In each day, the division of the sampling circles is unchanged, and the same sampling circle in each day continuously keeps a corresponding and consistent relation.
In some embodiments, the imaging and infrared thermal imaging of the high-entropy alloy coating surface is performed daily and every day for a plurality of days, which may be performed daily and every night for 12 pm and 24 pm for 15 to 30 days, each day having two images and two infrared thermal imaging of day and night. On the basis of the images and the infrared thermal imaging, dividing two images and two infrared thermal imaging of each day according to sampling circles, and respectively dividing the images and the infrared thermal imaging into a part of day and night images and a part of infrared thermal imaging of each day and night corresponding to each sampling circle.
Further, images of each sampling circle, which are respectively day and night, and infrared thermal imaging thereof are sequenced according to the time sequence of the date and the time, so as to obtain a day image time sequence and a night image time sequence, a day thermal imaging time sequence and a night thermal imaging time sequence which correspond to each sampling circle;
the elements in the diurnal image time sequence are called diurnal images, the elements in the night image time sequence are called night images, the elements in the diurnal imaging time sequence are called diurnal imaging, the elements in the night imaging time sequence are called night imaging, and the diurnal image, the night image, the diurnal imaging and the night imaging are all pixels of a circular part of a corresponding sampling circle cut from a complete image matrix of the original high-entropy alloy coating surface and the numerical values thereof, but for the sake of convenience of calculation, the diurnal image, the night image, the diurnal imaging and the night imaging are all placed in an image matrix with the minimum circumscribed rectangle size because the circular part is inconvenient to process in image preprocessing, the redundant part outside the sampling circle in the image matrix with the minimum circumscribed rectangle size is uniformly filled with the numerical values which do not affect the numerical value calculation of the pixel value in the sampling circle, for example, when using the pad filling function of opencv, the numerical values including 0 can be used.
The size of the image matrix, the sequence numbers of the rows and the columns in the image matrix and the positions of the rows and the columns are kept consistent, and the images and the infrared thermal imaging are stored in the form of data of the image matrix.
In some embodiments, the size of each image and the image matrix of the two infrared thermal imaging, the serial numbers of the rows and columns in the image matrix and the positions thereof are all kept consistent, and the shooting of the image at night can use the illumination of the camera device or an external light source illumination tool, so that the brightness of the image at night is consistent with the brightness of the image at daytime of the day. But in order to improve the accuracy of measurement, the illumination of the imaging apparatus itself or the illumination tool of an external light source used every day should be kept the same.
In some embodiments, the pixel values of each pixel point on each infrared thermal imaging are the values which have undergone the unified graying treatment and normalization treatment.
Further, a diurnal rust ratio vector and a nocturnal rust ratio vector of each sampling circle are calculated according to a diurnal image time sequence and a nocturnal image time sequence corresponding to each sampling circle:
in some embodiments, for each sample circle corresponding diurnal image time series, except for a first diurnal image, calculating a rust value ratio of each other diurnal image relative to the first diurnal image as a diurnal rust ratio corresponding to the first diurnal image, and for the first diurnal image, the diurnal rust ratio corresponding to the first diurnal image is the rust value ratio of the first diurnal image relative to the first night image corresponding to the sample circle, and an array obtained by the diurnal rust ratio values of each diurnal image in each sample circle corresponding diurnal image time series is used as a diurnal rust ratio vector of the sample circle;
in some embodiments, for each night image time sequence corresponding to the sampling circle, except for the first night image, calculating the rust value ratio of each other night image relative to the first night image as the night rust transformation ratio corresponding to the first night image, and for the first night image, the night rust transformation ratio corresponding to the first night image is the rust value ratio of the first night image relative to the first day image corresponding to the sampling circle, and the array obtained by the night rust transformation ratio values of each night image in each night image time sequence corresponding to each sampling circle is taken as the night rust transformation ratio vector of the sampling circle.
Thus, a diurnal rust ratio vector and a nocturnal rust ratio vector of each sampling circle are obtained. The purpose of designing and calculating the diurnal rust transformation ratio vector and the nocturnal rust transformation ratio vector of each sampling circle is to fully utilize the diurnal image time sequence, and the diurnal rust transformation ratio vector and the nocturnal rust transformation ratio vector are calculated to obtain the performance of each sampling circle under different illumination conditions. By calculating the diurnal rust transformation ratio vector and the nocturnal rust transformation ratio vector, the system can comprehensively understand the performance of the high-entropy alloy coating under different illumination conditions around the clock. Considering the fact that the temperature difference between day and night is large in tropical and subtropical monsoon climate, the design can more accurately capture the change of the surface of the coating under different temperature conditions. And because of the huge area of the surface of a large building and different azimuth angles, uneven cold and hot expansion of each part can cause the difficult-to-detect tensile tearing of the surface of the high-entropy alloy coating. By obtaining the diurnal rust transformation ratio vector and the nocturnal rust transformation ratio vector of each sampling circle, the system can accurately analyze the corrosion rust transformation probability of different areas on the surface of the coating, and further can pertinently perform rust prevention treatment. The system can timely discover potential corrosion rust problems by monitoring the time sequence of the day and night images in real time. And by combining with temperature monitoring, the method can respond more quickly and take optimization measures, so that the corrosion resistance of the high-entropy alloy coating can be timely protected. By fully utilizing the time sequence of the day and night images and calculating the day rust transformation ratio vector and the night rust transformation ratio vector, the performance of the high-entropy alloy coating under specific climatic conditions can be comprehensively, accurately and rapidly known, so that the rust prevention treatment is rapidly optimized, and the durability and the performance of the coating are improved.
Further, the method for calculating the rust surface sign value ratio comprises the following steps: the rust aspect ratio is a value that can be used for one image matrix relative to another image matrix to represent the change in the degree of rust occurring on the surface of the high-entropy alloy coating, and is calculated from the data characteristics of the two image matrices.
In some embodiments, the rust value ratio of one image matrix relative to another image matrix is calculated, the peak signal-to-noise ratio of the one image matrix relative to the other image matrix can be calculated, and then the result of the peak signal-to-noise ratio processed by a sigmoid function is used as the rust value ratio.
In some embodiments, it is preferable to calculate the ratio of rust values of one image matrix to another image matrix, in order to reduce the calculation step and increase the calculation speed, the values of each row position of the one image matrix are removed by removing points from the values of each row position of the other image matrix, so as to obtain a matrix composed of ratios of the values of each row position, and the mode of the values of the elements on the diagonal line in the matrix composed of the ratios is used as the ratio of the rust values.
Further, a hot-face rust ratio vector is calculated according to a diurnal thermal imaging time sequence and a nocturnal thermal imaging time sequence corresponding to each sampling circle:
and the diurnal thermal imaging time sequence and the nocturnal thermal imaging time sequence corresponding to each sampling circle are aligned with each other according to the dimension, and the proportion value of the characteristic value of the diurnal thermal imaging of each day corresponding to the sampling circle relative to the characteristic value of the diurnal thermal imaging of the same day is calculated as the hot surface rust ratio of the same day of the sampling circle, and an array formed by the hot surface rust ratios of each day of the sampling circle is normalized to be called as a hot surface rust ratio vector.
In some embodiments, the alignment of the day and night data of the same day according to the dimensions may be performed, the feature values of the night thermal imaging and the feature values of the day thermal imaging may be calculated by using feature values (for example, values on diagonal lines) of the image matrix, and the ratio values between the feature values may be obtained by dividing the feature values of the two feature values after respectively performing the exponential processing.
Further, by calculating the diurnal rust real value, the nocturnal rust real value and the hot surface rust real value of the sampling circle, the sampling circle to be optimized on the surface of the high-entropy alloy coating is marked, and rust prevention treatment is carried out on the sampling circle to be optimized, specifically:
calculating an expected value of a diurnal rust transformation ratio vector of each sampling circle to serve as a diurnal rust transformation value of the sampling circle, calculating an expected value of a nocturnal rust transformation ratio vector of each sampling circle to serve as a nocturnal rust transformation value of the sampling circle, and calculating an expected value of a hot surface rust transformation ratio vector of each sampling circle to serve as a hot surface rust transformation value of the sampling circle;
calculating the proportion value of the mode of the diurnal rust variable value of each sampling circle relative to the diurnal rust variable value of all the sampling circles to be used as the diurnal rust variable value of the sampling circle, calculating the proportion value of the night rust variable value of each sampling circle relative to the mode of the night rust variable value of all the sampling circles to be used as the night rust variable value of the sampling circle, and calculating the proportion value of the hot face rust variable value of each sampling circle relative to the mode of the hot face rust variable value of all the sampling circles to be used as the hot face rust variable value of the sampling circle.
If the sampling circle exists, the constraint condition is satisfied: and if the diurnal rust real value of the sampling circle is larger than the hot surface rust real value of the sampling circle, and if the nocturnal rust real value of the sampling circle is larger than the hot surface rust real value of the sampling circle, marking the sampling circle meeting the constraint condition as a sampling circle to be optimized on the surface of the high-entropy alloy coating, and carrying out rust prevention treatment on the sampling circle to be optimized.
In some embodiments, the sample circle to be optimized represents a place on the surface of the high-entropy alloy coating where the probability of occurrence of rust change exceeds an average level, rust removal can be performed on the sample circle to be optimized on the surface of the high-entropy alloy coating, and thickening coating can be performed on the sample circle to be optimized on the surface of the high-entropy alloy coating, so that the rust change degree of the sample circle to be optimized is prevented.
In some embodiments, the mathematical expectation of the array may be calculated as its expectation value by using statistical vectors such as numpy and scikit-learn or probability distributions of the values in the array.
The rust prevention treatment is carried out on the sample circle to be optimized in this way, so as to mark and treat the sample circle to be optimized on the surface of the high-entropy alloy coating, and further optimize the rust prevention treatment. By calculating the diurnal rust real value, the nocturnal rust real value and the hot surface rust real value, the sampling circle can be comprehensively evaluated, and the sampling circle to be optimized can be determined. By the design, only sampling circles meeting specific conditions are marked as to-be-optimized, and waste of rust prevention treatment on all the sampling circles is avoided. By calculating the ratio of the diurnal, nocturnal, and hot surface rust values for each sample circle relative to the mode of all sample circles, the statistical features can be better utilized to measure the degree of rust for each sample circle. This allows for a more accurate assessment of the actual rust of the sample circle, helping to determine the portion of the circle that needs to be rust-protected. By satisfying the determination of the constraint condition that the diurnal rust real value is larger than the hot-face rust real value and the nocturnal rust real value is larger than the hot-face rust real value, the sampling circle is marked as the area to be optimized, the area to be subjected to the rust prevention treatment can be accurately determined. The design enables rust prevention measures to be applied to specific areas on the surface of the high-entropy alloy coating in a targeted manner, and the corrosion prevention effect is improved. Thus, the sampling circles to be optimized can be marked by calculating the diurnal rust actual value, the nocturnal rust actual value and the hot surface rust actual value, and rust prevention treatment is carried out on the circles. Therefore, the area to be processed can be determined more accurately, statistical characteristics can be utilized more quickly, the anti-corrosion effect is improved, and unnecessary processing of all sampling circles is avoided.
The rapid computing processing system based on the high-entropy alloy data operates in any computing device of a desktop computer, a notebook computer, a mobile phone, a palm computer or a cloud data center, and the computing device comprises: a processor, a memory, and a computer program stored in and running on the memory, which when executed by the processor implements the steps of the one high entropy alloy data based fast computational processing method, and an operable system may include, but is not limited to, a processor, a memory, a server cluster.
As shown in fig. 2, a fast computing processing system based on high-entropy alloy data according to an embodiment of the present invention includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, the steps in the embodiment of the method for fast calculation processing based on high-entropy alloy data being implemented by the processor when the computer program is executed being used for controlling fast calculation processing based on high-entropy alloy data, the processor executing the computer program being executed in a unit of the following system:
the data sampling unit is used for dividing the surface of the high-entropy alloy coating into a plurality of sampling circles, and acquiring images of each sampling circle in day and night and infrared thermal imaging of each sampling circle;
the computing processing unit is used for computing a diurnal image time sequence and a night image time sequence corresponding to the sampling circle, and a diurnal imaging time sequence and a night imaging time sequence;
and the optimizing marking unit is used for marking a sampling circle to be optimized on the surface of the high-entropy alloy coating.
Wherein, the non-dimensionality and normalized numerical calculation are adopted among the physical quantities of different units.
The rapid computing processing system based on the high-entropy alloy data can be operated in computing equipment such as a desktop computer, a notebook computer, a mobile phone, a palm computer, a cloud data center and the like. The fast computing processing system based on the high-entropy alloy data comprises, but is not limited to, a processor and a memory. It will be understood by those skilled in the art that the examples are merely examples of a method and a system for fast computing processing based on high-entropy alloy data, and are not limited to a method and a system for fast computing processing based on high-entropy alloy data, and may include more or fewer components than examples, or may combine some components, or different components, for example, the fast computing processing system based on high-entropy alloy data may further include an input/output device, a network access device, a bus, and so on.
The processor may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete component gate or transistor logic devices, discrete hardware components, or the like. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc., and the processor is a control center of the rapid computing processing system based on the high-entropy alloy data, and various interfaces and lines are used to connect the various sub-areas of the whole rapid computing processing system based on the high-entropy alloy data.
The memory can be used for storing the computer program and/or the module, and the processor can realize various functions of the rapid calculation processing method and system based on the high-entropy alloy data by running or executing the computer program and/or the module stored in the memory and calling the data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, phonebook, etc.) created according to the use of the handset, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other volatile solid-state storage device.
The invention provides a rapid calculation processing method and a rapid calculation processing system based on high-entropy alloy data.
Although the present invention has been described in considerable detail and with particularity with respect to several described embodiments, it is not intended to be limited to any such detail or embodiment or any particular embodiment so as to effectively cover the intended scope of the invention. Furthermore, the foregoing description of the invention has been presented in its embodiments contemplated by the inventors for the purpose of providing a useful description, and for the purposes of providing a non-essential modification of the invention that may not be presently contemplated, may represent an equivalent modification of the invention.
Claims (8)
1. A rapid computing processing method based on high-entropy alloy data, which is characterized by comprising the following steps: dividing the surface of the high-entropy alloy coating into a plurality of sampling circles, acquiring images of each sampling circle in day and night and infrared thermal imaging of each sampling circle, and marking the sampling circle to be optimized on the surface of the high-entropy alloy coating by calculating a day image time sequence, a night image time sequence, a day thermal imaging time sequence and a night thermal imaging time sequence which correspond to the sampling circles, wherein the sampling circles to be optimized are specifically as follows:
calculating an expected value of a diurnal rust transformation ratio vector of each sampling circle to serve as a diurnal rust transformation value of the sampling circle, calculating an expected value of a nocturnal rust transformation ratio vector of each sampling circle to serve as a nocturnal rust transformation value of the sampling circle, and calculating an expected value of a hot surface rust transformation ratio vector of each sampling circle to serve as a hot surface rust transformation value of the sampling circle;
calculating the proportion value of the mode of the diurnal rust variable value of each sampling circle relative to the diurnal rust variable value of all the sampling circles to be used as the diurnal rust variable value of the sampling circle, calculating the proportion value of the night rust variable value of each sampling circle relative to the mode of the night rust variable value of all the sampling circles to be used as the night rust variable value of the sampling circle, and calculating the proportion value of the hot face rust variable value of each sampling circle relative to the mode of the hot face rust variable value of all the sampling circles to be used as the hot face rust variable value of the sampling circle;
if the sampling circle meets the constraint condition, namely the diurnal rust real value of the sampling circle is larger than the hot surface rust real value of the sampling circle and the nocturnal rust real value of the sampling circle is larger than the hot surface rust real value of the sampling circle, marking the sampling circle meeting the constraint condition as the sampling circle to be optimized on the surface of the high-entropy alloy coating.
2. The rapid computing processing method based on high-entropy alloy data according to claim 1, wherein in the process of dividing the high-entropy alloy coating surface into a plurality of sampling circles, overlapping areas are allowed to exist among the sampling circles, no overlapping circle center exists among the sampling circles, and all the sampling circles can completely cover the high-entropy alloy coating surface.
3. The rapid computing processing method based on high-entropy alloy data according to claim 1, wherein the images of each sampling circle, which are respectively day and night, and the infrared thermal imaging thereof are sequenced according to the time sequence of the date and the time, so as to obtain a day image time sequence and a night image time sequence, and a day imaging time sequence and a night imaging time sequence, which correspond to each sampling circle; wherein elements in the diurnal image time series are called diurnal images, elements in the nocturnal image time series are called nocturnal images, elements in the diurnal imaging time series are called diurnal imaging, elements in the nocturnal imaging time series are called nocturnal imaging, and images and infrared thermal imaging are stored in a data form of an image matrix.
4. The rapid computing processing method based on high-entropy alloy data according to claim 1, wherein a diurnal rust ratio vector and a nocturnal rust ratio vector of each sampling circle are computed according to a diurnal image time sequence and a nocturnal image time sequence corresponding to each sampling circle:
for the night image time sequence corresponding to each sampling circle, except for the first night image, calculating the rust value ratio of each other night image relative to the first night image as the rust transformation ratio of the night image corresponding to the first night image, wherein for the first night image, the rust transformation ratio of the first night image relative to the first day image corresponding to the sampling circle, and taking an array obtained by the rust transformation ratio values of each night image in the night image time sequence corresponding to each sampling circle as the night rust transformation ratio vector of the sampling circle, thereby obtaining the day rust transformation ratio vector and the night rust transformation ratio vector of each sampling circle.
5. The rapid computing and processing method based on high-entropy alloy data according to claim 4, wherein the method for computing the rust aspect ratio is as follows: the rust aspect ratio is a value that can be used for one image matrix relative to another image matrix to represent the change in the degree of rust occurring on the surface of the high-entropy alloy coating, and is calculated from the data characteristics of the two image matrices.
6. The rapid computing processing method based on high-entropy alloy data according to claim 1, wherein a hot-face rust transformation ratio vector is computed according to a diurnal thermal imaging time sequence and a nocturnal thermal imaging time sequence corresponding to each sampling circle:
and the diurnal thermal imaging time sequence and the nocturnal thermal imaging time sequence corresponding to each sampling circle are aligned with each other according to the dimension, and the proportion value of the characteristic value of the diurnal thermal imaging of each day corresponding to the sampling circle relative to the characteristic value of the diurnal thermal imaging of the same day is calculated as the hot surface rust ratio of the same day of the sampling circle, and an array formed by the hot surface rust ratios of each day of the sampling circle is normalized to be called as a hot surface rust ratio vector.
7. The rapid computing processing method based on high-entropy alloy data according to any one of claims 1, 4 to 6, wherein rust prevention treatment is performed on the sample circle to be optimized.
8. A fast computing processing system based on high-entropy alloy data, wherein the fast computing processing system based on high-entropy alloy data operates in any computing device of a desktop computer, a notebook computer, or a cloud data center, the computing device comprising: a processor, a memory and a computer program stored in the memory and running on the processor, which processor, when executing the computer program, implements the steps of a fast calculation processing method based on high entropy alloy data as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410108174.3A CN117635617B (en) | 2024-01-26 | 2024-01-26 | Rapid calculation processing method and system based on high-entropy alloy data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410108174.3A CN117635617B (en) | 2024-01-26 | 2024-01-26 | Rapid calculation processing method and system based on high-entropy alloy data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117635617A true CN117635617A (en) | 2024-03-01 |
| CN117635617B CN117635617B (en) | 2024-04-09 |
Family
ID=90025611
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410108174.3A Active CN117635617B (en) | 2024-01-26 | 2024-01-26 | Rapid calculation processing method and system based on high-entropy alloy data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117635617B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101409825A (en) * | 2007-10-10 | 2009-04-15 | 中国科学院自动化研究所 | Nighttime vision monitoring method based on information fusion |
| JP2009293993A (en) * | 2008-06-03 | 2009-12-17 | Central Res Inst Of Electric Power Ind | Method and apparatus for evaluating degree of corrosion and program |
| CN113689428A (en) * | 2021-10-25 | 2021-11-23 | 江苏南通元辰钢结构制造有限公司 | Mechanical part stress corrosion detection method and system based on image processing |
| CN117332620A (en) * | 2023-12-01 | 2024-01-02 | 广东海洋大学 | Corrosion-resistant material optimization method and system based on atmospheric corrosion data |
-
2024
- 2024-01-26 CN CN202410108174.3A patent/CN117635617B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101409825A (en) * | 2007-10-10 | 2009-04-15 | 中国科学院自动化研究所 | Nighttime vision monitoring method based on information fusion |
| JP2009293993A (en) * | 2008-06-03 | 2009-12-17 | Central Res Inst Of Electric Power Ind | Method and apparatus for evaluating degree of corrosion and program |
| CN113689428A (en) * | 2021-10-25 | 2021-11-23 | 江苏南通元辰钢结构制造有限公司 | Mechanical part stress corrosion detection method and system based on image processing |
| CN117332620A (en) * | 2023-12-01 | 2024-01-02 | 广东海洋大学 | Corrosion-resistant material optimization method and system based on atmospheric corrosion data |
Non-Patent Citations (1)
| Title |
|---|
| WEN CHENG ET AL.: "Modeling solid solution strengthening in high entropy alloys using machine learning", ACTA MATERIALIA, vol. 212, 15 June 2021 (2021-06-15), pages 1 - 11 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117635617B (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109671020B (en) | Image processing method, device, electronic equipment and computer storage medium | |
| CN109726649B (en) | Remote sensing image cloud detection method and system and electronic equipment | |
| Li et al. | Few-Shot Learning with Generative Adversarial Networks Based on WOA13 Data. | |
| CN116128141B (en) | Storm surge prediction method and device, storage medium and electronic equipment | |
| CN114067019A (en) | Urban waterlogging risk map rapid prefabricating method coupling deep learning and numerical simulation | |
| CN108399430A (en) | A kind of SAR image Ship Target Detection method based on super-pixel and random forest | |
| CN112508299A (en) | Power load prediction method and device, terminal equipment and storage medium | |
| CN114493052A (en) | Multi-model fusion self-adaptive new energy power prediction method and system | |
| CN114324336B (en) | Nondestructive measurement method for biomass of soybean in whole growth period | |
| CN117635617B (en) | Rapid calculation processing method and system based on high-entropy alloy data | |
| CN113870224A (en) | Flood monitoring method, system, equipment and medium | |
| CN113516077A (en) | Surface environment change monitoring method and device, readable storage medium and equipment | |
| CN116205918B (en) | Multi-mode fusion semiconductor detection method, device and medium based on graph convolution | |
| CN116958809A (en) | Remote sensing small sample target detection method for feature library migration | |
| Iyamuremye et al. | Extreme value modelling of rainfall using poisson-generalized pareto distribution: A case study tanzania | |
| CN113989632A (en) | Bridge detection method and device for remote sensing image, electronic equipment and storage medium | |
| Wang et al. | Measure for the difference between LBP features extracted from original and resized cloud images with varying resolutions | |
| CN113902187A (en) | Time-of-use electricity price prediction method and device and terminal equipment | |
| CN116757102B (en) | Apparent optical characteristic profile distribution estimation method based on inherent optical characteristics | |
| Amendola et al. | A neural network ensemble downscaling system (SIBILLA) for seasonal forecasts over Italy: winter case studies | |
| CN116129145B (en) | Method and system for extracting sandy coastline of high-resolution remote sensing image | |
| Koçak | Time Series Prediction of Temperature Using Seasonal ARIMA and LSTM Models | |
| CN113837668B (en) | Extreme climate event identification method and system | |
| CN114648646B (en) | Image classification method and device | |
| CN114723099A (en) | Seasonal climate statistical prediction method, system, device and storage medium |
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 |