CN115641467B - Method and device for identifying impurities in ore, medium and electronic equipment - Google Patents
Method and device for identifying impurities in ore, medium and electronic equipment Download PDFInfo
- Publication number
- CN115641467B CN115641467B CN202211206550.XA CN202211206550A CN115641467B CN 115641467 B CN115641467 B CN 115641467B CN 202211206550 A CN202211206550 A CN 202211206550A CN 115641467 B CN115641467 B CN 115641467B
- Authority
- CN
- China
- Prior art keywords
- ore
- energy data
- data
- impurity
- low
- 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
- 239000012535 impurity Substances 0.000 title claims abstract description 124
- 238000000034 method Methods 0.000 title claims abstract description 56
- 239000000463 material Substances 0.000 claims abstract description 124
- 239000013598 vector Substances 0.000 claims abstract description 40
- 238000010801 machine learning Methods 0.000 claims abstract description 32
- 238000001914 filtration Methods 0.000 claims abstract description 17
- 238000010586 diagram Methods 0.000 claims description 30
- 238000004422 calculation algorithm Methods 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 16
- 230000000877 morphologic effect Effects 0.000 claims description 11
- 238000003860 storage Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 5
- 238000013145 classification model Methods 0.000 claims description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 abstract description 50
- 229910052742 iron Inorganic materials 0.000 abstract description 25
- 238000012216 screening Methods 0.000 abstract description 4
- 238000012423 maintenance Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 12
- 230000007246 mechanism Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 238000005422 blasting Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 229910052500 inorganic mineral Inorganic materials 0.000 description 3
- 239000011707 mineral Substances 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000011068 loading method Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000001179 sorption measurement Methods 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 238000012896 Statistical algorithm Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000010439 graphite Substances 0.000 description 1
- 229910002804 graphite Inorganic materials 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000000053 physical method Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000002285 radioactive effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000007723 transport mechanism Effects 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
- Analysing Materials By The Use Of Radiation (AREA)
Abstract
The application discloses a method and a device for identifying impurities in ores, a medium and electronic equipment. The method comprises the following steps: acquiring low-energy data and high-energy data of ore materials under X rays; determining profile data of the ore material from the low energy data; if the profile data is matched with the impurity characteristics, determining that the ore material is impurity; if the profile data is not matched with the impurity characteristics, constructing a one-dimensional vector of the ore material for the high-energy data and the low-energy data; and inputting the one-dimensional vector into a pre-trained machine learning model, and determining the ore material as impurities if the classification result of the machine learning model is the impurity type. By adopting the technical scheme, the iron impurity filtering can be performed more efficiently, the accuracy of the iron impurity filtering is higher, the screening machine is not required to be shut down for maintenance, and the filtering efficiency is improved.
Description
Technical Field
The application relates to the technical field of mineral resources, in particular to a method and a device for identifying impurities in ores, a medium and electronic equipment.
Background
With rapid development of the technological level, social life has an increasing demand for resources, and mineral resources have become an important field of resource exploitation.
The traditional mining process of mineral resources mainly comprises the processes of perforation, blasting, loading, transportation, soil discharging and the like. A portion of the iron remains in the ore during blasting, such as a primarily post-blasting detonator. In addition, the farm work abandoned tool, the iron wire, the electric wire and the like remained on the mountain, so that a part of iron ware impurities exist in the blasted ore. Most of the existing impurity removing methods of the iron remover adopt a physical method, namely a magnet device is additionally arranged above a belt for transporting ores, and a part of iron remover can be removed by the method. But this approach has a number of drawbacks. First, if the iron is shaped like a relatively heavy sphere or pie, the magnet assembly will attract it and the surface of the magnet assembly will soon be occupied by the sphere or pie iron. At this time, the magnetic force of the magnet device will be greatly reduced, and if the magnet device is not cleaned in time, the adsorption of the following ironware will be affected, and the problem that the ironware is missed in the ore is generated. Even cleaning in time can consume manpower, and people need to monitor all the day. And, need shut down in the process of cleaning the ironware that is adsorbed by magnet device to delay production.
Disclosure of Invention
The embodiment of the application provides a method and a device for identifying impurities in ores, a medium and electronic equipment. The application achieves the aim of improving the impurity efficiency of the iron remover through screening the outline and classifying the machine learning model based on the characteristic data.
The embodiment of the application provides a method for identifying impurities in ores, which comprises the following steps:
Acquiring low-energy data and high-energy data of ore materials under X rays;
Determining profile data of the ore material from the low energy data;
If the profile data is matched with the impurity characteristics, determining that the ore material is impurity;
If the profile data is not matched with the impurity characteristics, constructing a one-dimensional vector of the ore material for the high-energy data and the low-energy data;
And inputting the one-dimensional vector into a pre-trained machine learning model, and determining the ore material as impurities if the classification result of the machine learning model is the impurity type.
Further, determining profile data of the ore material from the low energy data includes:
performing binarization processing on the low-energy data by using a preset algorithm to obtain a binary image; wherein 1 represents an ore region, and 0 represents a background region;
Carrying out morphological open operation on the binary image to carry out denoising treatment to obtain a material area image;
performing background filtering on the low-energy data according to the material area diagram to obtain a material outline diagram;
And carrying out contour recognition on the material contour map to obtain contour data of each ore material.
Further, after obtaining the profile data for each ore material, the method further comprises:
Determining the contour characteristics of each ore material according to the contour data; wherein the profile feature comprises: at least one characteristic parameter of roundness, the number of 80-100 angles, the length-width ratio, the centroid position and the position relation between points on the contour;
correspondingly, if the profile data is matched with the impurity characteristics, determining that the ore material is impurity comprises:
and if the degree of difference between one or more characteristic parameters in the profile characteristics of the ore material and the impurity characteristics is within a preset range, determining that the ore material is impurity.
Further, constructing a one-dimensional vector of ore material for the high energy data and the low energy data, comprising:
performing binarization processing on the low-energy data by using a preset algorithm to obtain a binary image; wherein 1 represents an ore region, and 0 represents a background region;
Carrying out morphological open operation on the binary image to carry out denoising treatment to obtain a material area image;
dividing the high-energy data and the low-energy data by an original energy value based on the material area diagram, and dividing the high-energy data after taking the logarithm by the low-energy data after taking the logarithm to obtain a ratio diagram;
performing convolution operation on the ratio graph based on a specific filter to obtain a convolution graph;
and carrying out histogram statistics on the convolution graph to determine a one-dimensional vector of the ore material.
Further, the pre-trained machine learning model is a classification model;
the classification result of the pre-trained machine learning model comprises an ore category and an impurity category;
the pre-trained machine learning model is obtained through supervised training based on a one-dimensional vector of pre-acquired ore samples and a one-dimensional vector of impurity samples.
Further, performing binarization processing on the low-energy data by using a preset algorithm to obtain a binary image, including:
Performing binarization processing on the low-energy data by using an OTSU algorithm to obtain a binary image; or alternatively
And performing convolution operation on the low-energy data by using one of a sobel operator, a scharr operator and a Laplacian operator to obtain a binary image.
The embodiment of the application also provides a device for identifying impurities in ores, which comprises:
the data acquisition module is used for acquiring low-energy data and high-energy data of the ore materials under X rays;
The profile data determining module is used for determining profile data of the ore material according to the low-energy data;
The first identification module is used for determining that the ore material is impurity if the profile data is matched with the impurity characteristics;
The second identification module is used for constructing a one-dimensional vector of the ore material for the high-energy data and the low-energy data if the profile data is not matched with the impurity characteristics; and inputting the one-dimensional vector into a pre-trained machine learning model, and determining the ore material as impurities if the classification result of the machine learning model is the impurity type.
Further, the profile data determining module is specifically configured to:
performing binarization processing on the low-energy data by using a preset algorithm to obtain a binary image; wherein 1 represents an ore region, and 0 represents a background region;
Carrying out morphological open operation on the binary image to carry out denoising treatment to obtain a material area image;
performing background filtering on the low-energy data according to the material area diagram to obtain a material outline diagram;
And carrying out contour recognition on the material contour map to obtain contour data of each ore material.
The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, which when being executed by a processor, implements the method for identifying impurities in ore according to the embodiment of the application.
The embodiment of the application also provides electronic equipment, which comprises a memory, a processor and a computer program stored in the memory and capable of being run on the processor, wherein the processor realizes the method for identifying impurities in ores according to the embodiment of the application when executing the computer program.
The above at least one technical scheme adopted by the embodiment of the application can achieve the following beneficial effects:
compared with the traditional method for filtering iron impurities by utilizing the magnetic adsorption mode, the technical scheme provided by the application can more efficiently filter the iron impurities, has higher accuracy for filtering the iron impurities, does not need shutdown maintenance of a screening machine and the like, and improves the filtering efficiency.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:
FIG. 1 is a schematic flow chart of a method for identifying impurities in ore according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of a method for identifying impurities in ore according to a second embodiment of the present application;
FIG. 3 is a schematic flow chart of a method for identifying impurities in ore according to a third embodiment of the present application;
fig. 4 is a schematic structural diagram of an apparatus for identifying impurities in ores according to a fourth embodiment of the present application;
Fig. 5 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The following describes in detail the technical solutions provided by the embodiments of the present application with reference to the accompanying drawings.
Example 1
Fig. 1 is a schematic flow chart of a method for identifying impurities in ore provided in an embodiment of the present application, where the embodiment is applicable to filtering ore materials, the method may be performed by an apparatus for identifying impurities in ore provided in the embodiment of the present application, and the apparatus may be implemented in a software and/or hardware manner and may be integrated into an electronic device for identifying impurities in ore.
As shown in fig. 1, the method includes:
S110, acquiring low-energy data and high-energy data of ore materials under X rays;
Specifically, the sorting operation adopted by the scheme is realized based on an ironware sorter device. The ironware separator device includes: the device comprises a feeding mechanism, a transmission mechanism, an X-ray acquisition mechanism and a sorting mechanism. A feeding mechanism for feeding ore; a transport mechanism for transporting the ore to a predetermined location after loading the ore from the feeding mechanism; the X-ray acquisition mechanism is used for emitting X-rays and acquiring images and is used for acquiring ore X-ray dual-energy data; and the sorting mechanism is used for sorting and picking up the sorting result of the ore according to the sorting system.
Among them, high-energy X-rays and low-energy X-rays relate to radiometry, semiconductor discrete devices, medical equipment, laboratory medicine, nuclear engineering. High-energy X-rays and low-energy X-rays relate to exploration, mining and process monitoring nuclear instruments, semiconductor discrete device synthesis, radiation protection monitoring and evaluation, isotope and radioactive source synthesis and radiation protection instruments.
In the scheme, the low-energy data and the high-energy data aiming at the ore materials can be simultaneously acquired based on the emission and the reception of X-rays.
S120, determining contour data of the ore material according to the low-energy data;
Wherein the low energy X-ray data has complete profile information of the ore, since the low energy X-ray data is taken from the end of the X-ray detector closest to the object. According to the scheme, an empirical threshold is set through multiple tests, and objects in the X-ray low-energy data are segmented from the background.
After the segmentation, contour data of the material may be determined. For example, the profile data may be the curvature of the boundary of the material, the centroid position of the material, and so on.
S130, if the profile data is matched with the impurity characteristics, determining that the ore material is impurity;
the profile data of the obtained material can be subjected to characteristic comparison with a set threshold, and if the profile data accords with a set comparison principle, the profile data is determined to be matched with the impurity characteristics, so that the ore material is determined to be impurity. It can be appreciated that the impurities can include iron impurities, other impurities, whether iron impurities or other impurities are doped in the ore or not can be determined based on matching of the profile data and the characteristics of the impurities, and the effect of rapidly identifying the impurities in a mode of image identification can be achieved.
For example, if the centroid location of the material is identified as being outside of the material profile, it may be determined that the material is an iron impurity, not an ore.
S140, if the profile data is not matched with the impurity characteristics, constructing a one-dimensional vector of the ore material for the high-energy data and the low-energy data;
Here, in the case where it is impossible to determine the iron impurity by the profile data, a one-dimensional vector of the ore material may be further determined based on the high-energy data and the low-energy data. The one-dimensional vector can be used for representing some characteristics of ore materials obtained under X rays, such as attenuation degree characteristics of the X rays and the like.
S150, inputting the one-dimensional vector into a pre-trained machine learning model, and determining that the ore material is impurity if the classification result of the machine learning model is impurity type.
In the scheme, the pre-trained machine learning model can be obtained by performing supervised training on one-dimensional vectors of different materials.
In one embodiment, optionally, the pre-trained machine learning model is a classification model;
the classification result of the pre-trained machine learning model comprises an ore category and an impurity category;
the pre-trained machine learning model is obtained through supervised training based on a one-dimensional vector of pre-acquired ore samples and a one-dimensional vector of impurity samples.
For example, the output results thereof may include impurity categories and ore categories. Specifically, the impurity type may be not limited to the iron impurity, but may be other impurities. The ore category can be more accurately trained to obtain copper ore, graphite or other ore, and the like. Specifically, the method can be a one-dimensional vector of a pre-collected ore sample and a one-dimensional vector of an impurity sample, for example, 1000 iron impurities are selected, the one-dimensional vector is obtained, and the part of data is labeled, wherein the labeling content is the impurity type. Similarly, 1000 ores are selected, one-dimensional vectors of the ores are obtained, and label marking is carried out on the data, wherein the marking content is the type of the ores. The machine learning model for classification is obtained by supervised training of the sample with the labels.
According to the embodiment provided by the application, the low-energy data and the high-energy data of the ore material under the X-ray are obtained; determining profile data of the ore material from the low energy data; if the profile data is matched with the impurity characteristics, determining that the ore material is impurity; if the profile data is not matched with the impurity characteristics, constructing a one-dimensional vector of the ore material for the high-energy data and the low-energy data; and inputting the one-dimensional vector into a pre-trained machine learning model, and determining the ore material as impurities if the classification result of the machine learning model is the impurity type. Therefore, the scheme is more efficient in iron impurity filtering, and the accuracy of iron impurity filtering is higher, and the screening machine is not required to be shut down, maintained and the like, so that the filtering efficiency is improved.
Example two
The second embodiment is further optimized based on the above embodiments. The concrete optimization is as follows: determining profile data of the ore material from the low energy data, comprising: performing binarization processing on the low-energy data by using a preset algorithm to obtain a binary image; wherein 1 represents an ore region, and 0 represents a background region; carrying out morphological open operation on the binary image to carry out denoising treatment to obtain a material area image; performing background filtering on the low-energy data according to the material area diagram to obtain a material outline diagram; and carrying out contour recognition on the material contour map to obtain contour data of each ore material.
Fig. 2 is a schematic flow chart of a method for identifying impurities in ores according to a second embodiment of the present application. As shown in fig. 2, the process mainly includes:
S210, acquiring low-energy data and high-energy data of ore materials under X rays;
S220, performing binarization processing on the low-energy data by using a preset algorithm to obtain a binary image; wherein 1 represents an ore region, and 0 represents a background region;
The preset algorithm may be an oxford binarization algorithm. In computer vision and image processing, the dyadic binarization method is used to automatically binarize cluster-based images, or to regress a gray-scale image into a binary image. The algorithm is named as Dajin. The algorithm assumes that the image contains two classes of pixels (foreground and background pixels) and then it computes the optimal threshold that separates the two classes so that their intra-class variance is minimal; since the square distance is constant every two times, i.e. their inter-class variance is the largest. Therefore, the method of the Sedrin binarization is roughly referred to as discretization simulation of one-dimensional Fisher discriminant analysis.
S230, carrying out morphological open operation on the binary image to carry out denoising treatment to obtain a material area image;
And carrying out morphological open operation on the binary image so as to carry out denoising treatment. The morphological open operation is characterized by firstly corroding and then expanding, and the open operation can remove isolated small points, burrs and small bridges, and the total position and shape are unchanged. The open operation is a filter based on geometric operations. The difference in the size of the structural elements will result in a difference in the filtering effect. The selection of different structural elements results in different segmentations, i.e. extraction of different features. The effect of the open operation is to remove noise and filter out some too small objects.
S240, carrying out background filtering on the low-energy data according to the material area diagram to obtain a material outline diagram;
In the scheme, the material area diagram obtained in the last step can be used for performing AND operation on the X-ray low-energy data to obtain the X-ray low-energy data only containing the object.
S250, carrying out contour recognition on the material contour map to obtain contour data of each ore material;
in the scheme, specifically, the contour recognition can be performed on the X-ray low-energy data to obtain the contour information of each object.
In this embodiment, optionally, after obtaining the profile data of each ore material, the method further comprises:
Determining the contour characteristics of each ore material according to the contour data; wherein the profile feature comprises: at least one characteristic parameter of roundness, the number of 80-100 angles, the length-width ratio, the centroid position and the position relation between points on the contour;
correspondingly, if the profile data is matched with the impurity characteristics, determining that the ore material is impurity comprises:
and if the degree of difference between one or more characteristic parameters in the profile characteristics of the ore material and the impurity characteristics is within a preset range, determining that the ore material is impurity.
Roundness is understood, among other things, as the variance or standard deviation between the distances of points on the contour to the centroid. And (3) respectively calculating the roundness, the number of 80-100 angles, the length-width ratio, the centroid position of each object and the position relation (inner part, upper part and outer part) between each point on the contour according to the contour information obtained in the last step. Wherein the calculation of 80-100 angles is to take 5 points from the starting point of the outline clockwise, forward and backward respectively, fit two straight lines by a straight line fitting method, then calculate the angles of the two straight lines (wherein the error value of the fitted straight lines also has a threshold value, if the error value is smaller than the threshold value, the 5 points are considered to be collinear and the new starting point is moved forward by 5 points, otherwise, the new starting point is not collinear and the new starting point is moved forward by 1 point), and finally count the number of the angles of 80-100 degrees. Aspect ratio refers to calculating the ratio of the closest to the centroid to the furthest distance of each point in the profile.
S260, if the profile data is matched with the impurity characteristics, determining that the ore material is impurity;
S270, if the profile data is not matched with the impurity characteristics, constructing a one-dimensional vector of the ore material for the high-energy data and the low-energy data;
s280, inputting the one-dimensional vector into a pre-trained machine learning model, and determining that the ore material is impurity if the classification result of the machine learning model is impurity type.
The embodiment provides a specific process for extracting the profile data on the basis of the embodiment, and by the arrangement, whether the currently identified material is the iron ware impurity can be judged from multiple angles based on the profile data, so that the identification speed is high, the calculation accuracy is high, the reliability is high, and the identification result is more accurate.
Example III
The third embodiment is further optimized based on the above embodiments, and specifically is: and constructing a one-dimensional vector of the ore material for the high-energy data and the low-energy data. Fig. 3 is a schematic flow chart of a method for identifying impurities in ore according to a third embodiment of the present application. As shown in fig. 3, the process mainly includes:
s310, acquiring low-energy data and high-energy data of ore materials under X rays;
s320, determining profile data of the ore material according to the low-energy data;
s330, if the profile data is matched with the impurity characteristics, determining that the ore material is impurity;
S340, if the profile data is not matched with the impurity characteristics, performing binarization processing on the low-energy data by using a preset algorithm to obtain a binary image; wherein 1 represents an ore region, and 0 represents a background region;
s350, carrying out morphological open operation on the binary image to carry out denoising treatment to obtain a material area image;
S360, dividing the high-energy data and the low-energy data by an original energy value based on the material area diagram, and dividing the high-energy data after the logarithm is obtained by the low-energy data after the logarithm is obtained to obtain a ratio diagram;
respectively collecting and preprocessing high-energy and low-energy X-ray data to obtain the high-energy and low-energy data of each object; because the collected X-ray high-low energy data comprise thickness information and density information of the objects, dividing the X-ray high-low energy data of each object by an original energy value, taking the logarithm, dividing the high-energy data after taking the logarithm by the low-energy data after taking the logarithm, and obtaining a ratio graph, wherein the interference of the thickness and the density can be reduced through the step, and the ratio graph information represents attenuation trend of different elements as much as possible.
S370, carrying out convolution operation on the ratio graph based on a specific filter to obtain a convolution graph;
analysis of the ratio diagram of the ironware and the ore shows that the ironware has the characteristics of relatively uniform overall distribution and relatively smooth fluctuation of each peak value, and the ore has the characteristics of uneven overall distribution and relatively severe peak distribution jitter. And carrying out convolution operation on the ratio graph of each object and the specific filter, thereby obtaining a convolution graph of each object. The filter employed herein may be of the form:
s380, carrying out histogram statistics on the convolution graph to determine a one-dimensional vector of the ore material.
And carrying out histogram statistics on each convolution graph to obtain a one-dimensional vector of each object. The histogram statistical algorithm is to judge and detect whether the fluctuation of each line of the object to be detected is severe or not by counting the gradient distribution in the x direction in the ROI area. The algorithm includes a maximum value algorithm, a minimum value algorithm, and an average value algorithm.
S390, inputting the one-dimensional vector into a pre-trained machine learning model, and determining that the ore material is impurity if the classification result of the machine learning model is impurity type.
The embodiment provides a process for calculating the one-dimensional vector of the material on the basis of the above embodiments. The characteristic difference between the iron ware impurity and the ore is considered in the scheme, the characteristic is extracted to identify the iron ware impurity, and the accuracy of identifying the iron ware impurity can be improved.
Based on the above embodiments, optionally, performing binarization processing on the low-energy data by using a preset algorithm to obtain a binary image, including:
Performing binarization processing on the low-energy data by using an OTSU algorithm to obtain a binary image; or alternatively
And performing convolution operation on the low-energy data by using one of a sobel operator, a scharr operator and a Laplacian operator to obtain a binary image.
The sobel operator can calculate image gradients, which function to extract boundaries. scharr is the same as the ideas of sobel operators, but the coefficients of convolution kernels are different, the scharr operator is more sensitive in extracting boundaries, and finer boundaries can be extracted. The Laplacian operator is also used to calculate image gradients and functions to extract boundaries. It differs from the above two operators in that: the sobel operator and scharr operator generally calculate a horizontal gradient and then a vertical gradient, and then image fusion is performed on the two results according to a weight of 0.5 to obtain a complete boundary.
According to the scheme, through the arrangement, the calculation speed and the calculation precision can be considered, and corresponding operators are adopted as convolution operators for actual binarization processing according to actual requirements.
Example IV
Fig. 4 is a schematic structural diagram of an apparatus for identifying impurities in ores according to a fourth embodiment of the present application. As shown in fig. 4, the apparatus includes:
A data acquisition module 410 for acquiring low energy data and high energy data of the ore material under X-rays;
A profile data determination module 420 for determining profile data of the ore material from the low energy data;
a first identification module 430, configured to determine that the ore material is an impurity if the profile data matches an impurity characteristic;
a second recognition module 440, configured to construct a one-dimensional vector of the ore material for the high energy data and the low energy data if the profile data does not match the impurity feature; and inputting the one-dimensional vector into a pre-trained machine learning model, and determining the ore material as impurities if the classification result of the machine learning model is the impurity type.
The device can execute the method for identifying the impurities in the ore provided by the embodiments, and has the corresponding functional modules and beneficial effects. And will not be described in detail herein.
Example five
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects.
Further, the present application also proposes an electronic device (or a computing device), and fig. 5 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present application. Comprising a memory 12, a processor 11, an input device 13, an output device 14, and a computer program stored on the memory 12 and executable by the processor for performing the method according to any of the embodiments of the application when said computer program is executed.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Other embodiments
Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The application therefore also proposes a computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, implements a method according to any of the embodiments of the application.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.
Claims (9)
1. A method of identifying impurities in an ore, the method comprising:
Acquiring low-energy data and high-energy data of ore materials under X rays;
Determining profile data of the ore material from the low energy data;
If the profile data is matched with the impurity characteristics, determining that the ore material is impurity;
If the profile data is not matched with the impurity characteristics, constructing a one-dimensional vector of the ore material for the high-energy data and the low-energy data;
inputting the one-dimensional vector into a pre-trained machine learning model, and determining that the ore material is an impurity if the classification result of the machine learning model is an impurity type;
constructing a one-dimensional vector of ore material for the high energy data and the low energy data, comprising:
performing binarization processing on the low-energy data by using a preset algorithm to obtain a binary image; wherein 1 represents an ore region, and 0 represents a background region;
Carrying out morphological open operation on the binary image to carry out denoising treatment to obtain a material area image;
dividing the high-energy data and the low-energy data by an original energy value based on the material area diagram, and dividing the high-energy data after taking the logarithm by the low-energy data after taking the logarithm to obtain a ratio diagram;
performing convolution operation on the ratio graph based on a specific filter to obtain a convolution graph;
and carrying out histogram statistics on the convolution graph to determine a one-dimensional vector of the ore material.
2. The method of claim 1, wherein determining profile data for the ore material from the low energy data comprises:
performing binarization processing on the low-energy data by using a preset algorithm to obtain a binary image; wherein 1 represents an ore region, and 0 represents a background region;
Carrying out morphological open operation on the binary image to carry out denoising treatment to obtain a material area image;
performing background filtering on the low-energy data according to the material area diagram to obtain a material outline diagram;
And carrying out contour recognition on the material contour map to obtain contour data of each ore material.
3. The method of claim 2, wherein after obtaining the profile data for each ore material, the method further comprises:
Determining the contour characteristics of each ore material according to the contour data; wherein the profile feature comprises: at least one characteristic parameter of roundness, the number of 80-100 angles, the length-width ratio, the centroid position and the position relation between points on the contour;
correspondingly, if the profile data is matched with the impurity characteristics, determining that the ore material is impurity comprises:
and if the degree of difference between one or more characteristic parameters in the profile characteristics of the ore material and the impurity characteristics is within a preset range, determining that the ore material is impurity.
4. The method of claim 1, wherein the pre-trained machine learning model is a classification model;
the classification result of the pre-trained machine learning model comprises an ore category and an impurity category;
the pre-trained machine learning model is obtained through supervised training based on a one-dimensional vector of pre-acquired ore samples and a one-dimensional vector of impurity samples.
5. The method of claim 2, wherein performing binarization processing on the low-energy data using a preset algorithm to obtain a binary image comprises:
Performing binarization processing on the low-energy data by using an OTSU algorithm to obtain a binary image; or alternatively
And performing convolution operation on the low-energy data by using one of a sobel operator, a scharr operator and a Laplacian operator to obtain a binary image.
6. An apparatus for identifying impurities in ore, for implementing the method of any one of claims 1 to 5, the apparatus comprising:
the data acquisition module is used for acquiring low-energy data and high-energy data of the ore materials under X rays;
The profile data determining module is used for determining profile data of the ore material according to the low-energy data;
The first identification module is used for determining that the ore material is impurity if the profile data is matched with the impurity characteristics;
The second identification module is used for constructing a one-dimensional vector of the ore material for the high-energy data and the low-energy data if the profile data is not matched with the impurity characteristics; and inputting the one-dimensional vector into a pre-trained machine learning model, and determining the ore material as impurities if the classification result of the machine learning model is the impurity type.
7. The apparatus of claim 6, wherein the profile data determination module is configured to:
performing binarization processing on the low-energy data by using a preset algorithm to obtain a binary image; wherein 1 represents an ore region, and 0 represents a background region;
Carrying out morphological open operation on the binary image to carry out denoising treatment to obtain a material area image;
performing background filtering on the low-energy data according to the material area diagram to obtain a material outline diagram;
And carrying out contour recognition on the material contour map to obtain contour data of each ore material.
8. A computer readable storage medium having stored thereon a computer program, characterized in that the program, when executed by a processor, implements a method for identifying impurities in an ore according to any one of claims 1-5.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable by the processor, wherein the processor implements a method for identifying impurities in an ore according to any one of claims 1-5 when the computer program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211206550.XA CN115641467B (en) | 2022-09-30 | 2022-09-30 | Method and device for identifying impurities in ore, medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211206550.XA CN115641467B (en) | 2022-09-30 | 2022-09-30 | Method and device for identifying impurities in ore, medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115641467A CN115641467A (en) | 2023-01-24 |
| CN115641467B true CN115641467B (en) | 2024-07-05 |
Family
ID=84941545
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211206550.XA Active CN115641467B (en) | 2022-09-30 | 2022-09-30 | Method and device for identifying impurities in ore, medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115641467B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111299187A (en) * | 2020-04-03 | 2020-06-19 | 广东弓叶科技有限公司 | Construction waste identification method and construction waste sorting equipment |
| CN114972922A (en) * | 2022-05-31 | 2022-08-30 | 东北大学 | Method, device and equipment for sorting and identifying coal gangue based on machine learning |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DK2198983T3 (en) * | 2008-12-19 | 2011-12-12 | Omya Development Ag | Process for separating mineral impurities from calcium carbonate-containing rocks by X-ray sorting |
| CN102455305B (en) * | 2010-11-01 | 2014-06-18 | 北京中盾安民分析技术有限公司 | Image processing method used by device for detecting hidden matters on human body by using dual-energy X-rays |
| CN104992139B (en) * | 2015-04-23 | 2019-04-09 | 北京宇航时代科技发展有限公司 | One kind is based on motion vector and the matched falling rock detection method of circularity |
| CN205341313U (en) * | 2016-01-28 | 2016-06-29 | 北矿机电科技有限责任公司 | Control system is selected separately to ore intelligence based on ray transmission discernment |
| CN106295705B (en) * | 2016-08-17 | 2019-04-05 | 广东三三智能科技有限公司 | A kind of more color materials under movement background screen number system |
| CN113926737A (en) * | 2021-09-26 | 2022-01-14 | 河南中平自动化股份有限公司 | Coal gangue device utilizing dual-energy dual-machine X-ray and identification method thereof |
-
2022
- 2022-09-30 CN CN202211206550.XA patent/CN115641467B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111299187A (en) * | 2020-04-03 | 2020-06-19 | 广东弓叶科技有限公司 | Construction waste identification method and construction waste sorting equipment |
| CN114972922A (en) * | 2022-05-31 | 2022-08-30 | 东北大学 | Method, device and equipment for sorting and identifying coal gangue based on machine learning |
Non-Patent Citations (1)
| Title |
|---|
| 基于阈值分割和形态学相结合的金属废料X射线图像轮廓提取方法;徐祥 等;《机械与电子》;20220430;第40卷(第4期);第34页2.1节第1-2段 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115641467A (en) | 2023-01-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110334706B (en) | Image target identification method and device | |
| CN109816644B (en) | An automatic detection system for bearing defects based on multi-angle light source images | |
| US10509979B2 (en) | Inspection methods and systems | |
| CN109636824B (en) | Multi-target counting method based on image recognition technology | |
| US9715723B2 (en) | Optimization of unknown defect rejection for automatic defect classification | |
| EP3176751B1 (en) | Information processing device, information processing method, computer-readable recording medium, and inspection system | |
| Guntoro et al. | Application of machine learning techniques in mineral phase segmentation for X-ray microcomputed tomography (µCT) data | |
| Koh et al. | Utilising convolutional neural networks to perform fast automated modal mineralogy analysis for thin-section optical microscopy | |
| CN114972922B (en) | Coal gangue sorting and identification method, device and equipment based on machine learning | |
| CN111881909A (en) | Coal and gangue identification method and device, electronic equipment and storage medium | |
| Phoulady et al. | Automatic quantification and classification of cervical cancer via adaptive nucleus shape modeling | |
| CN111517092A (en) | Transmission belt tearing detection method | |
| CN117746077B (en) | Chip defect detection method, device, equipment and storage medium | |
| CN112991280B (en) | Visual detection method, visual detection system and electronic equipment | |
| CN108596151B (en) | A fast extraction method of ship target slices in large scene SAR images | |
| US20150242676A1 (en) | Method for the Supervised Classification of Cells Included in Microscopy Images | |
| CN106900601B (en) | Method for quickly and accurately identifying shrimp head points and shrimp tail points of prawn image | |
| KR20190114241A (en) | Apparatus for algae classification and cell countion based on deep learning and method for thereof | |
| CN115641467B (en) | Method and device for identifying impurities in ore, medium and electronic equipment | |
| Fu et al. | Quantitative ore texture analysis with convolutional neural networks | |
| CN110619273A (en) | Efficient iris recognition method and device | |
| Saraswathi et al. | Detection of juxtapleural nodules in lung cancer cases using an optimal critical point selection algorithm | |
| Çelik et al. | Classification of hatchery eggs using a machine learning algorithm based on image processing methods: A comparative study | |
| Mathanker et al. | Local adaptive thresholding of pecan X-ray images: reverse water flow method | |
| EP3151194B1 (en) | Method and system for enhancement of cell analysis |
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 |