Multi-parameter fused ore comprehensive screening method and device

Abstract

The application discloses a multi-parameter fusion ore comprehensive screening method and device, and relates to the technical field of ore screening; a color image of a target ore is acquired, the color image is input into an ore screening model, and the ore type of the target ore is judged; a detection scheme of the component content of the target ore is selected according to the ore type of the target ore, and a component content model is obtained by modeling the target ore through X-rays according to the detection scheme; component analysis is performed on the component content model to obtain the component content of the target ore, and the screening mode of the ore is determined according to the component content of the target ore. The ore type is judged, the cost of ore screening can be effectively reduced, the internal components of the ore are analyzed by using multi-angle X-rays, the accuracy of ore detection can be increased, different screening modes are determined according to different analysis results, the screening error can be reduced while ensuring the efficiency, and therefore the cost of the subsequent processing flow is reduced.

Description

Technical Field

[0001] This invention belongs to the field of ore screening technology, specifically relating to a multi-parameter integrated ore screening method and apparatus. Background Technology

[0002] Ores, as a precious resource bestowed by Earth, occupy a central position in human production and daily life. They are not only the basic materials for smelting metals such as steel, copper, and aluminum, supporting infrastructure construction in sectors like building, transportation, and machinery manufacturing; they are also widely used as chemical raw materials in fertilizer manufacturing, glass production, and plastics synthesis. With technological advancements, rare elements and compounds in ores have become key materials for high-tech industries such as new energy, electronics, and aerospace. The mining, screening, and deep processing of ores have not only propelled the progress of human civilization but also fostered the sustainable development of the economy and society.

[0003] Modern ore sorting relies primarily on highly automated and intelligent technological systems. After locating mineral deposits using advanced exploration techniques, large-scale machinery is employed for mining, followed by a complex sorting process. This process integrates various physical, chemical, and even biological methods, such as gravity separation, flotation, magnetic separation, and electrostatic separation, utilizing the differences in the physicochemical properties of different components within the ore for efficient separation. By combining high-precision sensors, automated control systems, and big data analytics, accurate identification of ore components and intelligent control of the sorting process are achieved, ensuring a dual improvement in sorting efficiency and product quality.

[0004] However, in the existing technology, the content of substances in the ore needs to be determined and analyzed by X-rays before screening. The sampling of the interior of the ore by a single X-ray is inaccurate, so the error in judging the substances in the ore will increase, resulting in a decrease in the efficiency of ore screening and an increase in cost. Summary of the Invention

[0005] The purpose of this invention is to solve the problem that before screening ores, X-rays are needed to determine and analyze the material content. However, the sampling of the interior of the ore by a single X-ray is inaccurate, which increases the error in judging the material content of the ore, resulting in a decrease in the efficiency of ore screening and an increase in cost. Therefore, this invention proposes a multi-parameter integrated ore screening method and device.

[0006] In a first aspect of this invention, a multi-parameter fusion-based comprehensive ore screening method is first proposed, the method comprising:

[0007] A color image of the target ore is acquired and input into an ore screening model to determine the type of the target ore. The types of ore include: miscellaneous stone, target processed ore, non-target processed ore, and mixed ore.

[0008] A detection scheme for the component content of the target ore is selected according to the type of the target ore, and a component content model is obtained by modeling the target ore with X-rays according to the detection scheme.

[0009] The component content of the target ore is obtained by performing component analysis on the component content model, and the screening method of the ore is determined based on the component content of the target ore.

[0010] Optionally, a detection scheme for the component content of the target ore is selected according to the type of the target ore, and the method includes:

[0011] The detection scheme for the component content of the target ore is determined according to the type of target ore;

[0012] If the target ore is a mixed stone, then the first detection method for determining the component content of the target ore is to exclude it;

[0013] If the target ore is a target processed ore or a non-target processed ore, the second detection method for determining the component content of the target ore is to take an X-ray image of the target ore from a single angle and perform component detection.

[0014] If the target ore is a mixed ore, the third detection method for determining the content of the target ore components is to take X-ray images of the target ore from multiple angles to obtain an X-ray image set, and to model the target ore based on the X-ray image set to obtain the content distribution model.

[0015] Optionally, when the detection scheme for the target ore component content is single X-ray component detection, the method includes:

[0016] The target ore is analyzed by X-ray component detection from a single angle to obtain the analytical results of the target ore; the analytical results are the content of the target component or the content of non-target components in the target ore.

[0017] If the content of the target component in the target ore is greater than or equal to the first component threshold, then the target ore is identified as the target processed ore and the target processed ore is screened into the first classification area;

[0018] If the content of non-target components in the target ore is greater than or equal to the first component threshold, the target ore is determined to be a non-target processed ore and the non-target processed ore is screened into the second classification area.

[0019] If the threshold value of the first component in the target ore is greater than the threshold value of the target component and the threshold value of the non-target component, and the second component value is greater than the threshold value of the second component, then the target ore is determined to be a mixed ore, the mixed ore is screened to the third classification area, and the third detection scheme is executed.

[0020] Optionally, the analysis is performed based on the content distribution model, and the method includes:

[0021] Obtain the content distribution model of each ore after implementing the third detection scheme;

[0022] The content ratio of target components and non-target components in the target ore is calculated based on the content distribution model.

[0023] Based on the stated content percentage, the fourth classification region for each ore is determined.

[0024] Optionally, the content ratio of the target component and non-target component in the target ore is calculated based on a content distribution model, the method including:

[0025] X-rays are emitted by an X-ray emitter to penetrate the target ore, and X-rays are received by an X-ray receiver to receive the fluorescent X-rays from the target ore.

[0026] The fluorescent X-rays are converted into electrical signals, and a spectrum is formed based on the electrical signals. The energy of the fluorescent X-rays in the spectrum is compared with the characteristic X-ray energies of known elements.

[0027] If the energy peak of the fluorescent X-rays in the spectrum matches the characteristic X-ray energy of a known element, then the composition of the target ore is determined.

[0028] The composition content of the target ore was determined according to the fluorescence X-ray intensity formula;

[0029] Formula for fluorescence X-ray intensity:

[0030]

[0031] Where C represents the content of the component, and I1, I2, ..., I n These represent the fluorescence X-ray intensities of the target ore received by each X-ray receiver, with α, β, ..., γ being weighting coefficients. α, β, ..., γ are all non-zero. α is the weighting coefficient for I1, β is the weighting coefficient for I2, and γ is the weighting coefficient for I... n The weighting coefficient is determined by the shooting angle.

[0032] In a second aspect of this invention, a multi-parameter fusion ore screening device is proposed, comprising: a type determination module, a component detection module, and a component analysis module.

[0033] The type determination module is used to acquire a color image of the target ore, input the color image into the ore screening model, and determine the type of the target ore; the ore types include: miscellaneous stone, target processed ore, non-target processed ore, and mixed ore;

[0034] The component detection module is used to select a detection scheme for the component content of the target ore according to the type of the target ore, and to model the target ore using X-rays according to the detection scheme to obtain a component content model;

[0035] The component analysis module is used to perform component analysis on the component content model to obtain the component content of the target ore, and to determine the ore screening method based on the component content of the target ore.

[0036] Optionally, the component detection module includes: a detection scheme determination module, a first detection scheme module, a second detection scheme module, and a third detection scheme module.

[0037] The detection scheme determination module is used to determine the detection scheme for the component content of the target ore based on the ore type of the target ore;

[0038] The first detection scheme module is used to determine that if the target ore is a mixed stone, the first detection scheme for determining the component content of the target ore is rejection;

[0039] The second detection scheme module is used to determine the composition content of the target ore by taking an X-ray image of the target ore from a single angle and performing composition detection if the target ore is a target processed ore or a non-target processed ore.

[0040] The third detection scheme module is used to determine the content of the target ore components if the target ore is a mixed ore. The third detection scheme is to take X-ray images of the target ore from multiple angles to obtain an X-ray image set, and to model the target ore based on the X-ray image set to obtain the content distribution model.

[0041] Optionally, the second detection scheme module includes: a component determination module.

[0042] The component determination module is used to perform X-ray component detection on the target ore from a single angle to obtain the analysis result of the target ore; the analysis result is the content of the target component or the content of non-target components in the target ore.

[0043] The first screening module is used to determine the target ore as a target processed ore if the content of the target component in the target ore is greater than or equal to the first component threshold, and to screen the target processed ore into the first classification area;

[0044] The second screening module is used to determine the target ore as a non-target processed ore if the content of non-target components in the target ore is greater than or equal to the first component threshold, and to screen the non-target processed ore into the second classification area;

[0045] The third screening module is used to determine the target ore as a mixed ore if the threshold of the first component in the target ore is greater than the threshold of the target component and the threshold of the non-target component, and the threshold of the second component is greater than the threshold of the second component. The mixed ore is then screened into the third classification area and the third detection scheme is executed.

[0046] Optionally, the third screening module includes: a model acquisition module, a content calculation module, and a fourth screening module.

[0047] The model acquisition module is used to acquire the content distribution model of each ore after the third detection scheme is executed;

[0048] The content calculation module is used to calculate the content ratio of the target component and non-target component in the target ore according to the content distribution model;

[0049] The fourth screening module is used to determine the fourth classification region of each ore based on the content ratio.

[0050] Optionally, the content calculation module includes: a data acquisition module, a component matching module, a component determination module, and a content determination module.

[0051] The data acquisition module is used to emit X-rays through an X-ray emitter to penetrate the target ore, and an X-ray receiver to receive the fluorescent X-rays of the target ore;

[0052] The component matching module is used to convert the fluorescent X-rays into electrical signals, generate a spectrum based on the electrical signals, and compare the fluorescent X-ray energy on the spectrum with the characteristic X-ray energy of known elements.

[0053] The composition determination module is used to determine the composition of the target ore if the energy peak of the fluorescent X-ray in the spectrum matches the characteristic X-ray energy of a known element.

[0054] The content determination module is used to determine the component content of the target ore according to the fluorescence X-ray intensity formula;

[0055] Formula for fluorescence X-ray intensity:

[0056]

[0057] Where C represents the content of the component, and I1, I2, ..., I n These represent the fluorescence X-ray intensities of the target ore received by each X-ray receiver, with α, β, ..., γ being weighting coefficients. α, β, ..., γ are all non-zero. α is the weighting coefficient for I1, β is the weighting coefficient for I2, and γ is the weighting coefficient for I... n The weighting coefficient is determined by the shooting angle.

[0058] The beneficial effects of this invention are:

[0059] This invention proposes a multi-parameter fusion-based comprehensive ore screening method. It involves acquiring a color image of the target ore and inputting it into an ore screening model to determine the ore type. Based on the ore type, a detection scheme for the target ore's component content is selected. Using X-rays, a component content model is created from the target ore. Component analysis is then performed on the component content model to obtain the target ore's component content. Finally, the screening method is determined based on the target ore's component content. Determining the ore type effectively reduces screening costs. Furthermore, utilizing multi-angle X-ray analysis of the ore's internal components increases detection accuracy. Different screening methods are determined based on different analysis results, ensuring efficiency while minimizing screening errors, thereby reducing the cost of subsequent processing steps. Attached Figure Description

[0060] The invention will now be further described with reference to the accompanying drawings.

[0061] Figure 1 A flowchart of a multi-parameter fusion-based comprehensive ore screening method is provided as an embodiment of the present invention;

[0062] Figure 2 This is a schematic diagram of the structure of a multi-parameter fusion ore screening device provided in an embodiment of the present invention. Detailed Implementation

[0063] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The term "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and B can represent: A alone, A and B simultaneously, and B alone. Furthermore, descriptions involving "first," "second," etc., in this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" can explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by the present invention.

[0064] Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0065] This invention provides a multi-parameter fusion-based comprehensive ore screening method. See also... Figure 1 , Figure 1 This is a flowchart illustrating a multi-parameter fusion-based comprehensive ore screening method provided in an embodiment of the present invention. The method includes the following steps:

[0066] S101, Obtain a color image of the target ore, input the color image into the ore screening model, and determine the type of the target ore;

[0067] S102, Select a detection scheme for the component content of the target ore according to the type of the target ore, and obtain a component content model by modeling the target ore with X-rays according to the detection scheme;

[0068] S103, Perform component analysis on the component content model to obtain the component content of the target ore, and determine the ore screening method based on the component content of the target ore.

[0069] Ore types include: mixed ore, target-processed ore, non-target-processed ore, and mixed ore;

[0070] Based on the multi-parameter fusion ore screening method provided by the embodiments of the present invention, the cost of ore screening can be effectively reduced by determining the type of ore, and the accuracy of ore detection can be increased by using multi-angle X-ray analysis of the internal composition of the ore. Different screening methods can be determined according to different analysis results, which can reduce screening errors while ensuring efficiency, thereby reducing the cost of subsequent processing.

[0071] In one implementation, the ore screening model is based on a convolutional neural network model. The model is trained by taking historical ore images and historical ore types as inputs. The ore type can be determined by inputting a color image into the ore screening model.

[0072] In one implementation, the meanings of miscellaneous stone, target processed ore, non-target processed ore, and mixed ore are as follows: Miscellaneous stone refers to stones with no utilization value that need to be removed, as their presence leads to a decrease in production efficiency; Target processed ore refers to stones with high value and a high content of these components, which need to be processed to obtain products, such as iron ore; Non-target processed ore refers to stones with value and a high content of these components, which can also be processed to obtain products, such as associated minerals of iron ore; Mixed ore refers to a type of ore in which various components are mixed, resulting in a corresponding increase in processing and production costs, such as ore formed by mixing iron ore and its associated minerals.

[0073] In one implementation, the main components of the target ore have been determined by the staff before mining, for example, the mine is an iron ore and its associated minerals; therefore, the subsequent process of determining the components of the target ore can reduce the scope of judgment accordingly.

[0074] In one implementation, the ore is screened by spraying it into a designated area using a high-pressure nozzle. In other words, the area of ​​the ore is determined by controlling the pressure of the nozzle. After pretreatment such as crushing, the ore is of uniform size and there are no excessively large ore pieces.

[0075] In one embodiment, the detection scheme for the component content of the target ore is selected according to the type of the target ore, and the method includes:

[0076] The detection scheme for the component content of the target ore is determined based on the type of target ore;

[0077] If the target ore is a mixed stone, the first detection method to determine the composition content of the target ore is to exclude it;

[0078] If the target ore is a target processed ore or a non-target processed ore, the second detection method for determining the component content of the target ore is to take an X-ray image of the target ore from a single angle and perform component detection.

[0079] If the target ore is a mixed ore, the third detection method to determine the content of the target ore components is to take X-ray images of the target ore from multiple angles to obtain an X-ray image set, and then model the target ore based on the X-ray image set to obtain a content distribution model.

[0080] In one implementation, the detection scheme for the content of target ore components can be determined according to the type of ore. Due to geological formation, the ore in the mine often has a very simple composition, which means that the main components of the ore can be determined by visual judgment. This can greatly reduce the pressure of systematic ore analysis and improve accuracy.

[0081] In one implementation, when the target ore is a target processed ore or a non-target processed ore, the composition can be determined simply by taking an X-ray image of the target ore from a single angle. This reduces unnecessary procedures, lowers costs, and increases accuracy. When the ore is a mixed ore, multiple angles are required to increase the accuracy of ore composition analysis.

[0082] In one embodiment, when the detection scheme for the content of the target ore component is single X-ray component detection, the method includes:

[0083] The target ore is analyzed by X-ray component detection from a single angle to obtain the analytical results; the analytical results are the content of the target component or the content of non-target components in the target ore.

[0084] If the content of the target component in the target ore is greater than or equal to the first component threshold, then the target ore is identified as the target processed ore and the target processed ore is screened into the first classification area;

[0085] If the content of non-target components in the target ore is greater than or equal to the first component threshold, the target ore is determined to be a non-target processed ore and is screened into the second classification area.

[0086] If the threshold of the first component in the target ore is greater than the threshold of the target component and the non-target component, and the threshold of the second component is greater than the threshold of the second component, then the target ore is determined to be a mixed ore, the mixed ore is screened to the third classification area, and the third detection scheme is executed.

[0087] In one implementation, the first classification area, the second classification area, and the third classification area are three different areas, which are sprayed by a high-pressure nozzle to different areas. The first and second classification areas are areas with high content of ore components, which can effectively reduce costs for subsequent processing. The third classification area is an area that requires secondary retrieval because the internal components of the ore are mixed, which will lead to a decrease in the quality of the processed product and an increase in costs.

[0088] In one approach, in addition to initial assessment of the ore's appearance, such as color and texture, this intuitive assessment, while efficient, carries the risk of unexpected results, as the internal condition remains unknown. Therefore, a third detection method is needed to determine the specific component content and enhance accuracy.

[0089] In one embodiment, the analysis is based on a content distribution model, and the method includes:

[0090] Obtain the content distribution model of each ore after implementing the third detection scheme;

[0091] The content ratio of target components and non-target components in the target ore is calculated based on the content distribution model.

[0092] The fourth classification zone for each ore is determined based on its content percentage.

[0093] In one implementation, the content distribution model of each ore after the third detection scheme is executed is used to calculate the content ratio of each component; wherein, the content distribution model is a three-dimensional model that displays the content of each component, and the content ratio can be calculated based on the volume of the content.

[0094] In one implementation, the fourth category region of each ore is determined according to the content ratio. The fourth category region contains multiple regions, that is, multiple regions are subdivided according to the content ratio. The materials and processing schemes for subsequent processing can be determined according to the content ratio of each region, which can effectively reduce costs and improve processing efficiency. For example, a region is defined as (target component 15%, non-target component 20%), and another region is defined as (target component 45%, non-target component 30%).

[0095] In one embodiment, the content ratio of target components and non-target components in the target ore is calculated based on a content distribution model. The method includes:

[0096] X-rays are emitted by an X-ray emitter to penetrate the target ore, and X-ray receivers receive the fluorescent X-rays from the target ore.

[0097] Fluorescent X-rays are converted into electrical signals, and a spectrum is generated based on the electrical signals. The energy of the fluorescent X-rays in the spectrum is then compared with the characteristic X-ray energies of known elements.

[0098] If the energy peak of the fluorescent X-rays in the spectrum matches the characteristic X-ray energy of a known element, then the composition of the target ore can be determined.

[0099] The composition of the target ore was determined based on the formula for fluorescence X-ray intensity.

[0100] Formula for fluorescence X-ray intensity:

[0101]

[0102] Where C represents the content of the component, and I1, I2, ..., I n These represent the fluorescence X-ray intensities of the target ore received by each X-ray receiver, with α, β, ..., γ being weighting coefficients. α, β, ..., γ are all non-zero. α is the weighting coefficient for I1, β is the weighting coefficient for I2, and γ is the weighting coefficient for I... n The weighting coefficient is determined by the shooting angle.

[0103] In one implementation, each element, upon excitation by high-energy X-rays (such as primary X-rays), releases fluorescent X-rays with specific energies. These fluorescent X-ray energies are element-specific; each element has its own unique characteristic X-ray energy. The fluorescent X-rays are captured by a detector, converted into electrical signals, and form a spectrum. The fluorescent X-ray energies on the spectrum are compared with the characteristic X-ray energies of known elements. If a certain energy peak on the spectrum matches the characteristic X-ray energy of an element, the presence of that element can be confirmed. The characteristic X-ray energy of an element is obtained through laboratory measurements and is existing, known data.

[0104] In one implementation, the weighting coefficients in the fluorescence X-ray intensity formula are determined by the shooting angle, the number of weighting coefficients is determined by the amount of fluorescence X-ray intensity of the target ore received by the X-ray receiver, and the number of X-ray receivers is determined by the actual X-ray emitters. Among them, the α weighting coefficient in αI1 is the largest of all weighting coefficients. The X-ray emitter corresponding to this α is located directly above the ore, and the deviation of the acquired data due to the shooting angle is minimal, so the weighting coefficient is the largest. The remaining weighting coefficients are equally distributed. For example, if one is installed directly above and four are installed around it, then the weight corresponding to the one directly above is 50%, and the weighting of the other four is 12.5%. The installation positions of the X-ray emitters and X-ray receivers are relative, which helps to receive data. The ore screening channel has a built-in conveyor belt, and the ore is transported on the conveyor belt. The X-ray emitters are generally installed above the screening channel, with the X-ray emitter with the largest weight installed directly above, and the remaining X-ray emitters are distributed around the one with the largest weight as the center.

[0105] Based on the same inventive concept, this invention also provides a multi-parameter fusion-based comprehensive ore screening device. See also Figure 2 , Figure 2 A schematic diagram of a multi-parameter fusion-based ore screening device provided in an embodiment of the present invention includes: a type determination module, a component detection module, and a component analysis module.

[0106] The type determination module is used to acquire color images of the target ore, input the color images into the ore screening model, and determine the type of the target ore. The ore types include: miscellaneous stone, target processed ore, non-target processed ore, and mixed ore.

[0107] The component detection module is used to select a detection scheme for the component content of the target ore according to the type of the target ore, and to obtain a component content model by modeling the target ore with X-rays according to the detection scheme.

[0108] The component analysis module is used to perform component analysis on the component content model to obtain the component content of the target ore, and to determine the ore screening method based on the component content of the target ore.

[0109] Based on the multi-parameter fusion ore screening device provided by the embodiments of the present invention, the cost of ore screening can be effectively reduced by determining the type of ore. Furthermore, the accuracy of ore detection can be increased by using multi-angle X-ray analysis to analyze the internal composition of the ore. Different screening methods can be determined according to different analysis results, which can reduce screening errors while ensuring efficiency, thereby reducing the cost of subsequent processing.

[0110] In one embodiment, the component detection module includes: a detection scheme determination module, a first detection scheme module, a second detection scheme module, and a third detection scheme module.

[0111] The detection scheme determination module is used to determine the detection scheme for the content of target ore components based on the type of target ore.

[0112] The first detection scheme module is used to determine the first detection scheme of the target ore composition content as rejection if the target ore is a mixed stone;

[0113] The second detection scheme module is used to determine the composition content of the target ore if the target ore is a target processed ore or a non-target processed ore. The second detection scheme is to take an X-ray image of the target ore from a single angle and perform composition detection.

[0114] The third detection scheme module is used to determine the content of the target ore components if the target ore is a mixed ore. The third detection scheme is to take X-ray images of the target ore from multiple angles to obtain an X-ray image set, and to model the target ore based on the X-ray image set to obtain a content distribution model.

[0115] In one embodiment, the second detection scheme module includes: a component determination module.

[0116] The composition determination module is used to perform X-ray composition detection on the target ore from a single angle to obtain the analysis results of the target ore; the analysis results are the content of the target component or the content of non-target components in the target ore;

[0117] The first screening module is used to determine the target ore as a target processed ore if the content of the target component in the target ore is greater than or equal to the first component threshold, and to screen the target processed ore into the first classification area.

[0118] The second screening module is used to determine the target ore as a non-target processed ore if the content of non-target components in the target ore is greater than or equal to the first component threshold, and to screen the non-target processed ore into the second classification area.

[0119] The third screening module is used to determine the target ore as a mixed ore if the threshold of the first component in the target ore is greater than the threshold of the target component and the threshold of the non-target component, and the threshold of the second component is greater than the threshold of the second component. The mixed ore is then screened into the third classification area and the third detection scheme is executed.

[0120] In one embodiment, the third screening module includes: a model acquisition module, a content calculation module, and a fourth screening module.

[0121] The model acquisition module is used to acquire the content distribution model of each ore after the third detection scheme is executed;

[0122] The content calculation module is used to calculate the content ratio of target components and non-target components in the target ore based on the content distribution model.

[0123] The fourth screening module is used to determine the fourth classification zone of each ore based on its content percentage.

[0124] In one embodiment, the content calculation module includes: a data acquisition module, a component matching module, a component determination module, and a content determination module.

[0125] The data acquisition module is used to emit X-rays through an X-ray emitter to penetrate the target ore, and the X-ray receiver receives the fluorescent X-rays from the target ore.

[0126] The component matching module is used to convert fluorescent X-rays into electrical signals, generate a spectrum based on the electrical signals, and compare the fluorescent X-ray energies on the spectrum with the characteristic X-ray energies of known elements.

[0127] The composition determination module is used to determine the composition of a target ore if the energy peak of the fluorescent X-rays in the spectrum matches the characteristic X-ray energy of a known element.

[0128] The content determination module is used to determine the component content of the target ore based on the fluorescence X-ray intensity formula;

[0129] Formula for fluorescence X-ray intensity:

[0130]

[0131] Where C represents the content of the component, and I1, I2, ..., I n These represent the fluorescence X-ray intensities of the target ore received by each X-ray receiver, where α, β, ..., γ are weighting coefficients. α, β, ..., γ are all non-zero. α is the weighting coefficient for I1, β is the weighting coefficient for I2, and γ is the weighting coefficient for I... n The weighting coefficient is determined by the shooting angle.

[0132] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the patent coverage of this invention.

Claims

1. A multi-parameter fusion-based comprehensive ore screening method, characterized in that, The method includes: A color image of the target ore is acquired and input into an ore screening model to determine the type of the target ore. The types of ore include: miscellaneous stone, target processed ore, non-target processed ore, and mixed ore. A detection scheme for the component content of the target ore is selected according to the type of the target ore, and a component content model is obtained by modeling the target ore using X-rays according to the detection scheme. The component content of the target ore is obtained by performing component analysis on the component content model, and the screening method of the ore is determined based on the component content of the target ore. The method includes selecting a detection scheme for the component content of the target ore based on the type of the target ore, and the method comprising: The detection scheme for the component content of the target ore is determined based on the type of target ore; If the target ore is a mixed stone, then the first detection method for determining the component content of the target ore is to exclude it; If the target ore is a target processed ore or a non-target processed ore, the second detection method for determining the component content of the target ore is to take an X-ray image of the target ore from a single angle and perform component detection. If the target ore is a mixed ore, the third detection method for determining the content of the target ore components is to take X-ray images of the target ore from multiple angles to obtain an X-ray image set, and to model the target ore based on the X-ray image set to obtain a content distribution model; When the detection scheme for the target ore component content is single X-ray component detection, the method includes: The target ore is analyzed by X-ray component detection from a single angle to obtain the analytical results of the target ore; the analytical results are the content of the target component or the content of non-target components in the target ore. If the content of the target component in the target ore is greater than or equal to the first component threshold, then the target ore is identified as the target processed ore and the target processed ore is screened into the first classification area; If the content of non-target components in the target ore is greater than or equal to the first component threshold, the target ore is determined to be a non-target processed ore and the non-target processed ore is screened into the second classification area. If the threshold value of the first component in the target ore is greater than the threshold value of the target component and the threshold value of the non-target component, and the second component value is greater than the threshold value of the second component, then the target ore is determined to be a mixed ore, the mixed ore is screened to the third classification area, and the third detection scheme is executed.

2. The multi-parameter fusion-based comprehensive ore screening method according to claim 1, characterized in that, The analysis is performed based on the content distribution model, and the method includes: Obtain the content distribution model of each ore after implementing the third detection scheme; The content ratio of target components and non-target components in the target ore is calculated based on the content distribution model. Based on the stated content percentage, the fourth classification region for each ore is determined.

3. The multi-parameter fusion-based comprehensive ore screening method according to claim 2, characterized in that, The content ratio of target components and non-target components in the target ore is calculated based on a content distribution model. The method includes: X-rays are emitted by an X-ray emitter to penetrate the target ore, and X-rays are received by an X-ray receiver to receive the fluorescent X-rays from the target ore. The fluorescent X-rays are converted into electrical signals, and a spectrum is formed based on the electrical signals. The energy of the fluorescent X-rays in the spectrum is compared with the characteristic X-ray energies of known elements. If the energy peak of the fluorescent X-rays in the spectrum matches the characteristic X-ray energy of a known element, then the composition of the target ore is determined. The composition content of the target ore was determined according to the fluorescence X-ray intensity formula; Formula for fluorescence X-ray intensity: ； Where C represents the component content, , … These represent the fluorescence X-ray intensities of the target ore received by each X-ray receiver, where α, β, ..., γ are weighting coefficients, and α, β, ..., γ are all non-zero. The weighting coefficient, β is The weighting coefficient, γ is The weighting coefficient is determined by the shooting angle.

4. A multi-parameter fusion ore comprehensive screening device, characterized in that, The device includes: a type identification module, a component detection module, and a component analysis module. The type determination module is used to acquire a color image of the target ore, input the color image into the ore screening model, and determine the type of the target ore; the ore types include: miscellaneous stone, target processed ore, non-target processed ore, and mixed ore; The component detection module is used to select a detection scheme for the component content of the target ore according to the type of the target ore, and to model the target ore using X-rays according to the detection scheme to obtain a component content model; The component analysis module is used to perform component analysis on the component content model to obtain the component content of the target ore, and to determine the screening method of the ore based on the component content of the target ore. The component detection module includes: a detection scheme determination module, a first detection scheme module, a second detection scheme module, and a third detection scheme module. The detection scheme determination module is used to determine the detection scheme for the component content of the target ore based on the ore type of the target ore; The first detection scheme module is used to determine that if the target ore is a mixed stone, the first detection scheme for determining the component content of the target ore is rejection; The second detection scheme module is used to determine the composition content of the target ore by taking an X-ray image of the target ore from a single angle and performing composition detection if the target ore is a target processed ore or a non-target processed ore. The third detection scheme module is used to determine the content of the target ore components if the target ore is a mixed ore. The third detection scheme is to take X-ray images of the target ore from multiple angles to obtain an X-ray image set, and to model the target ore based on the X-ray image set to obtain a content distribution model. The second detection scheme module includes: The component determination module is used to perform X-ray component detection on the target ore from a single angle to obtain the analysis results of the target ore; the analysis results are the content of target components or non-target components in the target ore. The first screening module is used to determine the target ore as a target processed ore if the content of the target component in the target ore is greater than or equal to the first component threshold, and to screen the target processed ore into the first classification area. The second screening module is used to determine the target ore as a non-target processed ore if the content of non-target components in the target ore is greater than or equal to the first component threshold, and to screen the non-target processed ore into the second classification area. The third screening module is used to determine the target ore as a mixed ore if the threshold of the first component in the target ore is greater than the threshold of the target component and the threshold of the non-target component, and the threshold of the second component is greater than the threshold of the second component. The mixed ore is then screened into the third classification area and the third detection scheme is executed.

5. The multi-parameter fusion ore comprehensive screening device according to claim 4, characterized in that, The third screening module includes: a model acquisition module, a content calculation module, and a fourth screening module. The model acquisition module is used to acquire the content distribution model of each ore after the third detection scheme is executed; The content calculation module is used to calculate the content ratio of the target component and non-target component in the target ore according to the content distribution model; The fourth screening module is used to determine the fourth classification region of each ore based on the content ratio.

6. The multi-parameter fusion ore comprehensive screening device according to claim 5, characterized in that, The content calculation module includes: a data acquisition module, a component matching module, a component determination module, and a content determination module. The data acquisition module is used to emit X-rays through an X-ray emitter to penetrate the target ore, and an X-ray receiver to receive the fluorescent X-rays of the target ore; The component matching module is used to convert the fluorescent X-rays into electrical signals, generate a spectrum based on the electrical signals, and compare the fluorescent X-ray energy on the spectrum with the characteristic X-ray energy of known elements. The composition determination module is used to determine the composition of the target ore if the energy peak of the fluorescent X-ray in the spectrum matches the characteristic X-ray energy of a known element. The content determination module is used to determine the component content of the target ore according to the fluorescence X-ray intensity formula; Formula for fluorescence X-ray intensity: ； Where C represents the component content, , … These represent the fluorescence X-ray intensities of the target ore received by each X-ray receiver, where α, β, ..., γ are weighting coefficients, and α, β, ..., γ are all non-zero. The weighting coefficient, β is The weighting coefficient, γ is The weighting coefficient is determined by the shooting angle.

Images