Material testing equipment and methods

Abstract

The present application provides a material detection device and method, including: a feeding device, a material detection channel, a material detection device and a processor; the feeding device is used to convey the material to be detected to the entrance of the material detection channel; the material detection channel is used to transmit the material; the material detection device includes at least two X-ray sources and linear array detectors corresponding to the X-ray sources; the X-ray sources and the corresponding linear array detectors are relatively arranged on both sides of the material detection channel, wherein the X-rays emitted by any two X-ray sources have different ray intensities, and the linear array detectors include a low-energy detection module with a filter and a high-energy detection module without a filter; the processor is respectively connected to each linear array detector, and is used to determine the material type to which the material belongs according to the first ray intensity detected by the high-energy detection module of each linear array detector and the second ray intensity detected by the low-energy detection module. The present application can improve the accuracy of material detection.

Description

Technical Field

[0001] The present application relates to the technical field of ore detection, and in particular to a material detection device and method. Background Art

[0002] Dry material testing has unique advantages in the field of coal sorting due to its advantages of not using water and not producing coal slime. In dry coal sorting, the concentrate and tailings in the material are generally sorted and processed by a dry sorter.

[0003] In the prior art, the dry separator includes an X-ray identification device, which detects the ash value of the material, determines the type of coal material to which the material belongs according to the ash value, and classifies the concentrate and tailings in the material.

[0004] However, the inventors have discovered that the prior art has at least the following technical problems: since the ash content of the material may be affected by thickness, which in turn leads to a large error in the ash content of the detected material, the accuracy of detecting the material using the above method is low. Summary of the invention

[0005] Based on this, the present application provides a material detection device and method, which can improve the accuracy of material detection.

[0006] In one aspect, the present application provides a material detection device, comprising: a feeding device, a material detection channel, a material detection device, and a processor;

[0007] The feeding device is used to convey the material to be detected to the entrance of the material detection channel; the material detection channel is used to transport the material;

[0008] The material detection device comprises at least two X-ray sources and linear array detectors corresponding to the X-ray sources one by one; the X-ray sources and the corresponding linear array detectors are arranged on both sides of the material detection channel relatively, wherein the X-rays emitted by any two X-ray sources have different intensities, and the linear array detectors comprise a low-energy detection module provided with a filter and a high-energy detection module not provided with a filter;

[0009] The processor is connected to each linear array detector respectively, and is used to obtain the radiation intensity detected by the high-energy detection module and the radiation intensity detected by the low-energy detection module of each linear array detector during the process of transmitting the material in the material detection channel, and determine the material type to which the material belongs.

[0010] In a possible implementation, the material detection device includes a first X-ray source, a second X-ray source, a first linear array detector corresponding to the first X-ray source, and a second linear array detector corresponding to the first X-ray source; the first X-ray source and the first linear array detector are relatively arranged on both sides of the material detection channel, and the second X-ray source and the second linear array detector are relatively arranged on both sides of the material detection channel; the processor is respectively connected to the first linear array detector and the second linear array detector; wherein the ray intensity of the X-ray emitted by the first X-ray source is greater than the ray intensity of the X-ray emitted by the second X-ray source.

[0011] In a possible implementation, the first linear array detector includes a first high-energy detection module and a first low-energy detection module, and the first low-energy detection module is provided with a first filter; the second linear array detector includes a second high-energy detection module and a second low-energy detection module, and the second low-energy detection module is provided with a second filter.

[0012] In a possible implementation, the material detection equipment further includes: a separation device; the processor is connected to the separation device, and is used to control the separation device to separate the material according to the material type to which the material belongs.

[0013] On the other hand, the present application provides a material detection method, which is applied to the above-mentioned material detection device, and the method comprises:

[0014] For each linear array detector corresponding to an X-ray source in the material detection device, the ray intensity detected by the high-energy detection module and the ray intensity detected by the low-energy detection module of the linear array detector are obtained, wherein the ray intensity detected by the high-energy detection module includes: the ray intensity of the X-ray detected before the material reaches the high-energy detection module, and the ray intensity of the X-ray detected after the material passes through the high-energy detection module; the ray intensity detected by the low-energy detection module includes: the ray intensity of the X-ray detected before the material reaches the low-energy detection module, and the ray intensity of the X-ray detected after the material passes through the low-energy detection module;

[0015] According to the ray intensity detected by the high-energy detection module of the linear array detector corresponding to each X-ray source and the ray intensity detected by the low-energy detection module of the linear array detector corresponding to each X-ray source, a plurality of classification parameters are determined, and according to the plurality of classification parameters, the material type to which the material belongs is determined; wherein the ray intensity of the X-rays emitted by any two X-ray sources is different.

[0016] In a possible implementation, the material detection device includes a first X-ray source, a second X-ray source, a first linear array detector, and a second linear array detector; wherein the first linear array detector includes a first high-energy detection module and a first low-energy detection module, and the second linear array detector includes a second high-energy detection module and a second low-energy detection module; accordingly, according to the ray intensity detected by the high-energy detection module of the linear array detector corresponding to each X-ray source and the ray intensity detected by the low-energy detection module of the linear array detector corresponding to each X-ray source, a plurality of classification parameters are determined, and according to the plurality of classification parameters, the material type to which the material belongs is determined, including: combining the first ray intensity detected by the first high-energy detection module, the second ray intensity detected by the first low-energy detection module, the third ray intensity detected by the second high-energy detection module, and the fourth ray intensity detected by the second low-energy detection module in pairs to determine 6 ray intensity combinations; according to the 6 ray intensity combinations and a preset classification model, 6 classification parameters are obtained; according to the 6 classification parameters, the material type to which the material belongs is determined.

[0017] In a possible implementation, the first ray intensity detected by the first high-energy detection module, the second ray intensity detected by the first low-energy detection module, the third ray intensity detected by the second high-energy detection module, and the fourth ray intensity detected by the second low-energy detection module are combined in pairs to determine six ray intensity combinations, including: combining the first ray intensity and the second ray intensity to obtain a first ray intensity combination; combining the first ray intensity and the third ray intensity to obtain a second ray intensity combination; combining the first ray intensity and the fourth ray intensity to obtain a third ray intensity combination; combining the second ray intensity and the third ray intensity to obtain a fourth ray intensity combination; combining the second ray intensity and the fourth ray intensity to obtain a fifth ray intensity combination; combining the third ray intensity and the fourth ray intensity to obtain a sixth ray intensity combination.

[0018] In a possible implementation, the first ray intensity detected by the first high-energy detection module includes: the ray intensity of the first X-ray detected before the material reaches the first high-energy detection module, and the ray intensity of the first X-ray detected after the material passes through the first high-energy detection module; the second ray intensity detected by the first low-energy detection module includes: the ray intensity of the first X-ray detected before the material reaches the first low-energy detection module, and the ray intensity of the first X-ray detected after the material passes through the first low-energy detection module; the third ray intensity detected by the second high-energy detection module The line intensity includes: the ray intensity of the second X-ray detected before the material reaches the second high-energy detection module, and the ray intensity of the second X-ray detected after passing through the material when the material passes through the second high-energy detection module; the fourth ray intensity detected by the second low-energy detection module includes: the ray intensity of the second X-ray detected before the material reaches the second low-energy detection module, and the ray intensity of the second X-ray detected after passing through the material when the material passes through the second low-energy detection module; wherein, the first X-ray is the X-ray emitted by the first X-ray source, and the second X-ray is the X-ray emitted by the second X-ray source.

[0019] In a possible implementation, six classification parameters are obtained based on six combinations of ray intensities and a preset classification model, including: for a first ray intensity combination, determining a first ratio between the ray intensity of a first X-ray detected before the material reaches the first high-energy detection module in the first ray intensity and the ray intensity of a first X-ray detected after the material passes through the first high-energy detection module, and determining a second ratio between the ray intensity of a first X-ray detected before the material reaches the first low-energy detection module in the second ray intensity and the ray intensity of a first X-ray detected after the material passes through the first low-energy detection module; inputting the first ratio and the second ratio into a preset classification model to obtain one classification parameter; for a second ray intensity combination, determining the first ratio, and determining a second ratio between the ray intensity of a second X-ray detected before the material reaches the second high-energy detection module and the ray intensity of a second X-ray detected after the material passes through the second high-energy detection module. three ratios; input the first ratio and the third ratio into the preset classification model to obtain one classification parameter; for the third ray intensity combination, determine the first ratio, and determine the fourth ratio between the ray intensity of the second X-ray detected before the material reaches the second low-energy detection module and the ray intensity of the second X-ray detected after passing through the material when the material passes through the second low-energy detection module; input the first ratio and the fourth ratio into the preset classification model to obtain one classification parameter; for the fourth ray intensity combination, determine the second ratio, and determine the third ratio; input the second ratio and the third ratio into the preset classification model to obtain one classification parameter; for the fifth ray intensity combination, determine the second ratio, and determine the fourth ratio; input the first ratio and the fourth ratio into the preset classification model to obtain one classification parameter; for the sixth ray intensity combination, determine the third ratio, and determine the fourth ratio; input the third ratio and the fourth ratio into the preset classification model to obtain one classification parameter.

[0020] In a possible implementation, determining the material type to which the material belongs based on the six classification parameters includes: determining the average of the six classification parameters, if the average is greater than or equal to a preset value, determining that the material type to which the material belongs is a target mineral, and if the average is less than the preset value, determining that the material type to which the material belongs is a non-target mineral; or, determining the median of the six classification parameters, if the median is greater than or equal to the preset value, determining that the material type to which the material belongs is a target mineral, and if the median is less than the preset value, determining that the material type to which the material belongs is a non-target mineral; or, inputting the six classification parameters into a preset support vector machine model, if the output result is greater than 0, determining that the material type to which the material belongs is a target mineral, and if the output result is less than 0, determining that the material type to which the material belongs is a non-target mineral.

[0021] The present application provides a material detection device and method, comprising: a feeding device, a material detection channel, a material detection device and a processor; the feeding device is used to convey the material to be detected to the entrance of the material detection channel; the material detection channel is used to transmit the material; the material detection device comprises at least two X-ray sources and linear array detectors corresponding to the X-ray sources one by one; the X-ray sources and the corresponding linear array detectors are relatively arranged on both sides of the material detection channel, wherein the X-rays emitted by any two X-ray sources have different ray intensities, and the linear array detector comprises a low-energy detection module with a filter and a high-energy detection module without a filter; the processor is connected to each linear array detector respectively, and is used to obtain the ray intensity detected by the high-energy detection module and the ray intensity detected by the low-energy detection module of each linear array detector during the process of transmitting the material in the material detection channel, and determine the material type to which the material belongs. In the embodiment of the present application, by using multiple X-ray sources and linear array detectors, combined with the high-energy detection module and the low-energy detection module in the linear array detector for detection, multiple classification parameters corresponding to the ray intensities can be obtained, and the material type to which the material belongs can be determined in combination with the multiple classification parameters. Compared with material detection through a single ray intensity, the material type determined by combining multiple classification parameters can reduce the error of material detection, thereby improving the detection accuracy of the material detection equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0023] Figure 1Schematic diagram of the structure of the material detection device provided in the embodiment of the present application Figure 1 ;

[0024] Figure 2 Schematic diagram of the structure of the linear array detector provided in the embodiment of the present application Figure 1 ;

[0025] Figure 3 The process of the material detection method provided in the embodiment of the present application Figure 1 .

[0026] Reference numerals:

[0027] 101: feeding device;

[0028] 102: Material detection channel;

[0029] 103: Material detection device;

[0030] 1031: X-ray source;

[0031] 1032: Linear array detector;

[0032] 104: processor;

[0033] 105: Separation device. DETAILED DESCRIPTION

[0034] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of methods and devices consistent with some aspects of the present application as detailed in the appended claims.

[0035] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the implementation of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0036] Dry material testing has unique advantages in the field of coal sorting due to its advantages of not using water and not producing coal slime. In dry coal sorting, the concentrate and tailings in the material are generally sorted and processed by a dry sorter.

[0037] In the prior art, the dry sorting machine includes an X-ray identification device, which detects the ash value of the material, determines the type of coal material to which the material belongs according to the ash value, and classifies the concentrate and tailings in the material. However, since the ash value of the material may be affected by the thickness, which leads to a large error in the ash value of the material, the accuracy of the material detection by the above method is low.

[0038] In view of the above-mentioned problems existing in the prior art, the material detection equipment provided by the present application includes: a feeding device, a material detection channel, a material detection device and a processor; the feeding device is used to transport the material to be detected to the entrance of the material detection channel; the material detection channel is used to transmit the material; the material detection device includes at least two X-ray sources and linear array detectors corresponding to the X-ray sources one by one; the X-ray sources and the corresponding linear array detectors are relatively arranged on both sides of the material detection channel, wherein the X-rays emitted by any two X-ray sources have different ray intensities, and the linear array detectors include a low-energy detection module with a filter and a high-energy detection module without a filter; the processor is connected to each linear array detector respectively, and is used to obtain the ray intensity detected by the high-energy detection module and the ray intensity detected by the low-energy detection module of each linear array detector during the process of transmitting the material through the material detection channel, and determine the material type to which the material belongs.

[0039] Since the above-mentioned material detection equipment can use multiple X-ray sources and linear array detectors, combined with the high-energy detection module and the low-energy detection module in the linear array detector for detection, it can obtain classification parameters corresponding to multiple ray intensities, and determine the material type to which the material belongs in combination with the multiple classification parameters. Compared with material detection through a single ray intensity, the material type determined by combining multiple classification parameters can reduce the error of material detection, thereby improving the detection accuracy of the material detection equipment.

[0040] The technical solution of the present application is described in detail below with reference to the accompanying drawings using specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0041] in, Figure 1 Schematic diagram of the structure of the material detection device provided in the embodiment of the present application Figure 1 .

[0042] Reference Figure 1 As shown, the material detection equipment includes: a feeding device 101, a material detection channel 102, a material detection device 103 and a processor 104.

[0043] The feeding device 101 is used to transport the material to be detected to the entrance of the material detection channel 102; the material detection channel 102 is used to transport the material.

[0044] The material detection device 103 includes at least two X-ray sources 1031 and linear array detectors 1032 corresponding to the X-ray sources 1031 one by one; the X-ray sources 1031 and the corresponding linear array detectors 1032 are relatively arranged on both sides of the material detection channel 102, wherein the X-rays emitted by any two X-ray sources 1031 have different intensities, and the linear array detectors 1032 include a low-energy detection module with a filter and a high-energy detection module without a filter.

[0045] The processor 104 is connected to each linear array detector 1032 respectively, and is used to obtain the radiation intensity detected by the high-energy detection module and the radiation intensity detected by the low-energy detection module of each linear array detector 1032 during the material transmission process of the material detection channel 102, so as to determine the material type to which the material belongs.

[0046] In one possible implementation, Figure 2 As shown, the material detection device 103 includes a first X-ray source, a second X-ray source, a first linear array detector corresponding to the first X-ray source, and a second linear array detector corresponding to the first X-ray source.

[0047] The first X-ray source and the first linear array detector are relatively arranged on both sides of the material detection channel 102 , and the second X-ray source and the second linear array detector are relatively arranged on both sides of the material detection channel 102 .

[0048] The processor 104 is connected to the first linear array detector and the second linear array detector respectively; wherein the ray intensity of the X-ray emitted by the first X-ray source is greater than the ray intensity of the X-ray emitted by the second X-ray source.

[0049] It should be noted that in the embodiment of the present disclosure, the values ​​of the intensity of the X-rays emitted by the first X-ray source and the intensity of the X-rays emitted by the second X-ray source are not specifically limited and can be set as needed.

[0050] In one possible implementation, Figure 2 As shown, the first linear array detector includes a first high-energy detection module and a first low-energy detection module, and the first low-energy detection module is provided with a first filter; the second linear array detector includes a second high-energy detection module and a second low-energy detection module, and the second low-energy detection module is provided with a second filter.

[0051] The first filter and the second filter can reduce the intensity of the X-rays, and obtain two different ray intensities through a single linear array detector. Optionally, the first filter and the second filter can be metal filters; for example, copper filters. The thickness of the first filter and the second filter can be the same or different. In the embodiment of the present disclosure, the thickness of the first filter and the second filter is not specifically limited and can be set as needed.

[0052] In one possible implementation, Figure 1 As shown, the material detection equipment further includes: a separation device 105; a processor connected to the separation device 105, and used to control the separation device 105 to separate the material according to the material type to which the material belongs.

[0053] Optionally, the separation device 105 may be an air pump. The processor 104 may control the air pump to turn on or off through a solenoid valve. For example, when the material type is gangue (useless rock or tailings), the air pump is turned on through the solenoid valve, and the gangue can be separated from the material through the air pump.

[0054] In the embodiment of the present disclosure, since the above-mentioned material detection equipment can obtain classification parameters corresponding to multiple ray intensities through multiple X-ray sources and linear array detectors, combined with the high-energy detection module and the low-energy detection module in the linear array detector, and determine the material type to which the material belongs in combination with the multiple classification parameters, compared with material detection through a single ray intensity, the material type determined by combining multiple classification parameters can reduce the error of material detection, thereby improving the detection accuracy of the material detection equipment.

[0055] Figure 3 The process of the material detection method provided in the embodiment of the present application Figure 1 .like Figure 3 As shown, the material detection method comprises:

[0056] S301. For each linear array detector corresponding to each X-ray source in the material detection device, obtain the radiation intensity detected by the high-energy detection module and the radiation intensity detected by the low-energy detection module of the linear array detector, wherein the radiation intensity detected by the high-energy detection module includes: the radiation intensity of the X-rays detected before the material reaches the high-energy detection module, and the radiation intensity of the X-rays detected after the material passes through the high-energy detection module; the radiation intensity detected by the low-energy detection module includes: the radiation intensity of the X-rays detected before the material reaches the low-energy detection module, and the radiation intensity of the X-rays detected after the material passes through the low-energy detection module.

[0057] In some embodiments, the material detection device includes a first X-ray source, a second X-ray source, a first linear array detector, and a second linear array detector; wherein the first linear array detector includes a first high-energy detection module and a first low-energy detection module, and the second linear array detector includes a second high-energy detection module and a second low-energy detection module.

[0058] Optionally, the first ray intensity detected by the first high-energy detection module includes: the ray intensity of the first X-ray detected before the material reaches the first high-energy detection module, and the ray intensity of the first X-ray detected after passing through the material when the material passes through the first high-energy detection module.

[0059] The second ray intensity detected by the first low-energy detection module includes: the ray intensity of the first X-ray detected before the material reaches the first low-energy detection module, and the ray intensity of the first X-ray detected after passing through the material when the material passes through the first low-energy detection module.

[0060] The third ray intensity detected by the second high energy detection module includes: the ray intensity of the second X-ray detected before the material reaches the second high energy detection module, and the ray intensity of the second X-ray detected after passing through the material when the material passes through the second high energy detection module.

[0061] The fourth ray intensity detected by the second low-energy detection module includes: the ray intensity of the second X-ray detected before the material reaches the second low-energy detection module, and the ray intensity of the second X-ray detected after the material passes through the second low-energy detection module;

[0062] The first X-ray is the X-ray emitted by the first X-ray source, and the second X-ray is the X-ray emitted by the second X-ray source.

[0063] S302, determining a plurality of classification parameters according to the radiation intensity detected by the high-energy detection module of the linear array detector corresponding to each X-ray source and the radiation intensity detected by the low-energy detection module of the linear array detector corresponding to each X-ray source, and determining the material type to which the material belongs according to the plurality of classification parameters; wherein the radiation intensity of the X-rays emitted by any two X-ray sources is different.

[0064] In the disclosed embodiment, multiple classification parameters can be obtained according to the radiation intensity detected by the high-energy detection module of each linear array detector, the radiation intensity detected by the high-energy detection module of each linear array detector, and a preset classification model. The more X-ray sources and linear array detectors corresponding to the X-ray sources, the more classification parameters are obtained, and the higher the accuracy of determining the material type to which the material belongs. The following is a detailed description of the method for determining the material type by taking the example that the number of X-ray sources is 2 and the number of linear array detectors corresponding to the X-ray sources is 2:

[0065] In some embodiments, the material detection device includes a first X-ray source, a second X-ray source, a first linear array detector, and a second linear array detector; wherein the first linear array detector includes a first high-energy detection module and a first low-energy detection module, and the second linear array detector includes a second high-energy detection module and a second low-energy detection module; accordingly, step S302 may include the following steps (1) to (3):

[0066] (1) The first ray intensity detected by the first high-energy detection module, the second ray intensity detected by the first low-energy detection module, the third ray intensity detected by the second high-energy detection module, and the fourth ray intensity detected by the second low-energy detection module are combined in pairs to determine six ray intensity combinations.

[0067] Optionally, this step may include: combining the first ray intensity and the second ray intensity to obtain a first ray intensity combination; combining the first ray intensity and the third ray intensity to obtain a second ray intensity combination; combining the first ray intensity and the fourth ray intensity to obtain a third ray intensity combination; combining the second ray intensity and the third ray intensity to obtain a fourth ray intensity combination; combining the second ray intensity and the fourth ray intensity to obtain a fifth ray intensity combination; combining the third ray intensity and the fourth ray intensity to obtain a sixth ray intensity combination.

[0068] (2) Based on the six ray intensity combinations and the preset classification model, six classification parameters are obtained.

[0069] Optionally, this step may include: determining, for the first ray intensity combination, a first ratio between the ray intensity of the first X-ray detected by the first high-energy detection module before the material reaches the first high-energy detection module in the first ray intensity and the ray intensity of the first X-ray detected by the first high-energy detection module after passing through the material when the material passes through the first high-energy detection module; and determining a second ratio between the ray intensity of the first X-ray detected by the first low-energy detection module before the material reaches the first low-energy detection module in the second ray intensity and the ray intensity of the first X-ray detected by the first low-energy detection module after passing through the material when the material passes through the first low-energy detection module; inputting the first ratio and the second ratio into a preset classification model to obtain 1 classification parameter (which can be expressed as K1).

[0070] Optionally, the preset classification model can be expressed as the following formula:

[0071]

[0072] Among them, I 01I represents the intensity of the first X-ray detected before the material reaches the first high-energy detection module in the first ray intensity; I1 represents the intensity of the first X-ray detected after the material passes through the first high-energy detection module; I 02 I2 represents the intensity of the first X-ray detected before the material reaches the first low-energy detection module in the second ray intensity; I3 represents the intensity of the first X-ray detected after the material passes through the first low-energy detection module.

[0073] For the second ray intensity combination, determine a first ratio, and determine a third ratio between the ray intensity of the second X-ray detected by the second high-energy detection module before the material reaches the second high-energy detection module and the ray intensity of the second X-ray detected by the second high-energy detection module after passing through the material when the material passes through the second high-energy detection module; input the first ratio and the third ratio into a preset classification model to obtain 1 classification parameter (which can be expressed as K2).

[0074] Optionally, the preset classification model can be expressed as the following formula:

[0075]

[0076] Among them, I 01 I represents the intensity of the first X-ray detected before the material reaches the first high-energy detection module in the first ray intensity; I1 represents the intensity of the first X-ray detected after the material passes through the first high-energy detection module; I 03 I1 represents the intensity of the second X-ray detected before the material reaches the second high-energy detection module; I2 represents the intensity of the second X-ray detected after the material passes through the second high-energy detection module.

[0077] For the third ray intensity combination, determine a first ratio, and determine a fourth ratio between the ray intensity of the second X-ray detected by the second low-energy detection module before the material reaches the second low-energy detection module and the ray intensity of the second X-ray detected by the second low-energy detection module after passing through the material when the material passes through the second low-energy detection module; input the first ratio and the fourth ratio into a preset classification model to obtain 1 classification parameter (which can be expressed as K3).

[0078] Optionally, the preset classification model can be expressed as the following formula:

[0079]

[0080] Among them, I 01I represents the intensity of the first X-ray detected before the material reaches the first high-energy detection module in the first ray intensity; I1 represents the intensity of the first X-ray detected after the material passes through the first high-energy detection module; I 04 I4 represents the intensity of the second X-ray detected before the material reaches the second low-energy detection module; I5 represents the intensity of the second X-ray detected after the material passes through the second low-energy detection module.

[0081] For the fourth ray intensity combination, determine the second ratio, and determine the third ratio; input the second ratio and the third ratio into the preset classification model to obtain a classification parameter (which can be expressed as K4). Optionally, the preset classification model can be expressed as the following formula:

[0082]

[0083] For the fifth ray intensity combination, determine the second ratio, and determine the fourth ratio; input the first ratio and the fourth ratio into the preset classification model to obtain a classification parameter (which can be expressed as K5). Optionally, the preset classification model can be expressed as the following formula:

[0084]

[0085] For the sixth ray intensity combination, determine the third ratio, and determine the fourth ratio; input the third ratio and the fourth ratio into the preset classification model to obtain a classification parameter (which can be expressed as K6). Optionally, the preset classification model can be expressed as the following formula:

[0086]

[0087] (3) Determine the material type to which the material belongs based on the six classification parameters.

[0088] In some embodiments, this step may include: determining the average of 6 classification parameters; if the average is greater than or equal to a preset value, determining that the material type to which the material belongs is a target mineral; if the average is less than the preset value, determining that the material type to which the material belongs is a non-target mineral.

[0089] In other embodiments, this step may include: determining the median of 6 classification parameters; if the median is greater than or equal to a preset value, determining that the material type to which the material belongs is a target mineral; if the median is less than the preset value, determining that the material type to which the material belongs is a non-target mineral.

[0090] The value of the preset value is not specifically limited and can be set as needed. Optionally, the preset value can be determined by experiment. For example, the critical value between the concentrate and the tailings can be obtained by testing the average or median of the classification parameters corresponding to the materials (concentrate and tailings) of known classification, and the critical value can be determined as the preset value.

[0091] In other embodiments, this step may include: inputting 6 classification parameters into a preset support vector machine model; if the output result is greater than 0, determining that the material type to which the material belongs is a target mineral; if the output result is less than 0, determining that the material type to which the material belongs is a non-target mineral.

[0092] Optionally, the preset support vector machine model may be a classification decision model, which may be expressed as: Among them, sign is also called the sign function, and its function is to take the sign (positive or negative) of a number. If the number is greater than 0, it returns 1 (at this time, it is determined that the material type to which the material belongs is the target mineral; for example, concentrate); if the number is less than 0, it returns -1 (at this time, it is determined that the material type to which the material belongs is a non-target mineral; for example, tailings).

[0093] Among them, ω*K may include ω1K1, ω2K2, ω3K3, ω4K4, ω5K5, ω6K6. Among them, ω1, ω2, ω3, ω4, ω5, ω6 and b can be solved by the method of classified hyperplane.

[0094] For example, four concentrate samples and three tailings samples are selected, and the values ​​of K1, K2, K3, K4, K5, and K6 are calculated respectively. Through the K values ​​of the seven samples, the values ​​of ω1, ω2, ω3, ω4, ω5, ω6, and b can be obtained.

[0095] Optionally, the specific method for solving ω and b by the classification hyperplane method is as follows. A preset number of two types of mineral samples can be manually selected (for example, 4 concentrate samples and 3 tailings samples). It should be noted that if the mineral sample is a concentrate sample, the values ​​of K1, K2, K3, K4, K5, and K6 are calculated respectively and taken as positive values, and the k value of the mineral sample is obtained as follows: k = (K n 1. K n 2. K n 3. K n 4. K n 5. K n 6), where n is the block number. If the mineral sample is a tailings sample, calculate the values ​​of K1, K2, K3, K4, K5, and K6 respectively and take the negative value to obtain the k value of the mineral sample: k = (-K n 1, -K n 2, -K n3, -K n 4, -K n 5, -K n 6), where n is the block number.

[0096] Specifically, taking 4 concentrate samples and 3 tailings samples as an example, the equation group corresponding to the classification hyperplane may include:

[0097] Min{0.5*(ω1 2 +ω2 2 +ω3 2 +ω4 2 +ω5 2 +ω6 2 )}

[0098] ω.b

[0099] st

[0100] K 1 1*ω1+K 1 2*ω2+K 1 3*ω3+K 1 3*ω4+K 1 4*ω5+K 1 5*ω6+b≥1

[0101] K 2 1*ω1+K 2 2*ω2+K 2 3*ω3+K 2 3*ω4+K 2 4*ω5+K 2 5*ω6+b≥1

[0102] K 3 1*ω1+K 3 2*ω2+K 3 3*ω3+K 3 3*ω4+K 3 4*ω5+K 3 5*ω6+b≥1

[0103] K 4 1*ω1+K 4 2*ω2+K 4 3*ω3+K 4 3*ω4+K 4 4*ω5+K 4 5*ω6+b≥1

[0104] -K 5 1*ω1-K 5 2*ω2-K 5 3*ω3-K 5 3*ω4-K5 4*ω5-K 5 5*ω6-b≥1

[0105] -K 6 1*ω1-K 6 2*ω2-K 6 3*ω3-K 6 3*ω4-K 6 4*ω5-K 6 5*ω6-b≥1

[0106] -K 7 1*ω1-K 7 2*ω2-K 7 3*ω3-K 7 3*ω4-K 7 4*ω5-K 7 5*ω6-b≥1

[0107] Solve to get ω = (ω1, ω2, ω3, ω4, ω5, ω6), b

[0108] Get the separating hyperplane: ω*k+b=0

[0109] Wherein, st represents the constraint condition. In the above classification hyperplane method, "ω.b st" represents the constraint conditions of the two parameters ω and b.

[0110] By solving the above variance group, we can get the classification decision model f(x)=sign(ω*k+b). The classification decision model can be used to determine the material type of the sample to be tested. That is, when ω*k+b>0, it is concentrate; when ω*k+b<0, it is tailings.

[0111] In the embodiments of the present disclosure, by using multiple X-ray sources and linear array detectors, combined with detection by high-energy detection modules and low-energy detection modules in the linear array detectors, classification parameters corresponding to multiple ray intensities can be obtained, and the material type to which the material belongs can be determined in combination with the multiple classification parameters. Compared with material detection through a single ray intensity, the material type determined by combining multiple classification parameters can reduce the error of material detection, thereby improving the detection accuracy of the material detection equipment.

[0112] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the application disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the claims.

[0113] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A material detection device, characterized in that: include: Feeding device, material detection channel, material detection device and processor; The feeding device is used to convey the material to be detected to the entrance of the material detection channel; the material detection channel is used to transport the material; The material detection device comprises at least two X-ray sources and linear array detectors corresponding to the X-ray sources one by one; the X-ray sources and the corresponding linear array detectors are arranged on both sides of the material detection channel relatively, wherein the X-rays emitted by any two X-ray sources have different intensities, and the linear array detectors comprise a low-energy detection module provided with a filter and a high-energy detection module not provided with a filter; The processor is connected to each linear array detector respectively, and is used to obtain the ray intensity detected by the high-energy detection module and the ray intensity detected by the low-energy detection module of each linear array detector during the process of transmitting the material in the material detection channel, wherein the ray intensity detected by the high-energy detection module includes: the ray intensity of the X-ray detected before the material reaches the high-energy detection module, and the ray intensity of the X-ray detected after the material passes through the high-energy detection module; the ray intensity detected by the low-energy detection module includes: the ray intensity of the X-ray detected before the material reaches the low-energy detection module, and the ray intensity of the X-ray detected after the material passes through the low-energy detection module; according to the ray intensity detected by the high-energy detection module of the linear array detector corresponding to each X-ray source, the ray intensity detected by the low-energy detection module of the linear array detector corresponding to each X-ray source and the preset classification model, multiple classification parameters are determined, and the material type to which the material belongs is determined according to the multiple classification parameters; wherein any two X-ray sources emit The X-ray intensity is different; wherein the material detection device includes a first X-ray source, a second X-ray source, a first linear array detector, and a second linear array detector; wherein the first linear array detector includes a first high-energy detection module and a first low-energy detection module, and the second linear array detector includes a second high-energy detection module and a second low-energy detection module. Accordingly, according to the ray intensity detected by the high-energy detection module of the linear array detector corresponding to each X-ray source, the ray intensity detected by the low-energy detection module of the linear array detector corresponding to each X-ray source and a preset classification model, a plurality of classification parameters are determined, and according to the plurality of classification parameters, the material type to which the material belongs is determined, including: combining the first ray intensity detected by the first high-energy detection module, the second ray intensity detected by the first low-energy detection module, the third ray intensity detected by the second high-energy detection module, and the fourth ray intensity detected by the second low-energy detection module in pairs to determine 6 ray intensity combinations; according to the 6 ray intensity combinations and the preset classification model, 6 classification parameters are obtained; according to the 6 classification parameters, the material type to which the material belongs is determined.

2. The material detection device according to claim 1, characterized in that: The material detection device comprises a first X-ray source, a second X-ray source, a first linear array detector corresponding to the first X-ray source, and a second linear array detector corresponding to the first X-ray source; The first X-ray source and the first linear array detector are arranged on both sides of the material detection channel, and the second X-ray source and the second linear array detector are arranged on both sides of the material detection channel; The processor is connected to the first linear array detector and the second linear array detector respectively; The intensity of the X-rays emitted by the first X-ray source is greater than the intensity of the X-rays emitted by the second X-ray source.

3. The material detection device according to claim 2, characterized in that: The first linear array detector includes a first high-energy detection module and a first low-energy detection module, and the first low-energy detection module is provided with a first filter; the second linear array detector includes a second high-energy detection module and a second low-energy detection module, and the second low-energy detection module is provided with a second filter.

4. The material detection device according to any one of claims 1 to 3, characterized in that: The material detection equipment further comprises: a separation device; The processor is connected to the separation device and is used to control the separation device to separate the material according to the material type to which the material belongs.

5. A material detection method, characterized in that: Applied to the material detection device according to any one of claims 1 to 4, the method comprises: For each linear array detector corresponding to an X-ray source in the material detection device, the ray intensity detected by the high-energy detection module and the ray intensity detected by the low-energy detection module of the linear array detector are obtained, wherein the ray intensity detected by the high-energy detection module includes: the ray intensity of the X-ray detected before the material reaches the high-energy detection module, and the ray intensity of the X-ray detected after the material passes through the high-energy detection module; the ray intensity detected by the low-energy detection module includes: the ray intensity of the X-ray detected before the material reaches the low-energy detection module, and the ray intensity of the X-ray detected after the material passes through the low-energy detection module; Determine multiple classification parameters based on the ray intensity detected by the high-energy detection module of the linear array detector corresponding to each X-ray source, the ray intensity detected by the low-energy detection module of the linear array detector corresponding to each X-ray source, and a preset classification model, and determine the material type to which the material belongs based on the multiple classification parameters; wherein the ray intensity of the X-rays emitted by any two X-ray sources is different; Wherein, the material detection device includes a first X-ray source, a second X-ray source, a first linear array detector, and a second linear array detector; wherein the first linear array detector includes a first high-energy detection module and a first low-energy detection module, and the second linear array detector includes a second high-energy detection module and a second low-energy detection module. Accordingly, according to the ray intensity detected by the high-energy detection module of the linear array detector corresponding to each X-ray source, the ray intensity detected by the low-energy detection module of the linear array detector corresponding to each X-ray source, and a preset classification model, a plurality of classification parameters are determined, and according to the plurality of classification parameters, the material type to which the material belongs is determined, including: combining the first ray intensity detected by the first high-energy detection module, the second ray intensity detected by the first low-energy detection module, the third ray intensity detected by the second high-energy detection module, and the fourth ray intensity detected by the second low-energy detection module in pairs to determine 6 ray intensity combinations; according to the 6 ray intensity combinations and the preset classification model, 6 classification parameters are obtained; according to the 6 classification parameters, the material type to which the material belongs is determined.

6. The material detection method according to claim 5, characterized in that: Determining the material type to which the material belongs according to the six classification parameters includes: Determine the average of the six classification parameters, if the average is greater than or equal to a preset value, determine that the material type to which the material belongs is a target mineral, if the average is less than the preset value, determine that the material type to which the material belongs is a non-target mineral; alternatively, determine the median of the six classification parameters, if the median is greater than or equal to the preset value, determine that the material type to which the material belongs is a target mineral, if the median is less than the preset value, determine that the material type to which the material belongs is a non-target mineral; alternatively, input the six classification parameters into a preset support vector machine model, if the output result is greater than 0, determine that the material type to which the material belongs is a target mineral, if the output result is less than 0, determine that the material type to which the material belongs is a non-target mineral.

7. The material detection method according to claim 5, characterized in that: The first ray intensity detected by the first high-energy detection module, the second ray intensity detected by the first low-energy detection module, the third ray intensity detected by the second high-energy detection module, and the fourth ray intensity detected by the second low-energy detection module are combined in pairs to determine six ray intensity combinations, including: The first ray intensity and the second ray intensity are combined to obtain a first ray intensity combination; the first ray intensity and the third ray intensity are combined to obtain a second ray intensity combination; the first ray intensity and the fourth ray intensity are combined to obtain a third ray intensity combination; the second ray intensity and the third ray intensity are combined to obtain a fourth ray intensity combination; the second ray intensity and the fourth ray intensity are combined to obtain a fifth ray intensity combination; the third ray intensity and the fourth ray intensity are combined to obtain a sixth ray intensity combination.

8. The material detection method according to claim 7, characterized in that: The first ray intensity detected by the first high-energy detection module includes: the ray intensity of the first X-ray detected before the material reaches the first high-energy detection module, and the ray intensity of the first X-ray detected after the material passes through the first high-energy detection module; The second ray intensity detected by the first low-energy detection module includes: the ray intensity of the first X-ray detected before the material reaches the first low-energy detection module, and the ray intensity of the first X-ray detected after the material passes through the first low-energy detection module; The third ray intensity detected by the second high-energy detection module includes: the ray intensity of the second X-ray detected before the material reaches the second high-energy detection module, and the ray intensity of the second X-ray detected after the material passes through the material when the material passes through the second high-energy detection module; The fourth ray intensity detected by the second low-energy detection module includes: the ray intensity of the second X-ray detected before the material reaches the second low-energy detection module, and the ray intensity of the second X-ray detected after the material passes through the second low-energy detection module; The first X-ray is an X-ray emitted by a first X-ray source, and the second X-ray is an X-ray emitted by a second X-ray source.

9. The detection method according to claim 8, characterized in that: According to the six ray intensity combinations and the preset classification model, six classification parameters are obtained, including: For the first ray intensity combination, determine a first ratio between the ray intensity of the first X-ray detected before the material reaches the first high-energy detection module in the first ray intensity and the ray intensity of the first X-ray detected after the material passes through the first high-energy detection module, and determine a second ratio between the ray intensity of the first X-ray detected before the material reaches the first low-energy detection module in the second ray intensity and the ray intensity of the first X-ray detected after the material passes through the first low-energy detection module; input the first ratio and the second ratio into a preset classification model to obtain 1 classification parameter; For the second ray intensity combination, the first ratio is determined, and a third ratio between the ray intensity of the second X-ray detected before the material reaches the second high-energy detection module and the ray intensity of the second X-ray detected after passing through the material when the material passes through the second high-energy detection module is determined; the first ratio and the third ratio are input into the preset classification model to obtain 1 classification parameter; For the third ray intensity combination, determining the first ratio, and determining a fourth ratio between the ray intensity of the second X-ray detected before the material reaches the second low-energy detection module and the ray intensity of the second X-ray detected after the material passes through the second low-energy detection module; inputting the first ratio and the fourth ratio into the preset classification model to obtain 1 classification parameter; For a fourth ray intensity combination, determining the second ratio and determining the third ratio; inputting the second ratio and the third ratio into the preset classification model to obtain one classification parameter; For the fifth ray intensity combination, determining the second ratio and determining the fourth ratio; inputting the first ratio and the fourth ratio into the preset classification model to obtain one classification parameter; For the sixth ray intensity combination, the third ratio is determined, and the fourth ratio is determined; the third ratio and the fourth ratio are input into the preset classification model to obtain 1 classification parameter.

Images