Material sorting method and material sorting device

Abstract

The invention provides a material sorting method, and relates to the field of material sorting, the field of radiation inspection or other fields. The method comprises the following steps: controlling at least one of a radiation source and a detector to move in response to the condition that particle size information of a to-be-sorted material meets a preset condition, so as to obtain a radiation distance and a detection distance matched with the particle size information; the radiation source is controlled to send radiation rays to the to-be-sorted materials based on the radiation distance, the detector is controlled to receive a ray signal of the radiation rays based on the detection distance, and a radiation image is obtained; and sorting the to-be-sorted materials according to the radiation image. The invention further provides a material sorting device.

Description

Technical Field

[0001] The present disclosure relates to the field of material sorting, radiation inspection or other fields, and more specifically, to a material sorting method and a material sorting device. Background Art

[0002] Material sorting refers to the process of classifying and selecting materials according to their specific properties or standards during production, logistics, warehousing, etc. For example, the materials to be sorted are evenly sent to the sorting area through a conveyor belt; then the materials to be sorted are scanned using radiographic imaging technology and the radiographic images are identified; the computer analyzes these data, determines the injection strategy, and passes the instructions to the injection execution system; finally, the injection execution system controls the opening and closing of the jet valve and the injection time according to the instructions to spray the materials to the target sorting position.

[0003] Therefore, in the material sorting process, the image quality of the material to be sorted is related to the accuracy of subsequent analysis and identification, determination of the blowing strategy, and execution of the blowing. How to improve the image quality of the imaging and the accuracy of the subsequent analysis and identification steps is an urgent problem to be solved. Summary of the invention

[0004] In view of the above problems, the present disclosure provides a material sorting method and a material sorting device.

[0005] According to a first aspect of the present disclosure, a material sorting method is provided, comprising: in response to particle size information of a material to be sorted meeting a preset condition, controlling at least one of a radiation source and a detector to move to obtain a radiation distance and a detection distance that match the particle size information; controlling the radiation source to send radiation rays to the material to be sorted based on the radiation distance, and controlling the detector to receive radiation signals of the radiation rays based on the detection distance to obtain a radiation image; and sorting the material to be sorted according to the radiation image.

[0006] In some embodiments, based on the particle size information of the material to be sorted, controlling the movement of at least one of the radiation source and the detector includes at least one of the following: controlling the radiation source to approach or move away from the bottom of the material to be sorted along the transmission path of the radiation ray, wherein the radiation source is located below the material to be sorted; controlling the detector to approach or move away from the top of the material to be sorted along the transmission path of the radiation signal, wherein the detector is located above the material to be sorted.

[0007] In some embodiments, controlling the movement of at least one of the radiation source and the detector based on the particle size information of the material to be sorted also includes: in the process of transporting the material to be sorted, in response to the change of the particle size information of the material to be sorted entering the radiation area of ​​the radiation source, dynamically adjusting the position of at least one of the radiation source and the detector.

[0008] In some embodiments, a conveyor belt is configured to transport the materials to be sorted, wherein the radiation source is located below the area of ​​the conveyor belt carrying the materials to be sorted, and the detector is located above the area of ​​the conveyor belt carrying the materials to be sorted.

[0009] In some embodiments, controlling the movement of at least one of the radiation source and the detector according to the particle size information of the material to be sorted also includes: controlling the movement of the radiation source according to the particle size information of the material to be sorted to obtain a radiation distance matching the particle size information; and controlling the movement of the detector according to the position of the radiation source to obtain a detection distance matching the particle size information.

[0010] In some embodiments, the detector includes multiple sub-detectors, and controlling the movement of the detector according to the position of the radiation source includes: controlling the movement of at least one of the multiple sub-detectors according to the position of the radiation source to obtain a detection distance for each sub-detector that matches the particle size information; wherein each sub-detector and any other sub-detector are adapted to the same particle size information and have the same or different detection distance.

[0011] In some embodiments, multiple sub-detectors are arranged in an arc shape, and after the detectors are controlled to move according to the position of the radiation source, at least one of the following items is further included: the distances between the multiple sub-detectors arranged in an arc shape and the radiation source are basically equal; the distances between any two of the multiple sub-detectors arranged in an arc shape are basically equal; the detection angles of each sub-detector before and after the movement are basically the same, wherein the detection angle of each sub-detector is adjustable.

[0012] In some embodiments, before controlling at least one of the radiation source and the detector to move, the materials to be sorted are arranged in batches, wherein the preset conditions include at least one of the following: when the particle sizes of materials in the same batch are different, the difference between the particle size of the material to be sorted radiated at a first moment in the future and the particle size of the material to be sorted radiated at a second moment in the past is greater than a specific threshold, wherein the first moment is adjacent to the second moment; when the particle sizes of materials in different batches are different and the particle sizes of materials in the same batch are the same, the difference in particle sizes of adjacent batches of materials to be sorted is greater than a specific threshold.

[0013] In some embodiments, sorting the material to be sorted according to the radiation image includes: obtaining at least one of a visible light image, a near-infrared image, and a hyperspectral image of the material to be sorted; and sorting the material to be sorted according to the image processing result of the radiation image and at least one of the visible light image, the near-infrared image, and the hyperspectral image of the material to be sorted.

[0014] In some embodiments, based on the image processing results of the radiation image and at least one of the visible light image, near-infrared image and hyperspectral image of the material to be sorted, sorting the material to be sorted includes: fusing the radiation image and at least one of the visible light image, near-infrared image and hyperspectral image of the material to be sorted to obtain a fused image; and sorting the material to be sorted based on the material identification result based on the fused image.

[0015] In some embodiments, based on the image processing results of the radiation image and at least one of the visible light image, near-infrared image and hyperspectral image of the material to be sorted, sorting the material to be sorted includes: respectively identifying the radiation image, the visible light image, the near-infrared image and the hyperspectral image; weightedly fusing the recognition results of the radiation image, the visible light image, the near-infrared image and the hyperspectral image to obtain a final recognition result; and sorting the material to be sorted according to the final recognition result.

[0016] In some embodiments, before weighted fusion of the recognition results of the radiation image, visible light image, near-infrared image and hyperspectral image, the method also includes: extracting radiation features, visible light features, near-infrared features and hyperspectral features from the radiation image, visible light image, near-infrared image and hyperspectral image, respectively; matching the radiation features, visible light features, near-infrared features and hyperspectral features with their respective preset feature conditions, respectively; and assigning corresponding weights according to the matching degree of the radiation features, visible light features, near-infrared features and hyperspectral features, wherein the matching degree is positively correlated with the weight.

[0017] Another aspect of the disclosed embodiment provides a material sorting device, comprising: a conveying module for conveying materials to be sorted; a radiation source installed on a first moving component and located below the bottom of an area of ​​the conveying module for carrying materials to be sorted; a detector installed on a second moving component and located above the top of the materials to be sorted; and a control module for controlling the first moving component to drive the radiation source to move, and controlling the second moving component to drive the detector to move, so as to execute any of the above material sorting methods.

[0018] In some embodiments, the first moving assembly includes: a first guide rail connected to the radiation source and used to drive the radiation source to move closer to or away from the bottom.

[0019] In some embodiments, the second moving assembly includes: a second guide rail connected to the detector and used to drive the detector to move closer to or away from the top.

[0020] In some embodiments, the detector includes a plurality of sub-detectors arranged in an arc shape, wherein the distance between each of the plurality of sub-detectors and the radiation source is substantially equal.

[0021] In some embodiments, the second moving assembly further includes: a plurality of third guide rails connected to the plurality of sub-detectors in a one-to-one correspondence; wherein each third guide rail is configured to drive the connected sub-detector to move.

[0022] In some embodiments, the second moving component also includes: a plurality of rotating components, which are installed one-to-one on the third guide rail and connected one-to-one with the plurality of sub-detectors; wherein each rotating component is used to drive the connected sub-detector to rotate to change the detection angle.

[0023] One or more of the above embodiments have the following beneficial effects: by adjusting the positions of the radiation source and the detector, they can be adapted to the particle size information of the material to be sorted, and the radiation source can be used to irradiate the material at a short distance, so that the energy loss of the radiation before entering the material is small, and it is easy to obtain a higher imaging quality. In addition, the detector can detect the radiation source or the material at a short distance, further improving the overall imaging quality and improving the material identification ability. In addition, through the matching radiation distance and detection distance, it can also play a role in adjusting the radiation field and the detection field, so that the number of materials presented in the radiation image is moderate, and each material is irradiated with sufficient intensity of radiation, which is conducive to obtaining richer information about each material in the subsequent image analysis stage. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0025] Figure 1 The structure diagram of the material sorting device according to the embodiment of the present application is schematically shown;

[0026] Figure 2 The position diagram of the ray source and the detector according to the embodiment of the present application is schematically shown;

[0027] Figure 3 A schematic diagram showing the positions of a ray source and a detector according to another embodiment of the present application;

[0028] Figure 4 The structure diagram of the detector according to the embodiment of the present application is schematically shown;

[0029] Figure 5 A flow chart of a material sorting method according to an embodiment of the present disclosure is schematically shown;

[0030] Figure 6 A flowchart schematically illustrates a method for controlling the movement of at least one of a ray source and a detector according to an embodiment of the present disclosure; and

[0031] Figure 7 The figure schematically shows a sorting flow chart according to an embodiment of the present disclosure.

[0032] The reference numerals related to the above drawings are as follows:

[0033] 100, conveying module; 210, integrated imaging camera; 220, radiation image acquisition module; 221, radiation source; 222, detector; 2221, sub-detector; 2222, third guide rail; 300, blowing module; 400, sorting bin; 500, control module; 600, feeder; 710, first moving assembly; 720, second moving assembly.

[0034] It should be noted that, for the sake of clarity, in the drawings used to describe the embodiments of the present disclosure, the sizes of the overall / local structures or the overall / local areas may be enlarged or reduced, that is, these drawings are not drawn according to the actual scale. DETAILED DESCRIPTION

[0035] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0036] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0037] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0038] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0039] Figure 1 The structural diagram of a material sorting device according to an embodiment of the present application is schematically shown.

[0040] like Figure 1 As shown, the material sorting device includes a conveying module 100, an integrated imaging camera 210, a radiographic image acquisition module 220, a blowing module 300, a sorting bin 400, a control module 500 and a feeder 600. The feeder 600 is used to arrange the material to be sorted to the conveying module 100, and the conveying module 100 is used to convey the material to be sorted; the radiographic image acquisition module 220 is used to capture the radiographic image of the material to be sorted; the integrated imaging camera 210 is used to capture one or more images of the material to be sorted; the control module 500 is used to obtain one or more images of the material to be sorted, and execute the material sorting method provided by any embodiment of the present disclosure to generate a sorting instruction; the blowing module 300 is used to respond to the sorting instruction of the control module 500 and blow the material leaving the conveying module 100.

[0041] Exemplarily, the conveying module 100 may be a horizontally arranged conveyor belt, an inclined conveyor belt, an angled inclined slide plate, or a combination of the above. In the following, unless otherwise specified, the conveying module 100 is a horizontally arranged conveyor belt. Materials of different types and sizes are distributed along the length direction (i.e., the conveying direction) and the width direction on the conveying module 100. Since the conveyor belt has a certain running speed, different materials are scattered on the conveyor belt, and when the conveyor belt is transported to the end position at the end, the materials are thrown out from the conveyor belt to perform horizontal throwing motion.

[0042] Exemplarily, the radiation image acquisition module 220 may include a radiation source 221 and a detector 222. For example, the radiation source 221 may be disposed above or below the material to be sorted, and the detector 222 is opposite to the radiation source 221 and may be disposed below or above the material to be sorted. The detector 222 receives the radiation signal after penetrating the material and converts it into a radiation image.

[0043] Exemplarily, the spray module 300 includes one or more nozzles, for example, a plurality of nozzles arranged in an array. The spray module 300 may also include a solenoid valve and a gas supply device, each nozzle may be connected to a solenoid valve, and the type of the solenoid valve may be a high-frequency solenoid valve. The solenoid valve is connected to a gas supply device (not shown). The gas supply device is equipped with compressed gas, which is used to provide a gas source for the nozzle to spray different types of materials.

[0044] The blowing module 300 in the embodiment of the present application is located at the lower side of the material movement trajectory. The material movement trajectory in the present application refers to the movement trajectory of the material after it leaves the end of the conveying module 100. In this embodiment, by setting the blowing module 300 at the lower side of the movement trajectory, a blowing force can be applied to the material, reducing energy consumption while improving the influence of different blowing positions on the sorting accuracy. For example, when the material reaches the blowing position, the blowing module 300 can instantly spray out a high-pressure airflow of a specific duration, and change the movement trajectory of the material through the airflow, so that the material falls into the corresponding sorting bin 400.

[0045] In some embodiments, the spraying pressure can also be controlled by adjusting the number of nozzles. For example, when the area of ​​the material is large, a larger number of nozzles can be used to spray the material surface, and when the area of ​​the material is small, a smaller number of nozzles can be used to spray the material surface, so that the spraying distance (horizontal movement distance) of materials of different volumes and weights is maintained within a certain range.

[0046] In some embodiments, during the sorting process, the control module 500 can adjust the blowing strategy in real time based on the recognition results of the radiation image and / or other categories of images, such as increasing or decreasing the nozzle pressure to change the intensity of the airflow, thereby affecting the flight distance and direction of the material; adjusting the nozzle spray angle so that the airflow direction is perpendicular to the tangent at a certain point on the flight trajectory of the material; adjusting the start and stop time of the blowing to match the speed and position of the material through the nozzle.

[0047] Figure 2 The diagram schematically shows the positions of the ray source 221 and the detector 222 according to an embodiment of the present application. Figure 3 The figure schematically shows the positions of a ray source 221 and a detector 222 according to another embodiment of the present application. Figure 4 The structure of the detector 222 according to the embodiment of the present application is schematically shown.

[0048] In some embodiments, the material sorting device further includes a first moving assembly 710 and a second moving assembly 720. The ray source 221 is installed on the first moving assembly 710 and is located below the bottom of the area of ​​the conveying module 100 for carrying the material to be sorted; the detector 222 is installed on the second moving assembly 720 and is located above the top of the material to be sorted. The control module 500 can control the first moving assembly 710 to drive the ray source 221 to move, and control the second moving assembly 720 to drive the detector 222 to move.

[0049] The X-rays are emitted from the bottom to the top at a wide angle, penetrate the conveyor belt and enter the material. By adjusting the radiation distance, the X-ray energy loss is reduced, and it is easy to obtain high imaging quality. It can flexibly realize the detection and identification of materials with a particle size of 5mm-300mm (only as an example). The X-ray imaging algorithm can include processes such as air correction, geometric correction, contour segmentation and identification classification.

[0050] For example, the first moving assembly 710 includes a first guide rail, which is connected to the ray source 221 and is used to drive the ray source 221 to move closer to or away from the bottom. The first guide rail includes a track and a driving device, and the driving device drives the ray source 221 to move up and down along the track through a transmission mechanism (such as a lead screw, a belt, etc.).

[0051] For example, the second moving assembly 720 includes a second guide rail, which is connected to the detector 222 and is used to drive the detector 222 to move closer to or away from the bottom. The second guide rail may also include a track and a driving device, and the driving device drives the detector 222 to move up and down along the track through a transmission mechanism (such as a lead screw, a belt, etc.). The first guide rail and the second guide rail may be tracks that are separated or connected to each other.

[0052] like Figure 3 As shown, the detector 222 includes a plurality of sub-detectors 2221 arranged in an arc shape (eg, arranged centripetally in an arc shape), wherein the distance between each of the plurality of sub-detectors 2221 and the ray source 221 is substantially equal.

[0053] In some embodiments, the second moving assembly 720 further includes a plurality of third guide rails 2222 connected to the plurality of sub-detectors 2221 in a one-to-one correspondence; wherein each third guide rail 2222 is configured to drive the connected sub-detector 2221 to move.

[0054] For example, the detector 222 is connected to the second guide rail via a bracket (not shown in the figure). Figure 4 The third guide rails 2222 may also include a track and a driving device, and the driving device drives the sub-detector 2221 to move along the track through a transmission mechanism (such as a lead screw, a belt, etc.).

[0055] In some embodiments, the second moving assembly 720 further includes a plurality of rotating assemblies which are mounted one by one on the third guide rail 2222 and connected to the plurality of sub-detectors 2221 one by one; wherein each rotating assembly is used to drive the connected sub-detector 2221 to rotate to change the detection angle.

[0056] Reference Figure 4Each sub-detector 2221 is connected to the third guide rail 2222 via a rotating assembly (not shown in the figure). The driving device of the third guide rail 2222 can drive the rotating assembly to move along the track and can drive the sub-detector 2221 to rotate. For example, the rotating assembly can include an inner gear and an outer gear, wherein the gear teeth of the outer gear mesh with the gear teeth on the inner wall of the inner gear. The rotation of the outer gear can drive the sub-detector 2221 to rotate.

[0057] The following will be based on Figures 1 to 4 The material sorting device described is used to describe the material sorting method of the embodiment of the present disclosure in detail.

[0058] Figure 5 The flowchart of the material sorting method according to the embodiment of the present disclosure is schematically shown.

[0059] like Figure 5 As shown, the material sorting method of this embodiment includes:

[0060] In operation S510, in response to the particle size information of the material to be sorted meeting a preset condition, at least one of the radiation source 221 and the detector 222 is controlled to move to obtain a radiation distance and a detection distance that match the particle size information.

[0061] The materials to be sorted may include ores, foods, beverages or other objects to be sorted on the assembly line. By identifying the material information of the materials to be sorted, the materials are divided into multiple types based on the material information, and the different types of materials are sorted. In the specific classification, there may be different types of division methods according to different sorting requirements. The material types can be classified according to shape and size, density, material content, etc., and this application does not limit this. The target material can be determined by the control module 500 based on one or more parameters such as the identified material particle size and material type.

[0062] For example, taking ore sorting as an example, ores can be divided into metal ores and non-metallic ores. Metallic ores include ferrous metals and non-ferrous metals; such as iron, manganese, chromium, etc.; non-ferrous metal ores, such as copper, lead, zinc, aluminum, tin, molybdenum, nickel, antimony, tungsten, etc. Non-metallic ores include most oxygen-containing salt ores and some oxide and halide ores, such as diamond, crystal, Iceland spar, boron, tourmaline, mica, topaz, corundum, graphite, gypsum, asbestos, and fuel ores. When classifying ores, the material type includes the type of metal contained, the grade, and the chemical composition. Take ore sorting as an example. Ore types can be divided into three types according to the content of specific metals, including high-quality ores (highest content of specific metals), medium-quality ores (middle content of specific metals), and low-quality ores (lowest content of specific metals).

[0063] In operation S520, the radiation source 221 is controlled to send radiation rays to the material to be sorted based on the radiation distance, and the detector 222 is controlled to receive radiation signals of the radiation rays based on the detection distance to obtain a radiation image;

[0064] In operation S530, the materials to be sorted are sorted according to the radiation image.

[0065] The particle size information includes metric information describing the particle size of the material. For example, the particle size of the iron ore to be sorted may be between 5 mm and 10 mm. The preset condition includes presetting a particle size determination value during the sorting process to trigger the movement process of the ray source 221 and the detector 222. For example, when the ore particle size is less than 5 mm, at least one of the ray source 221 and the detector 222 works at the first position. When the ore particle size is greater than 5 mm, at least one of the ray source 221 and the detector 222 works at the second position. The first position is different from the second position. The radiation ray may include X-rays. The radiation distance refers to the distance from the target point of the ray source 221 to the material to be sorted. The detection distance refers to the distance from the detector 222 to the material to be sorted. The radiation image may include an X-ray image converted from the radiation signal received by the detector 222.

[0066] For example, the particle size, the amount of material in the radiation image, the radiation distance, and the detection distance can also be comprehensively considered. When the particle sizes of the multiple materials to be sorted entering the radiation area of ​​the radiation source 221 are large, the amount of material that can be accommodated in the current radiation area can be considered. If there is a need to increase or decrease the amount of material, the radiation distance can be increased or decreased accordingly. In addition, the detector 222 can be moved according to the particle size of the material and the radiation distance to have an adaptive detection distance.

[0067] For example, the shape of the material may also be considered, and the length of the material at different incident angles (i.e., the radiation penetration distance) may be obtained in combination with the shape. According to the incident angle of the radiation source 221 or the detection angle of the detector 222 receiving the radiation signal, the movement of at least one of the two may be controlled.

[0068] For example, the ray source 221 and the detector 222 can move up and down, left and right, or in any direction. Taking the detector 222 as an example, the detection distance with the adapted particle size can achieve consistent ray attenuation at the imaging distance, so that the imaging consistency is better, thereby improving the overall imaging quality, and achieving that the ray attenuation difference received by the detection module represents the material difference as much as possible, thereby improving the material identification ability.

[0069] According to the embodiments of the present disclosure, by adjusting the positions of the ray source 221 and the detector 222, it is possible to adapt to the particle size information of the material to be sorted, and the ray source 221 can be used to radiate the material at a short distance, so that the energy loss of the radiated rays before entering the material is small, and it is easy to obtain a higher imaging quality. In addition, the detector 222 can detect the ray source 221 or the material at a short distance, further improving the overall imaging quality and improving the material identification ability. In addition, through the matching radiation distance and detection distance, it can also play a role in adjusting the radiation field and the detection field, so that the number of materials presented in the radiation image is moderate, and each material is irradiated with sufficient intensity of rays, which is conducive to obtaining richer information about each material in the subsequent image analysis stage.

[0070] In some embodiments, according to the particle size information of the material to be sorted, controlling the movement of at least one of the radiation source 221 and the detector 222 further includes:

[0071] During the process of transporting the materials to be sorted, in response to the change in particle size information of the materials to be sorted entering the radiation area of ​​the radiation source 221, the position of at least one of the radiation source 221 and the detector 222 is dynamically adjusted to obtain the radiation distance and detection distance that are compatible with the particle size information.

[0072] For example, the particle size information of the material to be sorted can be manually input or acquired through real-time detection by a sensor. During the sorting process, if the particle size of the material continuously flowing through the radiation area suddenly increases, the position of the ray source 221 and the detector 222 will be dynamically adjusted according to this change. For example, when it is detected that the particle size of the material increases, the distance between the ray source 221 and the material is automatically reduced so that the ray can penetrate the material and be effectively detected. For example, it is also possible to send rays to a certain target material when it reaches above the ray source 221, or control the ray source 221 to move to the bottom of the target material.

[0073] In some embodiments, before controlling at least one of the radiation source 221 and the detector 222 to move, the materials to be sorted are arranged in batches. Figure 1 , using the feeder 600 to place the materials to be sorted on the conveyor belt in batches.

[0074] The preset condition is used to determine whether the positions of the radiation source 221 and the detector 222 need to be adjusted according to the change in the particle size of the material, and includes at least one of the following:

[0075] In the case of different particle sizes of materials in the same batch, the difference between the particle size of the material to be sorted radiated at a first moment in the future and the particle size of the material to be sorted radiated at a second moment in the past is greater than a specific threshold, wherein the first moment is adjacent to the second moment;

[0076] Assume that at the first moment (the tth second), the particle size of the material to be irradiated is detected to be 12 mm, while the particle size of the material that has received radiation at the immediately previous moment (the second moment, the t-1th second) is 9 mm. The difference in the particle size of the material at these two adjacent moments is 3 mm. If the preset specific threshold is 1 mm, the positions of the ray source 221 and the detector 222 are automatically adjusted to adapt to the change in particle size. For example, the ray source 221 may be moved closer to the material to penetrate larger particles, and the detector 222 may also be moved closer to the material to better capture the reflected ray signal.

[0077] When the particle sizes of materials in different batches are different and the particle sizes of materials in the same batch are the same, the difference in particle sizes of adjacent batches of materials to be sorted is greater than a specific threshold.

[0078] For example, in the current batch (batch A), the average particle size of the material is detected to be 30 mm, while in the previous batch (batch B), the average particle size of the material is 20 mm. The difference in particle size between the two adjacent batches is 10 mm, and the specific threshold is 5 mm, so the positions of the radiation source 221 and the detector 222 are automatically adjusted.

[0079] According to the embodiments of the present disclosure, even when the particle size of the material changes, efficient and accurate sorting can be achieved. In addition, sorting errors caused by particle size changes can be reduced, and the stability and reliability of the entire sorting process can be improved.

[0080] In some embodiments, in operation S510, controlling at least one of the radiation source 221 and the detector 222 to move according to the particle size information of the material to be sorted includes at least one of the following:

[0081] Along the transmission path of the radiation rays, the radiation source 221 is controlled to be close to or away from the bottom of the material to be sorted, wherein the radiation source 221 is located below the material to be sorted;

[0082] Along the transmission path of the ray signal, the detector 222 is controlled to be close to or away from the top of the material to be sorted, wherein the detector 222 is located above the material to be sorted.

[0083] It is understood that the transmission path of the radiation ray and the transmission path of the radiation signal may be the same or different. The radiation signal may be a signal that is emitted into the detector 222 after the radiation ray penetrates the material and is absorbed and attenuated by the material.

[0084] The ray source 221 is installed at the bottom of the material with the beam emitting direction facing upward. At the same time, the detector 222 is installed above the material to receive the X-ray information that is attenuated after penetrating the conveyor belt and the material, so that the distance between the ray source 221 and the material can be shorter, providing the detector 222 with a larger space for arrangement and movement, which is beneficial to providing imaging quality.

[0085] Figure 6 The flowchart for controlling the movement of at least one of the ray source 221 and the detector 222 according to an embodiment of the present disclosure is schematically shown.

[0086] like Figure 6 As shown, this embodiment is one of the embodiments of operation S510, including:

[0087] In operation S610, according to the particle size information of the material to be sorted, the ray source 221 is controlled to move to obtain a radiation distance that matches the particle size information;

[0088] In operation S620 , the detector 222 is controlled to move according to the position of the ray source 221 to obtain a detection distance that matches the particle size information.

[0089] For example, on the sorting line, iron ore is transported to a radiation area equipped with an X-ray source 221 and a detector 222. Before the iron ore enters the radiation area, a high-precision laser particle size analyzer measures the particle size of each iron ore and sends the data to the control module 500 in real time. The control module 500 dynamically adjusts the position of the X-ray source 221 (operation S610) based on the received particle size information to ensure that the radiation distance is suitable for the particle size of the material. Subsequently, the position of the detector 222 is adjusted again (operation S620) based on the new position of the ray source 221 to ensure that the detection distance is suitable for the position of the ray source 221. In this way, the positions of the ray source 221 and the detector 222 can be dynamically adjusted according to materials of different particle sizes to improve the sorting accuracy and efficiency.

[0090] Dynamically adjusting the positions of the radiation source 221 and the detector 222 includes adaptively matching and adjusting three distances according to the known material size: the X-ray source target-material distance, the X-ray source target-detector distance, and the detector-material distance.

[0091] Assuming that the top of the first guide rail is the zero point of the ray source 221, the position of the ray source 221 can be determined by the moving stroke of the ray source 221, and the X-ray source target-detector distance can be quickly determined, which is conducive to improving the automatic adjustment speed.

[0092] In some embodiments, the detector 222 includes multiple sub-detectors 2221, and controlling the movement of the detector 222 according to the position of the ray source 221 includes: controlling the movement of at least one of the multiple sub-detectors 2221 according to the position of the ray source 221 to obtain a detection distance for each sub-detector 2221 that is adapted to the particle size information; wherein each sub-detector 2221 and any other sub-detector 2221 are adapted to the same particle size information with the same or different detection distance.

[0093] Exemplarily, multiple sub-detectors 2221 are located at different positions. The ray signals at different positions may come from different materials to be sorted. Due to the differences in material particle size, shape, ray incident direction, and sub-detector position, different sub-detectors 2221 may have different detection distances adapted for materials of the same particle size. Therefore, with each sub-detector 2221 as the granularity, its position can be adjusted separately to obtain an adapted detection distance, so that the overall imaging quality of the detector 222 can be improved by adapting each sub-detector 222.

[0094] In some embodiments, the plurality of sub-detectors 2221 are arranged in an arc shape, and after the detector 222 is controlled to move according to the position of the ray source 221, at least one of the following items is further included:

[0095] The distances between the arc-shaped multiple sub-detectors 2221 and the radiation source 221 are substantially equal; it can be understood that different distances from the radiation source 221 result in different times for the radiation signals to reach the sub-detectors 2221, so the imaging times are inconsistent, which will reduce the sorting accuracy and affect the sorting effect. Figure 3 As shown, placing the ray detector 222 above the conveyor belt can provide a larger space for arrangement, and can meet different requirements for detector structure, parameters, type, etc. When the distance between each sub-detector 2221 and the ray source 221 is roughly the same, the consistency of imaging time can be improved, and a high sorting accuracy can be maintained.

[0096] The distances between any two of the multiple arc-shaped sub-detectors 2221 are substantially equal; the incident position of the ray can be determined more accurately, thereby improving the spatial resolution of the imaging, and also helping each sub-detector 2221 to receive roughly the same X-ray intensity, thereby improving detection efficiency and imaging uniformity.

[0097] The detection angle of each sub-detector 2221 before and after the movement is substantially the same, wherein the detection angle of each sub-detector 2221 is adjustable. The consistency of the detection angle helps to maintain the stability and repeatability of the detection results under the same detection parameters, and helps to improve the imaging quality.

[0098] Taking X-ray transmission of ore as an example, when X-rays penetrate the ore and irradiate on the sensitive medium of the sub-detector 2221, an angle will be formed between the normal line of the receiving surface formed by the sensitive medium, and the angle will affect the formation of the ore image. In some embodiments, multiple sub-detectors 2221 are arranged in an arc to form an arc receiving surface. When the ray signal reaches the arc receiving surface, it can be perpendicular to the tangent of each sub-detector 2221 receiving surface at the receiving point, which is conducive to making the ray signal as perpendicular as possible to the ray receiving surface of the sub-detector 2221, thereby avoiding affecting the formation of the ore image and ensuring the ore image effect and ore sorting effect.

[0099] The following further describes the process of combining radiation imaging with other imaging techniques for material sorting.

[0100] Figure 7 The figure schematically shows a sorting flow chart according to an embodiment of the present disclosure.

[0101] like Figure 7 As shown, this embodiment is one of the embodiments of operation S530, including:

[0102] In operation S710, at least one of a visible light image, a near infrared image, and a hyperspectral image of the material to be sorted is obtained;

[0103] In operation S720, the material to be sorted is sorted according to an image processing result of the radiation image and at least one of the visible light image, the near infrared image, and the hyperspectral image of the material to be sorted.

[0104] like Figure 1 The comprehensive imaging camera 210 shown can realize visible light imaging, near infrared imaging and hyperspectral imaging, so the comprehensive imaging camera 210 can be used to scan and obtain corresponding images by running one or more of the imaging technologies. The comprehensive use of the imaging camera combined with the radiographic image acquisition module 220 can collect more abundant image information and improve the quality of material identification by taking advantage of the respective advantages of multiple imaging technologies.

[0105] The image processing result can be obtained by at least one of the following:

[0106] (1) Materials have differences in X-ray absorption. For example, for materials with high atomic numbers (such as lead, zinc, tungsten, antimony, gold, silver, etc.), dual-energy X-ray imaging technology is used for matching. There is obvious ore feature information in the X-ray image, and the dual-energy X-ray curve algorithm is used to identify the material. For the atomic number features, a deep learning algorithm is used for identification;

[0107] (2) Materials have characteristics such as color, gloss, texture, surface roughness, and flatness. Visible light imaging technology is used to match them. For example, for kaolin, phosphate rock, fluorite, quartz, calcite, feldspar, wollastonite, etc., COMS sensors are used for data imaging and acquisition, and deep learning algorithms are applied for material identification.

[0108] (3) The material has a reflection or absorption characteristic response to the near-infrared spectrum in the wavelength range of 780 to 3000 nm, including the use of near-infrared imaging technology and CMOS sensing materials to obtain the corresponding spectral characteristic wavelength and intensity to characterize the type and content of elements contained in the material;

[0109] (4) Materials with reflection or absorption spectral characteristics in the wavelength range of 400-1000, 900-1700, and 2700-5300 nm, such as pyrite, pyroxene, kaolinite, dolomite, etc., can be matched with hyperspectral imaging technology and CMOS, InGaAs, and InSb sensing materials to characterize the type and content of elements contained in the material.

[0110] In some embodiments, based on the image processing results of the radiation image and at least one of the visible light image, the near infrared image and the hyperspectral image of the material to be sorted, sorting the material to be sorted includes:

[0111] The radiation image is fused with at least one of the visible light image, near infrared image and hyperspectral image of the material to be sorted to obtain a fused image; the fusion can be performed in the feature dimension to obtain a fused image containing multi-dimensional feature information.

[0112] The materials to be sorted are sorted according to the material recognition results based on the fused image.

[0113] For example, a fixed physical distance is set between the X-ray imaging area and the integrated light imaging area, and the sampling frequencies of the two are set to have a certain proportional relationship. The corresponding images or energy spectrum data are obtained respectively, and the X-ray recognition algorithm is used to segment the material detection contour. According to the corresponding relationship between the time and position of the X-ray image and the integrated light imaging, the position of the same ore in the integrated light imaging is mapped, and the X-ray image and the integrated light image are registered, so that the material identification is performed independently or in combination, and the decision-making generates the injection instruction to guide the subsequent separation action.

[0114] Wherein, if it is the same material, the control unit combines the image features based on the ray and the image features based on at least one of the visible light image, the near infrared image and the hyperspectral image to obtain a fused image, and uses a deep learning algorithm to intelligently identify the image feature combination to determine the category of the identified object. For example, a deep learning algorithm can be used to construct an encoder and train it. The training samples include samples of at least one of the visible light image, the near infrared image and the hyperspectral image, radiation image samples and corresponding fused image samples. The back propagation algorithm is used to update the parameters of the encoder by comparing the difference between the predicted fused image output by the encoder and the fused image sample. Wherein, the encoder can be constructed using a neural network algorithm.

[0115] According to the embodiments of the present disclosure, the fused image is obtained by extracting image feature values ​​using two or more imaging technologies, which can reflect richer information and improve the accuracy of the recognition result.

[0116] In some embodiments, based on the image processing results of the radiation image and at least one of the visible light image, the near infrared image and the hyperspectral image of the material to be sorted, sorting the material to be sorted includes:

[0117] Recognize radiation images, visible light images, near-infrared images and hyperspectral images respectively;

[0118] For example, a radiation image recognition model, a visible light image recognition model, a near infrared image recognition model, and a hyperspectral image recognition model are constructed using a deep learning algorithm, and samples of the image types for each model are used for training. Alternatively, a comprehensive recognition model is constructed using a deep learning algorithm, and radiation image samples, visible light image samples, near infrared image samples, and hyperspectral image samples are used for comprehensive training to achieve the effect of recognizing multiple types of images.

[0119] The recognition results of the radiation image, visible light image, near infrared image and hyperspectral image are weighted and fused to obtain the final recognition result;

[0120] The recognition result of each type of image may include multiple predicted probability values ​​of multiple material categories. The predicted probability values ​​of the same material category may be multiplied by the weight coefficient, and the final probability value may be summed up. The material category with the largest final probability value may be taken as the final recognition result.

[0121] The materials to be sorted are sorted according to the final recognition results. The spraying strategy can be executed according to the final recognized category, material centroid and other information.

[0122] According to the embodiments of the present disclosure, by identifying multiple types of images one by one and comprehensively considering each recognition result in a weighted manner, it is helpful to improve the accuracy of the final recognition result.

[0123] In some embodiments, before weighted fusion of the recognition results of the radiation image, the visible light image, the near infrared image, and the hyperspectral image, the method further includes:

[0124] Extract radiation features, visible light features, near infrared features and hyperspectral features from radiation images, visible light images, near infrared images and hyperspectral images respectively;

[0125] Match the radiation characteristics, visible light characteristics, near infrared characteristics and hyperspectral characteristics with their respective preset characteristic conditions;

[0126] Corresponding weights are assigned according to the matching degree of radiation features, visible light features, near infrared features and hyperspectral features, where the matching degree is positively correlated with the weight.

[0127] For example, radiation features include atomic number features, visible light features include color, gloss, texture, surface roughness, flatness and other features, near-infrared features include near-infrared spectrum features, and hyperspectral features also include spectrum features of different bands. As mentioned above, different imaging technologies have a more suitable effect on different types of materials, and the recognition accuracy will be better accordingly. Therefore, each preset feature condition is used to screen which imaging technology is more compatible with the identified material, and a greater weight is assigned if the matching degree is higher.

[0128] For example, the preset characteristic conditions of the radiation characteristic may include a specific atomic number value, the radiation characteristic is greater than the atomic number value, and its own characteristic value is positively correlated with the matching degree. The preset characteristic conditions of the visible light characteristic can be determined for one or more of color, gloss, texture, surface roughness, flatness, etc. The preset characteristic conditions of the near-infrared characteristic can be determined based on the near-infrared spectrum, and the matching degree is high within the near-infrared spectrum range. The preset characteristic conditions of the hyperspectral characteristic can be determined based on the hyperspectral band range, and the matching degree is high within the hyperspectral band range.

[0129] According to the embodiments of the present disclosure, different current weights are assigned according to different feature matching degrees, and the most appropriate imaging technology can be selected to improve recognition efficiency and accuracy. In view of the material's radiation absorption characteristics, as well as the different spectral absorption or reflection strength optical characteristics, the comprehensive application of radiation imaging and visible light imaging, near-infrared imaging, hyperspectral imaging technology and various types of image recognition technology can be integrated and complemented to expand the range of material categories detected, thereby expanding the material recognition types and improving the material recognition effect.

[0130] It will be appreciated by those skilled in the art that the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations or combinations are not explicitly described in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0131] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A material sorting method, comprising: In response to the particle size information of the material to be sorted meeting the preset conditions, controlling at least one of the radiation source and the detector to move to obtain a radiation distance and a detection distance adapted to the particle size information; Controlling the radiation source to send radiation rays to the material to be sorted based on the radiation distance, and controlling the detector to receive radiation signals of the radiation rays based on the detection distance to obtain a radiation image; The material to be sorted is sorted according to the radiation image.

2. The method according to claim 1, characterized in that The step of controlling the movement of at least one of the radiation source and the detector according to the particle size information of the material to be sorted includes at least one of the following: Controlling the radiation source to approach or move away from the bottom of the material to be sorted along the transmission path of the radiation, wherein the radiation source is located below the material to be sorted; Along the transmission path of the ray signal, the detector is controlled to approach or move away from the top of the material to be sorted, wherein the detector is located above the material to be sorted.

3. The method according to claim 1 or 2, characterized in that: The step of controlling the movement of at least one of the radiation source and the detector according to the particle size information of the material to be sorted further comprises: During the process of transporting the material to be sorted, in response to the change of the particle size information of the material to be sorted entering the radiation area of ​​the radiation source, the position of at least one of the radiation source and the detector is dynamically adjusted.

4. The method according to claim 3, characterized in that A conveyor belt is provided to transport the materials to be sorted. The radiation source is located below the area of ​​the conveyor belt carrying the material to be sorted, and the detector is located above the area of ​​the conveyor belt carrying the material to be sorted.

5. The method according to any one of claims 1, 2 or 4, characterized in that: The step of controlling the movement of at least one of the radiation source and the detector according to the particle size information of the material to be sorted further comprises: According to the particle size information of the material to be sorted, controlling the movement of the radiation source to obtain a radiation distance that matches the particle size information; The detector is controlled to move according to the position of the ray source to obtain a detection distance that matches the particle size information.

6. The method according to claim 5, characterized in that The detector includes a plurality of sub-detectors, and controlling the movement of the detector according to the position of the ray source includes: Controlling the movement of at least one of the plurality of sub-detectors according to the position of the ray source to obtain a detection distance of each sub-detector adapted to the particle size information; Each sub-detector is adapted to have the same or different detection distance as any other sub-detector for the same particle size information.

7. The method according to claim 6, characterized in that The plurality of sub-detectors are arranged in an arc shape, and after the detectors are controlled to move according to the position of the ray source, at least one of the following items is further included: The distances between the plurality of arc-shaped sub-detectors and the ray source are substantially equal; The distances between any two of the plurality of arc-shaped sub-detectors are substantially equal; The detection angle of each sub-detector is substantially the same before and after the movement, wherein the detection angle of each sub-detector is adjustable.

8. The method according to claim 1, characterized in that Before controlling at least one of the radiation source and the detector to move, the materials to be sorted are arranged in batches, The preset condition includes at least one of the following: In the case of different particle sizes of materials in the same batch, the difference between the particle size of the material to be sorted radiated at a first moment in the future and the particle size of the material to be sorted radiated at a second moment in the past is greater than a specific threshold, wherein the first moment is adjacent to the second moment; When the particle sizes of materials in different batches are different and the particle sizes of materials in the same batch are the same, the difference in particle sizes of adjacent batches of materials to be sorted is greater than a specific threshold.

9. The method according to claim 1, characterized in that: The sorting of the materials to be sorted according to the radiation image comprises: Obtaining at least one of a visible light image, a near infrared image, and a hyperspectral image of the material to be sorted; The material to be sorted is sorted according to an image processing result of the radiation image and at least one of a visible light image, a near infrared image and a hyperspectral image of the material to be sorted.

10. The method according to claim 9, characterized in that Sorting the material to be sorted according to the image processing result of the radiation image and at least one of the visible light image, the near infrared image and the hyperspectral image of the material to be sorted comprises: fusing the radiation image with at least one of a visible light image, a near infrared image and a hyperspectral image of the material to be sorted to obtain a fused image; The materials to be sorted are sorted according to the material recognition result based on the fused image.

11. The method according to claim 9, characterized in that Sorting the material to be sorted according to the image processing result of the radiation image and at least one of the visible light image, the near infrared image and the hyperspectral image of the material to be sorted comprises: Respectively identifying the radiation image, the visible light image, the near infrared image, and the hyperspectral image; Performing weighted fusion on the recognition results of the radiation image, the visible light image, the near infrared image and the hyperspectral image to obtain a final recognition result; The materials to be sorted are sorted according to the final recognition result.

12. The method according to claim 11, characterized in that Before weighted fusion of the recognition results of the radiation image, the visible light image, the near infrared image and the hyperspectral image, the method further includes: extracting radiation features, visible light features, near infrared features and hyperspectral features from the radiation image, the visible light image, the near infrared image and the hyperspectral image respectively; Respectively matching the radiation characteristics, visible light characteristics, near infrared characteristics and hyperspectral characteristics with respective preset characteristic conditions; Corresponding weights are allocated according to the matching degrees of the radiation features, visible light features, near infrared features and hyperspectral features, wherein the matching degree is positively correlated with the weights.

13. A material sorting device, comprising: A conveying module, used for conveying materials to be sorted; A radiation source, mounted on the first moving assembly and located below the bottom of the conveying module for carrying the area of ​​the material to be sorted; A detector, mounted on the second moving assembly and located above the top of the material to be sorted; A control module is used to control the first moving component to drive the ray source to move, and control the second moving component to drive the detector to move, so as to execute the method according to any one of claims 1 to 12.

14. The device according to claim 13, characterized in that The first moving component comprises: The first guide rail is connected to the ray source and is used to drive the ray source to approach or move away from the bottom.

15. The device according to claim 13, characterized in that The second moving component comprises: The second guide rail is connected to the detector and is used to drive the detector to approach or move away from the top.

16. The device according to claim 13 or 15, characterized in that The detector includes a plurality of sub-detectors arranged in an arc shape, wherein the distances between each of the plurality of sub-detectors and the radiation source are substantially equal.

17. The device according to claim 16, characterized in that The second moving component also includes: A plurality of third guide rails connected to the plurality of sub-detectors in a one-to-one correspondence; Each third guide rail is configured to drive the connected sub-detector to move.

18. The device according to claim 17, characterized in that The second moving component also includes: A plurality of rotating assemblies are mounted on the third guide rail in a one-to-one correspondence and are connected to the plurality of sub-detectors in a one-to-one correspondence; Each rotating assembly is used to drive the connected sub-detector to rotate so as to change the detection angle.

Images