Tailings control method and terminal of elutriation magnetic separator based on AI technology

Abstract

The application provides a kind of based on AI technology's elutriation magnetic separator tailings control method and terminal.The method comprises: obtaining overflow product identification data, and determining overflow tailings grade based on overflow product identification data and pre-trained overflow product element content identification model;When the overflow tailings grade exceeds the set grade range, determine the adjustment scheme of the operation parameters of the elutriation magnetic separator based on the overflow tailings grade and the set grade range;Wherein, the operation parameters: one or more of water supply amount, magnetic field strength and pulp concentration.The application can determine the overflow tailings grade through the overflow product identification data, improve the efficiency and accuracy of overflow tailings grade detection, improve the accuracy and efficiency of the adjustment of the elutriation magnetic separator, so as to realize the accurate control of the tailings grade.

Description

Technical Field

[0001] This invention relates to the field of magnetic mineral separation technology, and in particular to a method and terminal for controlling tailings of a washing magnetic separator based on AI technology. Background Technology

[0002] The washing magnetic separator is affected by factors such as ore feeding and water supply, resulting in unstable operation issues such as uneven water supply, uneven overflow of tailings, fluctuations in the overflow liquid level, and the tendency for the overflow tailings to turn black. Currently, the main way to determine whether the grade of the overflow tailings from the washing magnetic separator meets the requirements and to adjust the separator is through the operator's experience, such as observing the blackening state and color of the overflow surface to adjust the operation. However, due to subjective differences and biases in human judgment, it is impossible to continuously and accurately monitor the grade of the overflow tailings and maintain its optimal state. In addition, there is no stable and reliable detection instrument to improve the monitoring accuracy of the overflow tailings grade. Even when the overflow tailings are detected using laboratory testing equipment, the poor timeliness leads to low efficiency in the existing control schemes for the washing magnetic separator. Summary of the Invention

[0003] This invention provides a tailings control method and terminal for washing magnetic separators based on AI technology, in order to solve the problems of low efficiency and low control accuracy in existing control schemes for washing magnetic separators.

[0004] In a first aspect, embodiments of the present invention provide a method for controlling tailings from a washing magnetic separator based on AI technology, including:

[0005] Acquire overflow product identification data, and determine the overflow tailings grade based on the overflow product identification data and a pre-trained overflow product element content identification model;

[0006] When the grade of the overflow tailings exceeds the set grade range, an adjustment scheme for the operating parameters of the washing magnetic separator is determined based on the grade of the overflow tailings and the set grade range, and the operating parameters of the washing magnetic separator are adjusted according to the adjustment scheme; wherein, the operating parameters are one or more of the following: water supply, magnetic field strength and slurry concentration.

[0007] In one possible implementation, when the grade of the overflow tailings is greater than the upper limit of the set grade range, the difference between the grade of the overflow tailings and the upper limit is determined as a grade deviation value, and when the grade of the overflow tailings is less than the lower limit of the set grade range, the difference between the grade of the overflow tailings and the lower limit is determined as a grade deviation value.

[0008] The number of operating parameters in the adjustment scheme is determined based on the grade deviation value; wherein, the larger the grade deviation value, the more operating parameters are in the adjustment scheme.

[0009] In one possible implementation, the adjustment scheme for the operating parameters of the washing magnetic separator is determined based on the grade of the overflow tailings and the set grade range, including:

[0010] When the grade of the overflow tailings is greater than or less than the upper limit of the set grade range, the water supply correction value, magnetic field strength correction value, and slurry concentration correction value are determined.

[0011] Wherein, when the grade of the overflow tailings is greater than the set grade range, the water supply correction value and the slurry concentration correction value are negative, and the magnetic field strength correction value is positive;

[0012] When the grade of the overflow tailings is less than the set grade range, the water supply correction value and the slurry concentration correction value are positive.

[0013] In one possible implementation, the magnetic field determines the grade of the overflow tailings based on overflow product identification data and a pre-trained overflow product element content identification model, including:

[0014] Feature extraction is performed on the overflow product identification data to obtain feature data; wherein, the feature data includes one or more of the following: overflow product color, overflow product location, area ratio of the target area in the overflow product, volume ratio of the target area in the overflow product, electromagnetic wave intensity, and electromagnetic wave peak position;

[0015] Based on the aforementioned feature data and a pre-trained overflow product element content identification model, the grade of the overflow tailings is determined.

[0016] In one possible implementation, when the overflow product identification data is an overflow product image, radar stereo scanning result, or laser stereo scanning result, feature extraction is performed on the overflow product identification data to obtain feature data, including:

[0017] The color value of each pixel in the overflow product identification data is detected, and the overflow product identification data is divided into one or more target regions based on the color value of each pixel in the overflow product identification data. The area ratio of one or more of the target regions is determined, or the volume ratio of one or more of the target regions is determined.

[0018] Cross-sectional information is determined based on real-time overflow product identification data, and the location of the overflow product is determined based on the cross-sectional information.

[0019] In one possible implementation, when the overflow product identification data is an overflow product image, radar stereo scanning result, or laser stereo scanning result, feature extraction is performed on the overflow product identification data to obtain feature data, including:

[0020] The overflow product identification data is binarized and segmented, and the dark area image is extracted as the target region.

[0021] Determine the area percentage of the target region, or determine the volume percentage of the target region;

[0022] Cross-sectional information is determined based on real-time overflow product identification data, and the location of the overflow product is determined based on the cross-sectional information.

[0023] In one possible implementation, the grade of the overflow tailings is determined based on the feature data and a pre-trained overflow product element content identification model, including:

[0024] The grade of the overflow tailings is determined based on the area of ​​the target region and the overflow tailings content identification model; or...

[0025] The grade of the overflow tailings is determined based on the volume and overflow tailings content identification model of the target area;

[0026] The overflow tailings content identification model is derived from overflow product identification data and overflow tailings grade training.

[0027] In one possible implementation, obtaining the overflow product identification data includes:

[0028] Overflow product identification data is acquired at set time intervals, and the average value of the overflow product identification data acquired at each time point is calculated.

[0029] Secondly, embodiments of the present invention provide a tailings control device for a washing and magnetic separator based on AI technology, comprising:

[0030] The acquisition module is used to acquire overflow product identification data and determine the grade of overflow tailings based on the overflow product identification data and a pre-trained overflow product element content identification model.

[0031] The determination module is used to determine an adjustment scheme for the operating parameters of the washing magnetic separator based on the overflow tailings grade and the set grade range when the overflow tailings grade exceeds the set grade range.

[0032] An adjustment module is used to adjust the operating parameters of the washing magnetic separator according to the adjustment scheme; wherein the operating parameters are one or more of the following: water supply, magnetic field strength, and slurry concentration.

[0033] In one possible implementation, the determining module is specifically used for:

[0034] When the grade of the overflow tailings is greater than the upper limit of the set grade range, the difference between the grade of the overflow tailings and the upper limit is determined as the grade deviation value; and when the grade of the overflow tailings is less than the lower limit of the set grade range, the difference between the grade of the overflow tailings and the lower limit is determined as the grade deviation value.

[0035] The number of operating parameters in the adjustment scheme is determined based on the grade deviation value; wherein, the larger the grade deviation value, the more operating parameters are in the adjustment scheme.

[0036] In one possible implementation, the determining module is specifically used for:

[0037] When the grade of the overflow tailings is greater than or less than the upper limit of the set grade range, the water supply correction value, magnetic field strength correction value, and slurry concentration correction value are determined.

[0038] Wherein, when the grade of the overflow tailings is greater than the set grade range, the water supply correction value and the slurry concentration correction value are negative, and the magnetic field strength correction value is positive;

[0039] When the grade of the overflow tailings is less than the set grade range, the water supply correction value and the slurry concentration correction value are positive.

[0040] In one possible implementation, the acquisition module is specifically used for:

[0041] Feature extraction is performed on the overflow product identification data to obtain feature data; wherein, the feature data includes one or more of the following: overflow product color, overflow product location, area ratio of the target area in the overflow product, volume ratio of the target area in the overflow product, electromagnetic wave intensity, and electromagnetic wave peak position;

[0042] Based on the aforementioned feature data and a pre-trained overflow product element content identification model, the grade of the overflow tailings is determined.

[0043] In one possible implementation, when the overflow product identification data is an overflow product image, radar stereo scanning result, or laser stereo scanning result, the acquisition module is specifically used for:

[0044] The color value of each pixel in the overflow product identification data is detected, and the overflow product identification data is divided into one or more target regions based on the color value of each pixel in the overflow product identification data. The area ratio of one or more of the target regions is determined, or the volume ratio of one or more of the target regions is determined.

[0045] Cross-sectional information is determined based on real-time overflow product identification data, and the location of the overflow product is determined based on the cross-sectional information.

[0046] In one possible implementation, when the overflow product identification data is an overflow product image, radar stereo scanning result, or laser stereo scanning result, the acquisition module is specifically used for:

[0047] The overflow product identification data is binarized and segmented, and the dark area image is extracted as the target region.

[0048] Determine the area percentage of the target region, or determine the volume percentage of the target region;

[0049] Cross-sectional information is determined based on real-time overflow product identification data, and the location of the overflow product is determined based on the cross-sectional information.

[0050] In one possible implementation, the acquisition module is specifically used for:

[0051] The grade of the overflow tailings is determined based on the area of ​​the target region and the overflow tailings content identification model; or...

[0052] The grade of the overflow tailings is determined based on the volume and overflow tailings content identification model of the target area;

[0053] The overflow tailings content identification model is derived from overflow product identification data and overflow tailings grade training.

[0054] In one possible implementation, the acquisition module is specifically used for:

[0055] Overflow product identification data is acquired at set time intervals, and the average value of the overflow product identification data acquired at each time point is calculated.

[0056] Thirdly, embodiments of the present invention provide a terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method as described in the first aspect or any possible implementation thereof.

[0057] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method as described in the first aspect or any possible implementation thereof.

[0058] This invention provides a tailings control method and terminal for a washing magnetic separator based on AI technology. By acquiring overflow product identification data and determining the grade of overflow tailings based on this data, the accuracy and efficiency of overflow tailings grade determination are improved. When the overflow tailings grade exceeds a set grade range, an adjustment scheme for the operating parameters of the washing magnetic separator is determined based on the overflow tailings grade and the set grade range. The operating parameters include one or more of the following: water supply, magnetic field strength, and slurry concentration. This invention, by determining the overflow tailings grade through overflow product identification data, enables online, real-time, continuous, and accurate detection of the elemental content or concentration of the overflow product, improving detection efficiency and accuracy. Based on the detection results, the operating parameters of the washing magnetic separator are adjusted, thereby improving tailings control efficiency. Attached Figure Description

[0059] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0060] Figure 1 This is a flowchart illustrating the implementation of an AI-based tailings control method for washing magnetic separators, according to an embodiment of the present invention.

[0061] Figure 2 This is a schematic diagram of the structure of a tailings control device for a washing magnetic separator based on AI technology, provided in an embodiment of the present invention.

[0062] Figure 3 This is a schematic diagram of a terminal provided in an embodiment of the present invention. Detailed Implementation

[0063] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0064] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0065] Unless otherwise stated, the term "multiple" means two or more. The character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B means: A or B. The term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.

[0066] The terms used in this application are for describing embodiments only and are not intended to limit the claims. As used in the description of embodiments and claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. Similarly, the term “and / or” as used herein means including one or more of the associated listed elements and all possible combinations thereof. Additionally, when used in this application, the terms “comprise” and its variations “comprises” and / or “comprising” refer to the presence of stated features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof. Without further limitation, an element defined by the phrase “comprises an…” does not exclude the presence of additional identical elements in the process, method, or apparatus that includes said element.

[0067] In this application, each embodiment focuses on describing the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, then the relevant parts can be referred to the description of the method section.

[0068] In practical applications, column-type mineral processing equipment is commonly used. The feed enters the middle of the column from the upper part, disperses, and then enters the separation zone. Buoyancy is generated by water or gas, and the rise and fall of mineral particles are controlled by a magnetic field. Under the interaction of magnetic force, gravity, the force of rising water, and / or the buoyancy of air bubbles, the overflow tailings are separated from the product concentrate. Lighter particles flow out through the overflow trough and overflow pipe to form tailings, while the concentrate is discharged from the bottom.

[0069] To make the objectives, technical solutions, and advantages of the present invention clearer, specific embodiments will be described below in conjunction with the accompanying drawings.

[0070] Figure 1 This diagram illustrates an application scenario of the AI-based tailings control method for magnetic separator washing, as provided in an embodiment of the present invention. Figure 1 As shown, it includes the following steps:

[0071] S101, acquire overflow product identification data, and determine the overflow tailings grade based on the overflow product identification data and the pre-trained overflow product element content identification model.

[0072] The tailings control method for washing magnetic separators based on AI technology provided in this application is executed by a washing magnetic separator controller, or by an electronic terminal with data processing capabilities that is communicatively connected to the washing magnetic separator controller, such as a desktop computer, laptop, tablet, or mobile phone. Overflow product identification data is obtained from an image acquisition module, such as a camera, located on the washing magnetic separator or in a working environment capable of monitoring the status of the washing magnetic separator. Optionally, the overflow product identification data is obtained based on scanning with a stereo scanning radar, laser stereo scanner, or infrared scanner.

[0073] The controller or electronic terminal of the washing magnetic separator includes at least a communication module to acquire overflow product identification data through direct or indirect communication with an image acquisition module, scanning radar or scanner.

[0074] The determination of overflow tailings grade based on overflow product identification data is mainly achieved by inputting the overflow product identification data into a pre-trained overflow tailings grade identification model to obtain the overflow tailings grade identification result. Optionally, the overflow tailings grade identification model is mainly trained based on the historical overflow tailings content data of the target washing magnetic separator equipment, wherein the overflow tailings content data specifically includes: overflow tailings grade and / or overflow tailings concentration.

[0075] Accordingly, before determining the grade of overflow tailings based on overflow product identification data, the process also includes: obtaining the corresponding overflow tailings grade identification model based on the local information of the washing magnetic separator, so as to ensure that the overflow tailings grade identification model can adapt to the identification needs of the washing magnetic separator and improve the accuracy of overflow tailings grade identification.

[0076] S102, when the grade of the overflow tailings exceeds the set grade range, determine the adjustment scheme of the operating parameters of the washing magnetic separator based on the grade of the overflow tailings and the set grade range, and adjust the operating parameters of the washing magnetic separator according to the adjustment scheme; wherein, the operating parameters are one or more of the following: water supply, magnetic field strength and slurry concentration.

[0077] The grade of overflow tailings refers to the percentage of metal contained in the overflow tailings relative to the quantity of raw ore, reflecting the metal loss during the beneficiation process. The grade of concentrate, on the other hand, refers to the percentage of metal contained in the concentrate relative to the quantity of concentrate, serving as an indicator of concentrate quality. A higher overflow tailings grade indicates more severe metal loss, and consequently, a lower metal content in the concentrate. Due to the difficulty in acquiring images or calculating the grade of concentrate, easily accessible overflow product identification data is used to adjust the overflow tailings grade to ensure the concentrate grade meets requirements after washing. The set grade range is primarily based on the required concentrate grade.

[0078] In different embodiments, the grade of overflow tailings can be flexibly adjusted by adjusting one or more of the operating parameters, such as water supply, magnetic field strength, and slurry concentration, thereby improving the control accuracy and efficiency of overflow tailings grade.

[0079] In this embodiment of the invention, by acquiring overflow product identification data and determining the overflow tailings grade based on the overflow product identification data, the accuracy and efficiency of overflow tailings grade determination are improved. When the overflow tailings grade exceeds the set grade range, an adjustment scheme for the operating parameters of the washing magnetic separator is determined based on the overflow tailings grade and the set grade range. The operating parameters include one or more of the following: water supply, magnetic field strength, and slurry concentration. This embodiment of the invention, by determining the overflow tailings grade through overflow product identification data, allows for online, real-time, continuous, and accurate detection of the elemental content or concentration of the overflow product, improving detection efficiency and accuracy. Furthermore, based on the detection results, the operating parameters of the washing magnetic separator are adjusted, thereby improving tailings control efficiency.

[0080] In one possible implementation, when the grade of the overflow tailings is greater than the upper limit of the set grade range, the difference between the grade of the overflow tailings and the upper limit is determined as the grade deviation value, and when the grade of the overflow tailings is less than the lower limit of the set grade range, the difference between the grade of the overflow tailings and the lower limit is determined as the grade deviation value.

[0081] The number of operating parameters in the adjustment plan is determined based on the grade deviation value; the larger the grade deviation value, the more operating parameters are required in the adjustment plan.

[0082] The larger the grade deviation value, the more operating parameters are included in the adjustment plan, and the faster the adjustment speed. In practice, as the operating parameters are adjusted, the grade deviation value decreases, and the number of operating parameters in the corresponding adjustment plan decreases, avoiding over-adjustment and improving control accuracy.

[0083] In this embodiment, the number of operating parameters in the adjustment scheme is determined based on the deviation between the grade of the overflow tailings and the set grade range, which can comprehensively meet the requirements of control accuracy and control efficiency.

[0084] In one possible implementation, step S102, which involves determining the adjustment scheme for the operating parameters of the washing magnetic separator based on the grade of the overflow tailings and a set grade range, includes:

[0085] When the grade of the overflow tailings is greater than or less than the upper limit of the set grade range, determine the correction values ​​for water supply, magnetic field strength and slurry concentration.

[0086] Among them, when the grade of overflow tailings is greater than the set grade range, the correction values ​​for water supply and slurry concentration are negative, while the correction value for magnetic field strength is positive.

[0087] When the grade of the overflow tailings is less than the set grade range, the correction values ​​for water supply and slurry concentration are positive, while the correction value for magnetic field strength is negative.

[0088] When the grade of the overflow tailings exceeds the set grade range, the metal loss in the overflow tailings is more severe. The water supply correction value and slurry concentration can be reduced to avoid further metal loss. In addition, the magnetic field strength can be increased to prevent metal from entering the overflow tailings and causing losses.

[0089] This shows that different strategies exist for adjusting water supply, magnetic field strength, and slurry concentration. Under the same operating conditions, the more severe the metal loss during the mineral processing, the more effective it is to reduce the water supply and slurry concentration, thus decreasing the metal content in the overflow tailings. Conversely, increasing the magnetic field strength can reduce the metal content in the overflow tailings.

[0090] In the embodiments of this application, different control strategies are adopted for water supply, magnetic field strength and slurry concentration to improve the accuracy of overflow tailings grade control.

[0091] In one possible implementation, step S101, which determines the grade of the overflow tailings based on overflow product identification data and a pre-trained overflow product element content identification model, includes:

[0092] Feature extraction is performed on the overflow product identification data to obtain feature data; the feature data includes one or more of the following: overflow product color, overflow product location, area ratio of the target area in the overflow product, volume ratio of the target area in the overflow product, electromagnetic wave intensity, and electromagnetic wave peak position;

[0093] The grade of the overflow tailings is determined based on the characteristic data and the pre-trained overflow product element content identification model.

[0094] The target region is the region corresponding to the feature data. The feature data is the metal image data in the overflow tailings. In the specific implementation process, water needs to be added to wash the overflow tailings. In addition, the overflow tailings contain sand and dust, and the area of ​​water mixed with sand and dust in the overflow product identification data accounts for a relatively large proportion. The image area corresponding to water is not used to represent the metal content in the overflow tailings, and therefore is not used as feature data. Specifically, what needs to be extracted is the image data of color that is different from the water mixed with sand and dust.

[0095] Furthermore, when different components exist in the overflow tailings, their corresponding colors will differ. Additionally, in cases of uneven mixing, the same component will appear with varying shades of color in the image. Therefore, when determining feature data, it is necessary to cluster different overflow tailings regions based on color difference values ​​within different ranges to improve the accuracy of target region segmentation within the overflow tailings.

[0096] In actual implementation, as the overflow product increases, the liquid overflows the overflow weir, and the height changes to a certain extent before it no longer increases linearly. The overflow outlet angle will change, meaning that the position of the overflow product will be different. Therefore, the volume of the overflow product can be determined based on the position of the overflow product.

[0097] In one possible implementation, when the overflow product identification data is an image of the overflow product, and the image is a planar image, feature extraction is performed on the overflow product identification data to obtain feature data, including:

[0098] Detect the color value of each pixel in the real-time overflow product image, divide the real-time overflow product image into one or more target regions based on the color value of each pixel, and determine the area percentage of one or more target regions; or,

[0099] The overflow product image is binarized and segmented to extract the dark area image as the target region, and the area ratio of the target region is determined.

[0100] Cross-sectional information is determined based on real-time overflow product identification data, and the location of the overflow product is determined based on the cross-sectional information.

[0101] In one possible implementation, when the real-time overflow product identification data is a radar stereo scan result or a laser stereo scan result, the scan result is a stereo image. Feature extraction is performed on the overflow product identification data to obtain feature data, including:

[0102] Detect the color value of each pixel in the real-time overflow product recognition data, divide the real-time overflow product image based on the color value of each pixel, and determine the volume proportion of one or more target regions; or...

[0103] The real-time overflow product identification data is binarized and segmented, the dark area image is extracted as the target area, and the volume ratio of the target area is determined.

[0104] Cross-sectional information is determined based on real-time overflow product identification data, and the location of the overflow product is determined based on the cross-sectional information.

[0105] In actual implementation, as the overflow product increases, the liquid overflows the overflow weir, and the height changes to a certain extent before it no longer increases linearly. The overflow outlet angle will change, meaning that the position of the overflow product will be different. Therefore, the volume of the overflow product can be determined based on the position of the overflow product.

[0106] In one possible implementation, when the overflow product identification data is infrared spectrum, feature extraction is performed on the real-time overflow product identification data to obtain feature data, including:

[0107] The intensity of electromagnetic waves and the corresponding peak positions are read from the infrared spectrum.

[0108] Specifically, based on the color value of each pixel in the overflow product identification data, the overflow product identification data is divided to determine one or more target regions, including:

[0109] The main color of the overflow product identification data;

[0110] Based on the main color, a coarse match is performed on the overflow product identification data to filter out candidate feature regions;

[0111] Determine the center point of one or more candidate feature regions;

[0112] The edge features of the candidate region are obtained by fine matching using the color value of the pixel corresponding to the center point and the preset tolerance.

[0113] One or more target regions are determined based on edge features after segmentation.

[0114] Specifically, when the overflow product identification data is a planar image captured by a camera, the determined target area is a region with a certain area ratio on the plane; when the overflow product identification data is the scanning result of a stereo scanning radar or a laser stereo scanner, the determined target area is a region with a certain volume ratio within the stereo range.

[0115] The main color of the overflow product identification data is the color of the water during the washing process (or background color). Based on the main color, the overflow product identification data is coarsely matched to filter out candidate feature regions that are significantly different from the main color, so as to further refine the region division and reduce the amount of computation in the feature region identification process.

[0116] Candidate feature regions are represented as discrete areas or discontinuously connected large areas, corresponding to one or more candidate feature regions. The center point of each candidate feature region is roughly estimated; often, the color value changes within the region follow a certain pattern radiating outwards from the center point. Fine matching is then performed using the color value of the center point of each candidate feature region and a preset tolerance to obtain the edge features of the candidate regions, thus eliminating regions whose edges are close to the main color. Furthermore, when different components are mixed together, regions of different components are divided based on the color value of the center point and the preset tolerance. Therefore, the number of target regions obtained after fine matching is greater than or equal to the number of candidate feature regions.

[0117] In another possible implementation, when the overflow product identification data is an image of the overflow product, a radar stereo scan result, or a laser stereo scan result, feature extraction is performed on the overflow product identification data to obtain feature data, including:

[0118] The overflow product identification data is binarized and segmented, and the dark area image is extracted as the target region.

[0119] Determine the area percentage of the target region, or determine the volume percentage of the target region;

[0120] Cross-sectional information is determined based on real-time overflow product identification data, and the location of the overflow product is determined based on the cross-sectional information.

[0121] Among them, binarization of overflow product identification data can improve image contrast, distinguish feature regions from main colors, and distinguish feature regions corresponding to different components, thereby improving feature recognition efficiency.

[0122] In one possible implementation, the grade of the overflow tailings is determined based on feature data and a pre-trained overflow product element content identification model, including:

[0123] The grade of overflow tailings is determined based on an identification model that identifies the area and content of the overflow tailings in the target region; or,

[0124] The grade of overflow tailings is determined based on the volume and overflow tailings content identification model of the target area;

[0125] Among them, the overflow tailings content identification model is trained based on overflow product identification data and overflow tailings grade.

[0126] In one possible implementation, acquiring overflow product identification data includes:

[0127] Overflow product identification data is acquired at set time intervals, and the average value of the overflow product identification data acquired at each time point is calculated.

[0128] In one specific embodiment, when the overflow product identification data is a planar image captured by a camera, multiple frames of images are acquired in a time-division manner according to a set time interval, and the average value of the multiple frames of images is calculated.

[0129] In this embodiment, the accuracy of identifying each component during the washing process is improved by using multiple consecutive frames of overflow tailings data, or the accuracy of identifying each component is improved by using multiple frames of overflow tailings data images taken at different times or light angles in a static state.

[0130] In another specific embodiment, when the overflow product identification data is the scanning result of a stereo scanning radar or a laser stereo scanner, multiple overflow product scanning results are acquired at set time intervals, and the average value of the overflow product identification data acquired at each time point is calculated. The time interval between two adjacent overflow product scanning results is less than a set value.

[0131] Radar stereo scanning results need to be determined based on multiple frames of radar scanning signals within a set scanning period, with a certain time interval between adjacent scanning periods. Laser stereo scanning results need to be determined based on multiple frames of laser signals within a set scanning period, with a certain time interval between adjacent scanning periods. If the scanning time interval between two adjacent scanning periods is less than a set value, it ensures that the selected overflow product identification data is obtained through continuous scanning, and that the changes in the overflow product are minimal.

[0132] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0133] The following are device embodiments of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.

[0134] Figure 2 A schematic diagram of a tailings control device for a washing and magnetic separator based on AI technology, according to an embodiment of the present invention, is shown. For ease of explanation, only the parts relevant to the embodiment of the present invention are shown, and are described in detail below:

[0135] like Figure 2 As shown, the tailings control device 2 based on AI technology for washing and magnetic separation includes: an acquisition module 201, a determination module 202, and an adjustment module 203.

[0136] The acquisition module 201 is used to acquire overflow product identification data and determine the grade of overflow tailings based on the overflow product identification data and the pre-trained overflow product element content identification model.

[0137] The determination module 202 is used to determine the adjustment scheme of the operating parameters of the washing magnetic separator based on the overflow tailings grade and the set grade range when the overflow tailings grade exceeds the set grade range.

[0138] The adjustment module 203 is used to adjust the operating parameters of the washing magnetic separator according to the adjustment plan; wherein the operating parameters are one or more of the following: water supply, magnetic field strength and slurry concentration.

[0139] In one possible implementation, module 202 is specifically used for:

[0140] When the grade of the overflow tailings is greater than the upper limit of the set grade range, the difference between the grade of the overflow tailings and the upper limit is determined as the grade deviation value. When the grade of the overflow tailings is less than the lower limit of the set grade range, the difference between the grade of the overflow tailings and the lower limit is determined as the grade deviation value.

[0141] The number of operating parameters in the adjustment plan is determined based on the grade deviation value; the larger the grade deviation value, the more operating parameters are required in the adjustment plan.

[0142] In one possible implementation, module 202 is specifically used for:

[0143] When the grade of the overflow tailings is greater than or less than the upper limit of the set grade range, determine the correction values ​​for water supply, magnetic field strength and slurry concentration.

[0144] Among them, when the grade of overflow tailings is greater than the set grade range, the correction values ​​for water supply and slurry concentration are negative, while the correction value for magnetic field strength is positive.

[0145] When the grade of the overflow tailings is less than the set grade range, the correction values ​​for water supply and slurry concentration are positive.

[0146] In one possible implementation, module 201 is specifically used for:

[0147] Feature extraction is performed on the overflow product identification data to obtain feature data; the feature data includes one or more of the following: overflow product color, overflow product location, area ratio of the target area in the overflow product, volume ratio of the target area in the overflow product, electromagnetic wave intensity, and electromagnetic wave peak position;

[0148] The grade of the overflow tailings is determined based on the characteristic data and the pre-trained overflow product element content identification model.

[0149] In one possible implementation, when the overflow product identification data is an overflow product image, radar stereo scanning result, or laser stereo scanning result, the acquisition module 201 is specifically used for:

[0150] The color value of each pixel in the overflow product identification data is detected. Based on the color value of each pixel in the overflow product identification data, the overflow product identification data is divided to determine one or more target regions, and the area ratio of one or more target regions is determined, or the volume ratio of one or more target regions is determined.

[0151] Cross-sectional information is determined based on real-time overflow product identification data, and the location of the overflow product is determined based on the cross-sectional information.

[0152] In one possible implementation, when the overflow product identification data is an overflow product image, radar stereo scanning result, or laser stereo scanning result, the acquisition module 201 is specifically used for:

[0153] The overflow product identification data is binarized and segmented, and the dark area image is extracted as the target region.

[0154] Determine the area percentage of the target region, or determine the volume percentage of the target region;

[0155] Cross-sectional information is determined based on real-time overflow product identification data, and the location of the overflow product is determined based on the cross-sectional information.

[0156] In one possible implementation, module 201 is specifically used for:

[0157] The grade of overflow tailings is determined based on an identification model that identifies the area and content of the overflow tailings in the target region; or,

[0158] The grade of overflow tailings is determined based on the volume and overflow tailings content identification model of the target area;

[0159] Among them, the overflow tailings content identification model is trained based on overflow product identification data and overflow tailings grade.

[0160] In one possible implementation, module 201 is specifically used for:

[0161] Overflow product identification data is acquired at set time intervals, and the average value of the overflow product identification data acquired at each time point is calculated.

[0162] In this embodiment of the invention, by acquiring overflow product identification data and determining the overflow tailings grade based on the overflow product identification data, the accuracy and efficiency of overflow tailings grade determination are improved. When the overflow tailings grade exceeds the set grade range, an adjustment scheme for the operating parameters of the washing magnetic separator is determined based on the overflow tailings grade and the set grade range. The operating parameters include one or more of the following: water supply, magnetic field strength, and slurry concentration. This embodiment of the invention, by determining the overflow tailings grade through overflow product identification data, allows for online, real-time, continuous, and accurate detection of the elemental content or concentration of the overflow product, improving detection efficiency and accuracy. Furthermore, based on the detection results, the operating parameters of the washing magnetic separator are adjusted, thereby improving tailings control efficiency.

[0163] Figure 3 This is a schematic diagram of a terminal provided in an embodiment of the present invention. For example... Figure 3 As shown, the terminal 3 in this embodiment includes: a processor 30, a memory 31, and a computer program 32 stored in the memory 31 and executable on the processor 30. When the processor 30 executes the computer program 32, it implements the steps in the various embodiments of the AI-based tailings control method for washing and magnetic separation machines, for example... Figure 1 The steps are shown. Alternatively, when the processor 30 executes the computer program 32, it implements the functions of each module / unit in the above-described device embodiments, for example... Figure 2 The functions of each module are shown.

[0164] For example, the computer program 32 can be divided into one or more modules / units, which are stored in the memory 31 and executed by the processor 30 to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program 32 in the terminal 3. For example, the computer program 32 can be divided into... Figure 2 The modules shown.

[0165] The terminal 3 can be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal 3 may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art will understand that... Figure 3 This is merely an example of terminal 3 and does not constitute a limitation on terminal 3. It may include more or fewer components than shown, or combine certain components, or different components. For example, the terminal may also include input / output devices, network access devices, buses, etc.

[0166] The processor 30 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0167] The memory 31 can be an internal storage unit of the terminal 3, such as a hard disk or memory of the terminal 3. The memory 31 can also be an external storage device of the terminal 3, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the terminal 3. Furthermore, the memory 31 can include both internal storage units and external storage devices of the terminal 3. The memory 31 is used to store the computer program and other programs and data required by the terminal. The memory 31 can also be used to temporarily store data that has been output or will be output.

[0168] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0169] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0170] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0171] In the embodiments provided by this invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0172] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0173] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0174] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of the above embodiments of the AI-based tailings control method for washing and separating magnetic separators. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately added to or subtracted from the content as required by the legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium may not include mains carrier signals and telecommunication signals.

[0175] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for controlling tailings from a washing magnetic separator based on AI technology, characterized in that, include: Acquire overflow product identification data, and determine the overflow tailings grade based on the overflow product identification data and a pre-trained overflow product element content identification model; When the grade of the overflow tailings exceeds the set grade range, an adjustment scheme for the operating parameters of the washing magnetic separator is determined based on the grade of the overflow tailings and the set grade range, and the operating parameters of the washing magnetic separator are adjusted according to the adjustment scheme; wherein, the operating parameters are one or more of the following: water supply, magnetic field strength and slurry concentration; Specifically, when the grade of the overflow tailings is greater than the upper limit of the set grade range, the difference between the grade of the overflow tailings and the upper limit is determined as the grade deviation value; and when the grade of the overflow tailings is less than the lower limit of the set grade range, the difference between the grade of the overflow tailings and the lower limit is determined as the grade deviation value. The number of operating parameters in the adjustment plan is determined based on the grade deviation value; wherein, the larger the grade deviation value, the more operating parameters are in the adjustment plan. Specifically, when the overflow product identification data is an overflow product image, radar stereo scanning result, or laser stereo scanning result, feature extraction is performed on the overflow product identification data to obtain feature data, including: The color value of each pixel in the overflow product identification data is detected, and the overflow product identification data is divided into one or more target regions based on the color value of each pixel in the overflow product identification data. The area ratio of one or more of the target regions is determined, or the volume ratio of one or more of the target regions is determined. Cross-sectional information is determined based on real-time overflow product identification data, and the location of the overflow product is determined based on the cross-sectional information; The determination of the grade of overflow tailings based on overflow product identification data and a pre-trained overflow product element content identification model includes: Feature extraction is performed on the overflow product identification data to obtain feature data; wherein, the target area is the area corresponding to the feature data; the feature data is metal image data in the overflow tailings; the feature data includes: overflow product color, overflow product location, area ratio of the target area in the overflow product, volume ratio of the target area in the overflow product, electromagnetic wave intensity, and electromagnetic wave peak position; Based on the aforementioned feature data and a pre-trained overflow product element content identification model, the grade of the overflow tailings is determined.

2. The tailings control method for washing magnetic separators based on AI technology according to claim 1, characterized in that, The adjustment scheme for the operating parameters of the washing magnetic separator is determined based on the grade of the overflow tailings and the set grade range, including: When the grade of the overflow tailings is greater than or less than the upper limit of the set grade range, the water supply correction value, magnetic field strength correction value, and slurry concentration correction value are determined. Wherein, when the grade of the overflow tailings is greater than the set grade range, the water supply correction value and the slurry concentration correction value are negative, and the magnetic field strength correction value is positive; When the grade of the overflow tailings is less than the set grade range, the water supply correction value and the slurry concentration correction value are positive, and the magnetic field strength correction value is negative.

3. The tailings control method for washing magnetic separators based on AI technology according to claim 1, characterized in that, When the overflow product identification data is an overflow product image, radar stereo scanning result, or laser stereo scanning result, feature extraction is performed on the overflow product identification data to obtain feature data, including: The overflow product identification data is binarized and segmented, and the dark area image is extracted as the target region. Determine the area percentage of the target region, or determine the volume percentage of the target region; Cross-sectional information is determined based on real-time overflow product identification data, and the location of the overflow product is determined based on the cross-sectional information.

4. The tailings control method for washing magnetic separators based on AI technology according to claim 1, characterized in that, Based on the aforementioned feature data and a pre-trained overflow product element content identification model, the grade of the overflow tailings is determined, including: The grade of the overflow tailings is determined based on the area of ​​the target region and the overflow tailings content identification model; or... The grade of the overflow tailings is determined based on the volume and overflow tailings content identification model of the target area; The overflow tailings content identification model is derived from overflow product identification data and overflow tailings grade training.

5. The method for controlling tailings from a washing magnetic separator based on AI technology according to any one of claims 1 to 4, characterized in that, The acquisition of overflow product identification data includes: Overflow product identification data is acquired at set time intervals, and the average value of the overflow product identification data acquired at each time point is calculated.

6. A terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 5 above.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 5 above.

Images