Mineral screening system and method based on mechanical arm

Abstract

The invention relates to the technical field of mechanical arm control and discloses a mineral screening system and method based on a mechanical arm, and the method comprises the steps that three-dimensional form information of all minerals on a conveying belt is obtained based on a scanning module, element fingerprints of all the minerals are determined according to a short wave infrared spectrum, and form component characteristics of the minerals are established based on mineral coordinates; establishing each mineral model according to the three-dimensional form of each mineral, and determining the classification and specification of each mineral on the conveyor belt based on each mineral model and the form component characteristics of each mineral; screening the minerals based on preset mineral types and mineral specifications, and determining to-be-screened minerals; and the grabbing posture scores of all the to-be-screened minerals are obtained, the grabbing sequence of all the to-be-screened minerals is determined according to the grabbing posture scores, a grabbing instruction is generated, and the mechanical arm is controlled to grab all the to-be-screened minerals. According to the method, efficient and accurate mineral classification and automatic screening are achieved through the three-dimensional form of the mineral, spectral component analysis and an intelligent screening and grabbing strategy.

Description

Technical Field

[0001] The present invention relates to the technical field of robotic arm control, and more particularly, to a mineral screening system and method based on a robotic arm. Background Art

[0002] With the continuous development of automation technology, robotic arms are increasingly widely used in the industrial field. Especially in the process of mineral screening, the application of robotic arms improves the screening efficiency and accuracy.

[0003] However, currently, mineral screening tasks usually face challenges such as a large variety of minerals, different shapes, and complex screening environments. Therefore, how to accurately and efficiently classify, screen, and grasp minerals has become an important issue in current technical research. In addition, the screening process of minerals needs to be classified based on the three-dimensional morphological information and elemental composition characteristics of minerals. Traditional mineral screening methods rely on manual labor or simple robotic arms, lacking accurate mineral data support, resulting in low screening accuracy and poor efficiency. At the same time, when using a robotic arm for grasping, the grasping strategy is the most important technology. However, most traditional grasping strategies rely on manual experience or simple algorithms and do not fully utilize the accurate data of minerals, resulting in low mineral grasping efficiency and certain operation risks.

[0004] Therefore, there is an urgent need to invent a mineral screening technology for robotic arms to solve the problems of low screening accuracy, poor efficiency, complex screening environment, grasping strategy relying on manual experience, and insufficient grasping stability in the prior art when screening minerals based on a robotic arm. Summary of the Invention

[0005] In view of this, the present invention proposes a mineral screening system and method based on a robotic arm, aiming to solve the problems of low screening accuracy, poor efficiency, complex screening environment, grasping strategy relying on manual experience, and insufficient grasping stability in the prior art when screening minerals based on a robotic arm.

[0006] The present invention proposes a mineral screening method based on a robotic arm, including:

[0007] Obtaining the three-dimensional morphological information of each mineral on the conveyor belt based on a scanning module, and determining the elemental fingerprint of each mineral according to the short-wave infrared spectrum, and establishing the morphological composition characteristics of the minerals based on the mineral coordinates;

[0008] Establishing a model for each mineral based on the three-dimensional morphology of each mineral, and determining the classification and specifications of each mineral on the conveyor belt based on the models of each mineral and the morphological composition characteristics of each mineral;

[0009] Screening each mineral based on the preset mineral types and specifications, and determining the minerals to be screened;

[0010] Obtain the grasping posture scores of each candidate mineral, and determine the grasping order of each mineral to be screened according to the grasping posture scores;

[0011] Generate a grasping instruction according to the grasping order, and control the robotic arm to grasp each mineral to be screened according to the grasping instruction.

[0012] Further, when obtaining the three-dimensional morphological information of each mineral on the conveyor belt based on the scanning module, it includes:

[0013] Obtain the deformed image of the structured light stripes projected by the scanning module onto each mineral;

[0014] Perform phase analysis on the deformed image based on the phase shift method to determine the phase distribution information on the mineral surface;

[0015] Generate the three-dimensional morphological information of the mineral based on triangulation, the baseline distance between the projection unit and the image acquisition unit in the scanning module, the projection angle and the imaging angle, and the phase distribution information on the mineral surface.

[0016] Further, when determining the elemental fingerprint of each mineral according to the short-wave infrared spectrum, it includes:

[0017] Project short-wave infrared light onto each mineral on the conveyor belt, and determine the spectral data of each mineral based on the reflected light on the surface of each mineral;

[0018] Extract the spectral characteristic information of the mineral based on the spectral absorption and reflection characteristics of the mineral;

[0019] Pre-establish a mineral spectral model, substitute the spectral characteristic information into the mineral spectral model, and determine the elemental fingerprint of the mineral.

[0020] Further, when pre-establishing a mineral spectral model, it includes:

[0021] Obtain the spectral data of each mineral, and establish an elemental correlation formula for each mineral according to the spectral data, where the spectral data includes spectral characteristics and the elemental type of the mineral;

[0022] Obtain the distance metric between each elemental correlation formula based on the Euclidean distance, and construct a distance matrix between each elemental correlation formula according to the distance metric;

[0023] Perform iterative clustering between each elemental correlation formula based on the distance matrix, and establish a mineral spectral model according to each elemental correlation formula after clustering.

[0024] Further, when establishing the morphological component characteristics of the mineral based on the mineral coordinates, it includes:

[0025] Obtain the three-dimensional coordinate information of each mineral on the conveyor belt, and determine the three-dimensional data of each mineral based on the three-dimensional morphological information of the mineral. Among them, the three-dimensional data includes the length-width ratio, sphericity, surface roughness, and volume of the mineral.

[0026] Match the element fingerprint of the mineral with the spatial coordinates of the mineral.

[0027] Based on the matching results, establish the morphological and compositional characteristics of each mineral on the conveyor belt.

[0028] Furthermore, when establishing the model of each mineral based on the three-dimensional morphology of each mineral, it includes:

[0029] Obtain the three-dimensional morphological characteristics of each mineral, and establish the three-dimensional point cloud data of each mineral based on the three-dimensional morphological characteristics.

[0030] Based on noise filtering, remove redundant points, noise points, and isolated points in the three-dimensional point cloud data of each mineral.

[0031] Based on the iterative closest point algorithm, align the point cloud data of each mineral from different perspectives or different times to generate the three-dimensional point cloud model of each mineral.

[0032] Furthermore, when determining the classification of each mineral and the specifications of each mineral on the conveyor belt based on the models of each mineral and the morphological and compositional characteristics of each mineral, it includes:

[0033] Based on the three-dimensional model of the mineral and the clustering algorithm, determine the morphological classification of the mineral.

[0034] According to the element fingerprint and morphological classification in the morphological and compositional characteristics of the mineral, determine the chemical composition classification of the mineral.

[0035] Based on the morphological classification and chemical composition classification of the mineral, based on the decision tree algorithm, determine the classification between each mineral on the conveyor belt, and according to the classification results, determine the specification classification and mineral composition classification of each mineral located on the conveyor belt.

[0036] Obtain the maximum value of the specification classification ratio and the maximum value of the mineral composition classification ratio between the specification classifications of the conveyor belt, and respectively determine the types of minerals with the maximum specification classification ratio and the types of minerals with the maximum mineral composition classification ratio as suspected minerals.

[0037] Furthermore, when screening each mineral based on the preset mineral types and mineral specifications and determining the minerals to be screened, it includes:

[0038] Obtain the mineral composition type and mineral specifications of the suspected mineral, and determine the minerals to be screened according to the relationship between the mineral composition type and mineral specifications of the suspected mineral and the preset mineral composition type and preset mineral specifications.

[0039] When the mineral composition type of the suspected mineral is consistent with the preset mineral composition type, and the mineral specification of the suspected mineral is less than or equal to the preset mineral specification, it is determined that the suspected mineral is not the mineral to be screened;

[0040] When the mineral specification of the suspected mineral is greater than the preset mineral specification, and / or the mineral composition type of the suspected mineral is inconsistent with the preset mineral composition type, it is determined that the suspected mineral is the mineral to be screened.

[0041] Further, when obtaining the grasping posture scores of each candidate mineral and determining the grasping order of each mineral to be screened, it includes:

[0042] Based on the three-dimensional model of the mineral to be screened, by calculating the surface normal vector, grasping surface shape and surface characteristics of the mineral to be screened, using the geometric feature scoring method, determine the initial grasping score of the mineral to be screened;

[0043] Conduct a simulated grasping of the mineral to be screened based on finite element analysis, and determine the grasping force distribution and generate a stability score based on the force conditions during the simulated grasping process;

[0044] Based on the relationship between the stability score and the configured first preset stability score and second preset stability score, determine the adjustment coefficient, and adjust the initial grasping score of the mineral to be screened according to the adjustment coefficient, where:

[0045] When the stability score is lower than or equal to the first preset stability score, it is determined that the adjustment coefficient is L3;

[0046] When the stability score is higher than the first preset stability score and lower than or equal to the second preset stability score, it is determined that the adjustment coefficient is L2;

[0047] When the stability score is higher than the second preset stability score, it is determined that the adjustment coefficient is L1;

[0048] Among them, the first preset stability score is less than the second preset stability score, and 0.8 < L1 < L2 < L3 < 1.2;

[0049] Determine the adjusted initial grasping score as the grasping score of the mineral to be screened, and determine the grasping order of each mineral to be screened based on the reverse order.

[0050] Compared with the prior art, the beneficial effects of the present invention are as follows: By using the scanning module to obtain the three-dimensional morphological information of the minerals on the conveyor belt, and combining the short-wave infrared spectroscopy technology to extract the elemental fingerprints of the minerals, and then establishing the morphological composition characteristics based on the coordinate information of the minerals. This method of combining morphological information and composition analysis greatly improves the accuracy of mineral identification compared with the traditional single image recognition or manual sorting methods, reduces the misjudgment problems caused by factors such as light changes and morphological complexity, and makes the mineral classification more refined. Secondly, by establishing the three-dimensional models of the minerals and combining the morphological composition characteristics to classify and determine the specifications of the minerals, the accuracy of mineral screening is improved. The traditional mineral screening methods usually rely on manual experience or simple rule judgments, while this method uses computer vision and spectral analysis technologies to accurately determine the types and specifications of the minerals, improves the automation degree of the screening process, reduces manual intervention, and reduces the screening error. At the same time, the three-dimensional modeling method can more comprehensively describe the spatial characteristics of the minerals, making the screening decision more scientific and reasonable. In addition, after the mineral screening is completed, by calculating the grasping posture scores of the minerals to be selected and determining the grasping order based on the score results, the optimal grasping strategy can be ensured for the robotic arm to execute, improving the stability and success rate of grasping. Compared with the traditional robotic arm grasping methods, this method not only considers the morphological characteristics of the minerals, but also combines factors such as grasping stability analysis and force calculation, enabling the robotic arm to still maintain efficient grasping in complex environments, effectively avoiding dropping or breaking caused by improper grasping angles or unstable clamping. Finally, through optimizing the grasping order and automatically generating grasping instructions, the intelligent control of the robotic arm is realized. By automatically planning the optimal grasping path based on the mineral classification information and grasping scores, the ineffective movements of the robotic arm are reduced, and the overall working efficiency is improved. Compared with the prior art, while improving the accuracy of mineral screening, it also reduces the energy consumption and time cost, enhances the intelligent level of the screening system, enables it to adapt to different mineral types and production requirements, and has high application value.

[0051] On the other hand, the present application also provides a mineral screening system based on a robotic arm, including:

[0052] A scanning module, configured to obtain the three-dimensional morphological information of each mineral on the conveyor belt, determine the elemental fingerprints of each mineral according to the short-wave infrared spectroscopy, and establish the morphological composition characteristics of the minerals based on the mineral coordinates;

[0053] A central control module, electrically connected to the scanning module, the central control module is configured to establish each mineral model according to the three-dimensional morphology of each mineral, and determine the classification and specifications of each mineral on the conveyor belt based on each mineral model and the morphological composition characteristics of each mineral; the central control module is further configured to screen each mineral based on the preset mineral types and mineral specifications, and determine the minerals to be screened;

[0054] An output module, electrically connected to the central control module, is configured to obtain the grasping attitude scores of each candidate mineral and determine the grasping order of each mineral to be screened according to the grasping attitude scores; the output module is further configured to generate a grasping instruction according to the grasping order and control the robotic arm to grasp each mineral to be screened according to the grasping instruction.

[0055] It can be understood that the robotic arm-based mineral screening system and method in the above embodiments of the present invention have the same beneficial effects and will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not to be considered as limiting the present invention. Also, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0057] Figure 1 is a flowchart of the robotic arm-based mineral screening method provided by an embodiment of the present invention;

[0058] Figure 2 is a functional block diagram of the robotic arm-based mineral screening system provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] Hereinafter, exemplary embodiments of the present disclosure will be described in more detail with reference to the drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art. It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. Hereinafter, the present invention will be described in detail with reference to the drawings and in combination with the embodiments.

[0060] As Figure 1 shown, in some embodiments of the present application, this embodiment provides a robotic arm-based mineral screening method, including:

[0061] Step S100: Obtain the three-dimensional morphological information of each mineral on the conveyor belt based on the scanning module, determine the elemental fingerprint of each mineral according to the short-wave infrared spectrum, and establish the morphological composition characteristics of the mineral based on the mineral coordinates.

[0062] Specifically, when obtaining the three-dimensional morphological information of each mineral on the conveyor belt based on the scanning module, it includes: obtaining the deformed images of the structured light stripes projected by the scanning module onto each mineral; performing phase analysis on the deformed images based on the phase-shift method to determine the phase distribution information on the mineral surface; generating the three-dimensional morphological information of the mineral based on triangulation, the baseline distance between the projection unit and the image acquisition unit in the scanning module, the projection angle and the imaging angle, and the phase distribution information on the mineral surface.

[0063] It can be understood that by projecting structured light stripes onto the mineral through the scanning module, the undulations on the mineral surface will cause deformation of the light stripes, and the deformed stripe images are obtained by the image acquisition unit. The key to this process is to ensure the uniform projection of the light stripes and that the image acquisition unit can accurately capture the deformed images for subsequent analysis of the height changes on the mineral surface. Secondly, in order to further analyze the morphological information on the mineral surface, phase analysis is performed on the deformed images by using the phase-shift method. The phase-shift method is a common optical measurement technique that calculates the phase distribution information of each pixel point by projecting structured light stripes with different phases multiple times. Specifically, by adjusting the phase of the projected light stripes and combining the brightness changes of multiple acquired images, the phase values of each point on the mineral surface are calculated, thereby obtaining the phase distribution information on the mineral surface. The phase distribution information can accurately reflect the height changes in each region of the object surface and is an important basis for subsequent three-dimensional reconstruction. After obtaining the phase distribution information, based on the principle of triangulation, combined with parameters such as the baseline distance between the projection unit and the image acquisition unit, the projection angle, and the imaging angle, the three-dimensional coordinates of each point on the mineral surface are calculated. The basic idea of triangulation is to calculate the depth (Z-direction coordinate) of the target point through the known baseline distance between two points and two angle information. By traversing all the measurement points on the mineral surface, the complete three-dimensional morphological information can be reconstructed, providing accurate morphological data support for subsequent mineral classification, screening, and grasping.

[0064] Specifically, when determining the elemental fingerprints of each mineral based on the short-wave infrared spectrum, it includes: projecting short-wave infrared light onto each mineral on the conveyor belt and determining the spectral data of each mineral based on the reflected light from the surface of each mineral; extracting the spectral characteristic information of the mineral based on the spectral absorption and reflection characteristics of the mineral; pre-establishing a mineral spectral model and substituting the spectral characteristic information into the mineral spectral model to determine the elemental fingerprints of the mineral.

[0065] Specifically, when establishing a mineral spectral model in advance, it includes: obtaining the spectral data of each mineral, and establishing the element correlation formula of each mineral based on the spectral data, wherein the spectral data includes the spectral characteristics and the element type of the mineral; obtaining the distance metric between each element correlation formula based on the Euclidean distance, and constructing the distance matrix between each element correlation formula based on the distance metric; iteratively clustering each element correlation formula based on the distance matrix, and establishing the mineral spectral model based on the clustered element correlation formulas.

[0066] It is understandable that by projecting short-wave infrared light onto the minerals on the conveyor belt, the absorption and reflection characteristics of the light on the surfaces of each mineral are different, resulting in the uniqueness of the spectral data of the reflected light. By collecting the reflected light data of the mineral through the spectral detection module, the spectral characteristic information of each mineral can be obtained, laying the foundation for the subsequent mineral identification. Secondly, after obtaining the spectral data of the mineral, the spectral characteristic information of the mineral can be extracted based on the spectral absorption and reflection characteristics. The spectral characteristics of the mineral are usually manifested as absorption peaks and reflection peaks in specific bands, and these peaks are closely related to the elemental composition of the mineral. By analyzing the morphology of the spectral curve, the position of the absorption peak, the reflectivity and other information, the composition characteristics of the mineral can be preliminarily determined. However, since different minerals may have similar spectral characteristics, it is necessary to further use the spectral modeling method to improve the accuracy of mineral identification. In addition, in order to achieve high-precision mineral element fingerprint recognition, a mineral spectral model needs to be established in advance. Obtain the spectral data of different minerals, and establish the elemental correlation formula of the mineral based on these data, that is, analyze the relationship between the spectral data and the mineral element type. Spectral data include the spectral characteristics of minerals (such as absorption peaks, reflectivity) and the corresponding element types. These data can be used to train mineral spectral models so that they can accurately match the element fingerprints of minerals. Finally, when constructing the spectral model, a method based on Euclidean distance is used to measure the similarity between different mineral element correlations. Euclidean distance is a common measurement method that can calculate the numerical differences between different spectral data, thereby quantifying the relative distance between each element correlation. By calculating the distance matrix between element correlations and performing iterative clustering based on the matrix, mineral categories with similar spectral characteristics can be found, and mineral spectral models can be constructed accordingly. Finally, the model can be used to match newly collected mineral spectral data, thereby accurately identifying the element fingerprints of minerals, providing a reliable basis for subsequent mineral screening and classification.

[0067] Specifically, when establishing the morphological composition characteristics of minerals based on mineral coordinates, it includes: obtaining the three-dimensional coordinate information of each mineral on the conveyor belt, and determining the three-dimensional data of each mineral based on the three-dimensional morphological information of the mineral, wherein the three-dimensional data includes the aspect ratio, sphericity, surface roughness and volume of the mineral; matching the elemental fingerprint of the mineral with the spatial coordinates of the mineral; and establishing the morphological composition characteristics of each mineral on the conveyor belt based on the matching results.

[0068] It is understandable that the three-dimensional coordinate information of minerals on the conveyor belt is obtained by using technologies such as structured light scanning or laser point cloud scanning, and the three-dimensional point cloud data of minerals is constructed based on these coordinates. Then, key geometric features of minerals, such as aspect ratio, sphericity, surface roughness, and volume, are extracted through point cloud processing techniques. These features can accurately reflect the physical morphology of minerals and provide important data support for subsequent analysis. After obtaining the three-dimensional morphological information of minerals, combined with the elemental fingerprint data of minerals, the compositional characteristics of minerals can be further analyzed. The elemental fingerprint of minerals is obtained through short-wave infrared spectroscopy analysis, which reflects the chemical composition of minerals. In order to establish the corresponding relationship between morphology and composition, it is necessary to match the three-dimensional coordinates of minerals with the elemental fingerprints obtained by spectral analysis. The matching process usually adopts spatial position mapping technology, that is, the elemental fingerprint data in the spectral detection area is made to correspond one by one with the three-dimensional coordinate information obtained by the scanning module, so as to ensure the accurate association of the morphological features and compositional information of each mineral. Finally, after the matching is completed, statistical analysis or machine learning methods can be used to comprehensively integrate the three-dimensional morphological features and elemental fingerprint information to establish a morphological and compositional feature library of minerals. This feature library contains the geometric morphological parameters and chemical composition information of each mineral, providing data support for mineral classification, screening, and grasping. In this way, not only can the accuracy of mineral identification be improved, but also minerals that meet the requirements can be screened according to morphological and compositional features during the actual screening process, improving the accuracy and efficiency of screening.

[0069] It can be seen that the three-dimensional morphological information of minerals is obtained through structured light scanning and phase-shift method, and a high-precision three-dimensional model of minerals is generated by combining the principle of triangulation. Compared with the traditional two-dimensional image recognition method, this solution can accurately obtain the geometric features of minerals, such as aspect ratio, sphericity, surface roughness, etc., thus greatly improving the accuracy of mineral morphology recognition and providing more reliable morphological data support for subsequent screening. In addition, by using short-wave infrared spectroscopy to analyze the element fingerprints of minerals, minerals with similar chemical compositions but different morphologies can be effectively distinguished, improving the accuracy of mineral screening. Secondly, by establishing a mineral spectral model and using Euclidean distance measurement and iterative clustering algorithm to analyze the element correlation formula, this solution can accurately establish a spectral feature classification system for different minerals. Traditional mineral screening methods usually rely on fixed element thresholds for determination, while this solution uses a data-driven method to make mineral composition analysis more intelligent and adaptive, and can dynamically adjust the classification criteria according to the changes in mineral spectra, improving the recognition ability in complex mineral mixing environments. In addition, the morphological and compositional characteristics of minerals are jointly established by three-dimensional coordinates, morphological data and element fingerprint information, enabling mineral classification to be determined based on comprehensive characteristics rather than relying on a single information source, thus improving the screening accuracy. Finally, in practical applications, this solution can realize the full automation of the mineral screening process, effectively reducing manual intervention and improving production efficiency. Traditional mineral screening methods often rely on manual screening or simple mechanical sorting, while this solution forms complete morphological-compositional feature data by obtaining the three-dimensional coordinates of minerals and matching them with element fingerprints, making the screening process more accurate and stable. At the same time, this method can adapt to different types of mineral screening requirements, improve the intelligent level of mineral sorting, help improve the overall screening efficiency, and reduce losses caused by misjudgment or operational errors.

[0070] Step S200: Establish models for each mineral according to the three-dimensional morphology of each mineral, and determine the classification and specifications of each mineral on the conveyor belt based on each mineral model and the morphological and compositional characteristics of each mineral.

[0071] Specifically, when establishing models for each mineral according to the three-dimensional morphology of each mineral, it includes: obtaining the three-dimensional morphological characteristics of each mineral, and establishing the three-dimensional point cloud data of each mineral based on the three-dimensional morphological characteristics; removing redundant points, noise points and isolated points in the three-dimensional point cloud data of each mineral based on noise filtering; aligning the point cloud data of each mineral from different perspectives or at different times based on the iterative closest point algorithm to generate the three-dimensional point cloud model of each mineral.

[0072] Specifically, when determining the classification and specifications of each mineral on the conveyor belt based on each mineral model and the morphological and compositional characteristics of each mineral, it includes: determining the morphological classification of the mineral based on the three-dimensional model of the mineral and the clustering algorithm; determining the chemical composition classification of the mineral according to the element fingerprint and morphological classification in the morphological and compositional characteristics of the mineral; based on the morphological classification and chemical composition classification of the mineral, determining the classification between each mineral on the conveyor belt based on the decision tree algorithm, and according to the classification result, determining the specification classification and mineral composition classification of each mineral located on the conveyor belt; obtaining the maximum value of the specification classification ratio and the maximum value of the mineral composition classification ratio between each specification classification of the conveyor belt, and respectively determining the mineral types with the maximum specification classification ratio and the mineral types with the maximum mineral composition classification ratio as the suspected minerals.

[0073] It can be understood that through the three-dimensional point cloud data processing technology, the three-dimensional morphology of the mineral is modeled. The obtained three-dimensional morphological characteristics are represented by point cloud data. Since point cloud data usually contains noise points, redundant points, and isolated points, it is necessary to use noise filtering algorithms to remove these interference data to ensure the accuracy of the mineral morphological data. Further, since there may be position deviations in the scan data of the mineral at different perspectives or different times, the iterative closest point (ICP) algorithm is used to register and align the point cloud data to ensure that the finally generated three-dimensional point cloud model of the mineral can completely and accurately express the morphological characteristics of the mineral. Based on the constructed three-dimensional model of the mineral, morphological classification is carried out in combination with the clustering algorithm. Since the morphological characteristics of the mineral are similar, the clustering algorithm (such as K-means or DBSCAN) can be used to classify the three-dimensional morphological characteristics of the mineral and determine its morphological category. In addition, since the mineral not only has geometric morphological characteristics but also contains different element composition characteristics, the spectral data of the mineral is further combined to extract the element fingerprint information, and chemical composition classification is carried out through spectral clustering methods. In this way, more accurate classification of the mineral can be carried out based on the morphological characteristics and element fingerprints. Based on the morphological classification and chemical composition classification of the mineral, the decision tree algorithm is used to further optimize the mineral classification process. The decision tree algorithm can establish classification rules based on the morphological category and chemical composition category of the mineral, so as to automatically determine the final category of each mineral. In addition, in order to determine the specification classification of the mineral, this technical solution calculates the ratio of each specification category, identifies the mineral type with the highest ratio, and determines it as the suspected mineral to ensure efficient classification for the main mineral types during the mineral screening process. This mineral classification method based on multi-dimensional data fusion improves the accuracy and reliability of the screening.

[0074] It can be seen that by modeling the three-dimensional morphological characteristics of minerals, the accurate acquisition and processing of mineral morphological data are realized. By obtaining the three-dimensional morphological characteristics of minerals and generating three-dimensional point cloud data, and combining noise filtering and the Iterative Closest Point (ICP) algorithm to align the point cloud data collected from different perspectives and times, redundant points, noise points, and isolated points can be effectively removed, and an accurate three-dimensional point cloud model can be generated, ensuring the high precision and stability of mineral morphological data. This provides a reliable data basis for subsequent mineral classification and screening. Secondly, by combining the clustering algorithm to classify the morphology of the three-dimensional model of minerals, this solution can conduct preliminary screening based on the geometric morphological characteristics of minerals, and further classify the chemical composition of minerals by combining element fingerprint analysis. This classification method that combines the morphological characteristics and chemical composition characteristics of minerals greatly improves the accuracy and effectiveness of mineral classification and avoids the limitations of traditional methods that rely only on a single feature for classification. Finally, by using the decision tree algorithm to comprehensively classify minerals, based on the results of morphological classification and chemical composition classification, the specification classification and composition classification of minerals on the conveyor belt can be automatically determined. By calculating the maximum proportion of each specification classification and mineral composition classification and determining it as a suspected mineral,

[0075] Step S300: Screen each mineral based on the preset mineral types and mineral specifications, and determine the minerals to be screened.

[0076] Specifically, when screening each mineral based on the preset mineral types and mineral specifications and determining the minerals to be screened, it includes: obtaining the mineral composition type and mineral specification of the suspected mineral, and determining the minerals to be screened according to the relationship between the mineral composition type and mineral specification of the suspected mineral and the preset mineral composition type and preset mineral specification; when the mineral composition type of the suspected mineral is consistent with the preset mineral composition type and the mineral specification of the suspected mineral is less than or equal to the preset mineral specification, it is determined that the suspected mineral is not a mineral to be screened; when the mineral specification of the suspected mineral is greater than the preset mineral specification and / or the mineral composition type of the suspected mineral is inconsistent with the preset mineral composition type, it is determined that the suspected mineral is a mineral to be screened.

[0077] It can be understood that whether a suspected mineral is taken as an object to be screened is determined by comparing the mineral composition type and specifications. First, obtain the composition type and specification information of the suspected mineral, and then compare it with the preset mineral composition type and specifications to establish the relationship between the two. In this way, the preliminary screening of the suspected mineral can be realized, effectively reducing the minerals that do not meet the screening conditions from entering the subsequent processing stage. Secondly, through the rule for judging the consistency of mineral specifications and composition types: when the mineral composition type of the suspected mineral is the same as the preset mineral composition type and the mineral specification is less than or equal to the preset specification, the suspected mineral does not need to be screened, which helps to reduce the misjudgment probability in the screening process and improve the screening efficiency. On the contrary, when the mineral specification of the suspected mineral is greater than the preset specification or the mineral composition type is inconsistent, it needs to be determined as a mineral to be screened. Finally, through the establishment of a comparison mechanism between the mineral composition type and the specifications, the precise screening of the minerals is realized. The setting of the matching rules ensures that only the minerals that meet specific conditions are selected, avoiding the minerals that do not meet the requirements from entering the screening process. This principle not only optimizes the screening efficiency but also reduces the risks of misselection or omission, improving the overall accuracy and reliability of mineral screening.

[0078] Step S400: Obtain the grasping posture scores of each candidate mineral, and determine the grasping order of each mineral to be screened according to the grasping posture scores.

[0079] Specifically, when obtaining the grasping posture scores of each candidate mineral and determining the grasping order of each mineral to be screened according to the grasping posture scores, it includes: based on the three-dimensional model of the mineral to be screened, by calculating the surface normal vector, grasping surface shape and surface features of the mineral to be screened, using the geometric feature scoring method to determine the initial grasping score of the mineral to be screened; performing simulated grasping on the mineral to be screened based on finite element analysis, and determining the grasping force distribution and generating a stability score based on the force condition during the simulated grasping process; based on the relationship between the stability score and the configured first preset stability score and second preset stability score, determining an adjustment coefficient, and adjusting the initial grasping score of the mineral to be screened according to the adjustment coefficient, where: when the stability score is lower than or equal to the first preset stability score, the adjustment coefficient is determined to be L3; when the stability score is higher than the first preset stability score and lower than or equal to the second preset stability score, the adjustment coefficient is determined to be L2; when the stability score is higher than the second preset stability score, the adjustment coefficient is determined to be L1; where the first preset stability score is less than the second preset stability score, and 0.8 < L1 < L2 < L3 < 1.2; determining the adjusted initial grasping score as the grasping score of the mineral to be screened, and determining the grasping order of each mineral to be screened based on the reverse order.

[0080] It can be understood that by calculating the surface normal vectors, grasping surface shapes, and surface features of the three-dimensional models of the minerals, a geometric feature scoring method is used to conduct a preliminary grasping score for the minerals to be screened. This score evaluates the feasibility of grasping based on the geometric characteristics of the mineral surfaces, providing basic data for determining the subsequent grasping order. Secondly, combined with finite element analysis, simulated grasping is carried out to evaluate the force conditions of the minerals to be screened during the grasping process. By simulating the mechanical properties of the mineral surfaces during the grasping process, the grasping force distribution is obtained and a stability score is generated. This step ensures whether the minerals are stable during the grasping process through mechanical simulation, thus avoiding problems such as slipping or deformation during actual operation. The level of the stability score directly affects the feasibility and accuracy of grasping. Therefore, it is a key factor determining the grasping order of the minerals. Finally, based on the relationship between the stability score and the preset first and second stability scores, an adjustment coefficient is determined. Through this coefficient, the initial grasping score is dynamically adjusted to improve the stability and accuracy of the grasping operation. When the stability score is low, the adjustment coefficient is large and the grasping score is low; conversely, when the stability score is high, the adjustment coefficient is small and the grasping score is high. Finally, based on the adjusted grasping scores, the minerals to be screened are arranged in reverse order to ensure that minerals with higher stability are grasped first. This method effectively optimizes the grasping strategy for mineral screening and improves the safety and efficiency of the grasping operation.

[0081] Step S500: Generate a grasping instruction according to the grasping order, and control the robotic arm to grasp each mineral to be screened according to the grasping instruction.

[0082] In the above embodiments, the three-dimensional morphological information of the minerals on the conveyor belt is obtained by using the scanning module, and the elemental fingerprints of the minerals are extracted by combining the short-wave infrared spectroscopy technology. Then, the morphological composition features are established based on the coordinate information of the minerals. This method of combining morphological information and compositional analysis greatly improves the accuracy of mineral identification compared with the traditional single image recognition or manual sorting methods, reduces the misjudgment problems caused by factors such as light changes and morphological complexity, and makes the mineral classification more refined. Secondly, by establishing a three-dimensional model of the minerals and classifying and determining the specifications of the minerals in combination with the morphological composition features, the accuracy of mineral screening is improved. The traditional mineral screening methods usually rely on manual experience or simple rule judgments, while this method can accurately determine the types and specifications of minerals by means of computer vision and spectroscopy analysis technology, improve the automation degree of the screening process, reduce manual intervention, and reduce the screening error. At the same time, the three-dimensional modeling method can more comprehensively describe the spatial characteristics of the minerals, making the screening decision more scientific and reasonable. In addition, after the mineral screening is completed, by calculating the grasping posture scores of the minerals to be selected and determining the grasping order based on the score results, the optimal grasping strategy can be ensured for the robotic arm to execute, improving the stability and success rate of grasping. Compared with the traditional robotic arm grasping methods, this method not only considers the morphological characteristics of the minerals, but also combines factors such as grasping stability analysis and force calculation, enabling the robotic arm to still maintain efficient grasping in complex environments and effectively avoiding dropping or damage caused by improper grasping angles or unstable clamping. Finally, through the optimization of the grasping order and the automatic generation of grasping instructions, the intelligent control of the robotic arm is realized. By automatically planning the optimal grasping path according to the mineral classification information and grasping scores, the ineffective movements of the robotic arm are reduced, and the overall working efficiency is improved. Compared with the existing technologies, while improving the accuracy of mineral screening, it also reduces the energy consumption and time costs, enhances the intelligent level of the screening system, enables it to adapt to different mineral types and production requirements, and has high application value.

[0083] In another preferred embodiment based on the above embodiments, as Figure 2 shown, this embodiment provides a mineral screening system based on a robotic arm, including: a scanning module, a central control module, and an output module.

[0084] Specifically, the scanning module is configured to obtain the three-dimensional morphological information of each mineral on the conveyor belt, determine the elemental fingerprint of each mineral based on the short-wave infrared spectrum, and establish the morphological and compositional characteristics of the minerals based on the mineral coordinates; the central control module is electrically connected to the scanning module, and the central control module is configured to establish each mineral model based on the three-dimensional morphology of each mineral, and determine the classification and specifications of each mineral on the conveyor belt based on each mineral model and the morphological and compositional characteristics of each mineral; the central control module is further configured to screen each mineral based on the preset mineral types and specifications, and determine the minerals to be screened; the output module is electrically connected to the central control module, and the output module is configured to obtain the grasping attitude scores of each candidate mineral, and determine the grasping order of each mineral to be screened according to the grasping attitude scores; the output module is further configured to generate a grasping instruction according to the grasping order, and control the robotic arm to grasp each mineral to be screened according to the grasping instruction.

[0085] It can be understood that the mineral screening system and method based on the robotic arm in the above embodiments of the present invention have the same beneficial effects and will not be elaborated herein.

[0086] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0087] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the specified function in Figure 1 one or more flows or multiple flows and / or blocks Figure 1 one or more blocks or multiple blocks.

[0088] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured product including an instruction device, and the instruction device implements the specified function in Figure 1 one or more flows or multiple flows and / or blocks Figure 1The functions specified in one or more boxes.

[0089] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide for implementing the steps of the functions specified in Figure 1 one process or more processes and / or boxes Figure 1 the functions specified in one box or more boxes.

[0090] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications or equivalent replacements can still be made to the specific implementation manners of the present invention. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. A mineral screening method based on a robotic arm, characterized in that: include: The scanning module is used to obtain the three-dimensional morphological information of each mineral on the conveyor belt, and the element fingerprint of each mineral is determined based on the short-wave infrared spectrum, and the morphological composition characteristics of the mineral are established based on the mineral coordinates; Establish each mineral model according to the three-dimensional morphology of each mineral, and determine the classification and specifications of each mineral on the conveyor belt based on each mineral model and the morphological composition characteristics of each mineral; Screening each mineral based on the preset mineral type and mineral specifications, and determining the minerals to be screened; Obtaining the grasping posture score of each mineral to be selected, and determining the grasping order of each mineral to be screened according to the grasping posture score; According to the grabbing sequence, a grabbing instruction is generated, and the robotic arm is controlled to grab each mineral to be screened according to the grabbing instruction.

2. The mineral screening method based on a robotic arm according to claim 1, characterized in that: When the scanning module is used to obtain the three-dimensional morphological information of each mineral on the conveyor belt, it includes: Obtain a deformed image of the structured light stripes projected by the scanning module onto each mineral; Perform phase analysis on the deformation image based on the phase shift method to determine the phase distribution information on the mineral surface; The three-dimensional morphological information of the mineral is generated based on triangulation, the baseline distance between the projection unit and the image acquisition unit in the scanning module, the projection angle and the imaging angle, and the phase distribution information of the mineral surface.

3. The mineral screening method based on a robotic arm as claimed in claim 2, characterized in that: When determining the elemental fingerprint of each mineral based on short-wave infrared spectroscopy, it includes: Project short-wave infrared light onto each mineral on the conveyor belt, and determine the spectral data of each mineral based on the reflected light from the surface of each mineral; Extract the spectral characteristic information of minerals based on their spectral absorption and reflection characteristics; A mineral spectrum model is established in advance, and the spectral feature information is substituted into the mineral spectrum model to determine the element fingerprint of the mineral.

4. The mineral screening method based on a robotic arm as claimed in claim 3, characterized in that: When pre-building a mineral spectrum model, include: Acquire spectral data of each mineral, and establish element correlation equations of each mineral based on the spectral data, wherein the spectral data includes spectral characteristics and element types of the mineral; Obtain the distance metric between the association equations of each element based on the Euclidean distance, and construct the distance matrix between the association equations of each element based on the distance metric; The correlation equations of each element are iteratively clustered based on the distance matrix, and the mineral spectrum model is established according to the correlation equations of each element after clustering.

5. The mineral screening method based on a robotic arm as claimed in claim 4, characterized in that: When establishing the morphological composition characteristics of minerals based on mineral coordinates, it includes: Obtaining the three-dimensional coordinate information of each mineral on the conveyor belt, and determining the three-dimensional data of each mineral based on the three-dimensional morphological information of the mineral, wherein the three-dimensional data includes the aspect ratio, sphericity, surface roughness and volume of the mineral; Match the mineral's elemental fingerprint with the mineral's spatial coordinates; Based on the matching results, the morphological composition characteristics of each mineral on the transport belt are established.

6. The mineral screening method based on a robotic arm according to claim 1, characterized in that: When establishing each mineral model according to the three-dimensional morphology of each mineral, it includes: Obtaining the three-dimensional morphological features of each mineral, and establishing three-dimensional point cloud data of each mineral based on the three-dimensional morphological features; Based on noise filtering, redundant points, noise points and isolated points in the three-dimensional point cloud data of each mineral are removed; Based on the iterative closest point algorithm, the point cloud data of each mineral from different perspectives or at different times are aligned to generate a three-dimensional point cloud model of each mineral.

7. The mineral screening method based on a robotic arm as claimed in claim 6, characterized in that: Based on the mineral models and the morphological composition characteristics of each mineral, the classification and specifications of each mineral on the conveyor belt are determined, including: Determine the morphological classification of minerals based on the three-dimensional model and clustering algorithm of minerals; Determine the chemical composition classification of minerals based on the element fingerprints and morphological classification in the morphological composition characteristics of minerals; Based on the morphological classification and chemical composition classification of minerals and the decision tree algorithm, the classification of minerals on the conveyor belt is determined, and according to the classification results, the specification classification and mineral composition classification of each mineral on the conveyor belt are determined; The maximum value of the specification classification ratio and the maximum value of the mineral composition classification ratio among each specification classification in the conveyor belt are obtained, and the mineral type with the maximum value of the specification classification ratio and the mineral type with the maximum value of the mineral composition classification ratio are respectively determined as suspected minerals.

8. The mineral screening method based on a robotic arm as claimed in claim 7, characterized in that: Screening of minerals based on preset mineral types and mineral specifications, and determination of minerals to be screened include: Obtaining the mineral component type and mineral specification of the suspected mineral, and determining the mineral to be screened according to the relationship between the mineral component type and mineral specification of the suspected mineral and the preset mineral component type and preset mineral specification; When the mineral component type of the suspected mineral is consistent with the preset mineral component type, and the mineral specification of the suspected mineral is less than or equal to the preset mineral specification, it is determined that the suspected mineral is not the mineral to be screened; When the mineral specifications of the suspected mineral are greater than the preset mineral specifications, and / or the mineral component type of the suspected mineral is inconsistent with the preset mineral component type, the suspected mineral is determined to be the mineral to be screened.

9. The mineral screening method based on a robotic arm according to claim 1, characterized in that: Obtaining the grasping posture score of each mineral to be selected and determining the grasping order of each mineral to be screened according to the grasping posture score includes: Based on the three-dimensional model of the mineral to be screened, the initial grabbing score of the mineral to be screened is determined by calculating the surface normal vector, grabbing surface shape and surface features of the mineral to be screened, and using the geometric feature scoring method; Based on finite element analysis, simulate the grasping of the minerals to be screened, and determine the grasping force distribution and generate a stability score based on the force conditions during the simulated grasping process; Based on the relationship between the stability score and the configured first preset stability score and the second preset stability score, an adjustment coefficient is determined, and the initial grab score of the mineral to be screened is adjusted according to the adjustment coefficient, wherein: When the stability score is lower than or equal to the first preset stability score, the adjustment coefficient is determined to be L3; When the stability score is higher than the first preset stability score and the stability score is lower than or equal to the second preset stability score, the adjustment coefficient is determined to be L2; When the stability score is higher than the second preset stability score, the adjustment coefficient is determined to be L1; wherein the first preset stability score is less than the second preset stability score, and 0.8<L1<L2<L3<1.2; The adjusted initial grab score is determined as the grab score of the mineral to be screened, and the grab order of each mineral to be screened is determined based on the reverse order.

10. A mineral screening system based on a robotic arm, applicable to a mineral screening method based on a robotic arm as claimed in any one of claims 1 to 9, characterized in that: include: A scanning module is configured to obtain three-dimensional morphological information of each mineral on the conveyor belt, determine the element fingerprint of each mineral according to the short-wave infrared spectrum, and establish the morphological composition characteristics of the mineral based on the mineral coordinates; The central control module is electrically connected to the scanning module, and is configured to establish each mineral model according to the three-dimensional morphology of each mineral, and determine the classification and specification of each mineral on the conveyor belt based on each mineral model and the morphological composition characteristics of each mineral; the central control module is also configured to screen each mineral based on the preset mineral type and mineral specification, and determine the mineral to be screened; The output module is electrically connected to the central control module. The output module is configured to obtain the grasping posture score of each mineral to be selected, and determine the grasping order of each mineral to be screened according to the grasping posture score; the output module is also configured to generate a grasping instruction according to the grasping order, and control the robotic arm to grasp each mineral to be screened according to the grasping instruction.

Images