Intelligent beneficiation method and device based on machine vision technology

Abstract

The invention relates to the technical field of ore processing, and discloses an intelligent beneficiation method and device based on a machine vision technology. The method comprises the steps of collecting an ore map in real time by using an image collector; identifying the ore map, and determining an ore boundary in the ore map; identifying position information of a plurality of ore separators in the ore map, and determining an adjustment line according to the position information of each ore separator; acquiring an intersection point of the ore boundary line and the adjustment line; according to the intersection point and the position information of each ore separator, in combination with a preset deviation distance corresponding to each ore separator, determining an adjustment mode of each ore separator; and each ore separator is controlled to be adjusted to the corresponding target position through the corresponding adjustment mode. The position of the target ore is recognized in real time through the machine vision technology, the position and direction of the ore separator are automatically adjusted, full-automatic ore screening is achieved, when the type or grade of the ore changes, human intervention is not needed, the working efficiency is improved, and therefore the recognition accuracy of the target ore is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of ore processing, and in particular to an intelligent ore dressing method and device based on machine vision technology. Background Art

[0002] Due to the shortage of mineral resources (iron ore and nonferrous ore) in the industrial chain, the intensity of mineral mining has increased, and high-grade mineral resources are becoming increasingly scarce, so the requirements for existing mineral processing technology are also becoming higher and higher.

[0003] At present, intelligent mineral processing technologies mainly include solid ore screening technology based on vision and gas injection, and solid ore pre-selection technology based on X-ray detection. At present, for the ore pulp formed by dissolving in water after crushing and grinding, traditional slurry screening technologies are still used, such as magnetic separation, chute, shaking table, centrifugal separation, vibrating screen, screening machine, blanket machine, ore washing machine, etc. In these ore screening processes and the final waste disposal process, equal division or manual adjustment or manual setting of the ore separator position are adopted. However, when adopting this method of equal division, manual adjustment or manual setting, manual intervention is required every time the type or taste of the ore changes, and real-time online adjustment cannot be achieved, and its production efficiency and ore quality are difficult to further improve. Summary of the invention

[0004] The present invention provides an intelligent ore dressing method and device based on machine vision technology, which can realize fully automatic ore screening. When the type or grade of the ore changes, no human intervention is required, which improves work efficiency and thus improves the recognition accuracy of the target ore.

[0005] In order to solve the above technical problems, the present invention provides an intelligent mineral processing method based on machine vision technology, comprising:

[0006] Use image collector to collect ore map in real time;

[0007] Identify the ore map and determine an ore boundary line in the ore map; wherein the ore boundary line is used to distinguish target ore from non-target ore;

[0008] Identifying the position information of a plurality of ore separators in the ore map, and determining an adjustment line according to the position information of each ore separator;

[0009] Obtaining the intersection point of the ore boundary line and the adjustment line;

[0010] Determine the adjustment method of each of the ore separators according to the intersection point and the position information of each of the ore separators, combined with the preset deviation distance corresponding to each of the ore separators;

[0011] Control each of the ore separators to adjust to a corresponding target position through a corresponding adjustment method.

[0012] Further, the ore map is identified and the ore boundary line is determined in the ore map, specifically:

[0013] Performing image equalization on the ore map, determining a range of target colors in the ore map, and determining an ore boundary line in combination with a preset minimum color band width; wherein the target colors include preset target ore colors and non-target ore colors;

[0014] Alternatively, edge detection is performed on the ore map based on an edge detection algorithm, and the ore boundary line is determined according to the edge detection result; wherein the edge detection result includes the target ore edge and the non-target ore edge;

[0015] Alternatively, boundary line detection is performed on the ore map based on a first target detection algorithm, and the ore boundary line is determined according to the boundary line detection result.

[0016] Further, the ore separator is a movable ore separator slot, the position information is the position coordinates of the ore separator, the position information of several ore separators is identified in the ore map, and the adjustment line is determined according to the position information of each ore separator, specifically:

[0017] Based on the second target detection algorithm, ore separators are identified in the ore map to obtain position coordinates of several ore separators;

[0018] An adjustment line is determined based on the position coordinates of each of the separators.

[0019] Further, the ore separator is a rotating arm, the position information is the coordinates of the rotating fulcrum of the ore separator, the position information of several ore separators is identified in the ore map, and the adjustment line is determined according to the position information of each ore separator, specifically:

[0020] Based on the second target detection algorithm, the ore separator is identified in the ore map to obtain the coordinates of the rotation fulcrums of several ore separators;

[0021] The adjustment line is determined based on the coordinates of the rotation fulcrum of each of the separators.

[0022] Further, the obtaining of the intersection point of the ore boundary line and the adjustment line is specifically as follows:

[0023] Acquire a plurality of boundary line coordinates on the ore boundary line;

[0024] Perform straight line fitting based on the coordinates of each dividing line, and determine the fitted straight line as the dividing line fitting straight line;

[0025] The intersection point of the boundary line fitting straight line and the adjustment line is determined as the intersection point of the ore boundary line and the adjustment line.

[0026] Furthermore, the coordinates of several boundary lines are obtained on the ore boundary line, specifically:

[0027] Acquire the coordinates of all points on the ore boundary line identified in the ore map, and determine the coordinates of all points on the ore boundary line as boundary line coordinates;

[0028] Alternatively, according to a preset end determination method, a boundary line end range is determined on the ore boundary line, a plurality of end coordinates are obtained within the boundary line end range, and the plurality of end coordinates are determined as boundary line coordinates;

[0029] Alternatively, inflection points are identified on the ore boundary line, the terminal direction of the ore boundary line is determined according to a preset terminal determination method, the inflection point closest to the terminal direction of the ore boundary line is determined as the terminal inflection point, and the coordinates of all points identified along the terminal direction of the ore boundary line are determined as boundary line coordinates.

[0030] Further, when the ore separator is a movable ore separator slot, the adjustment method of each ore separator is determined according to the intersection point, the position information of each ore separator, and the preset deviation distance corresponding to each ore separator, specifically:

[0031] Obtaining the coordinates of the intersection points on the ore map;

[0032] According to the intersection point coordinates, combined with the preset deviation distance corresponding to each of the ore separators, the target position coordinates corresponding to each of the ore separators are obtained;

[0033] The adjustment method of each ore separator is determined to be that each ore separator moves along the adjustment line to the target position coordinate.

[0034] Furthermore, when the ore separator is a rotating arm, the adjustment mode of each ore separator is determined according to the intersection point, the position information of each ore separator, and the preset deviation distance corresponding to each ore separator, specifically:

[0035] The coordinates of the intersection point, the coordinates of the rotation fulcrum of each of the ore dividers and the effective arm length, the first angle and the second angle are respectively obtained on the ore map; the first angle is the angle between the ore boundary line and the adjustment line; the second angle is the angle between each of the ore dividers and the adjustment line;

[0036] In combination with the preset deviation distance corresponding to each of the ore separators, construct an auxiliary line corresponding to each of the ore separators and parallel to the ore boundary line;

[0037] An auxiliary circle of each ore separator is constructed with the effective arm length of each ore separator as the radius and the rotation fulcrum as the center;

[0038] Determining the target position of the end of the rotating arm of each of the ore separators at two intersection points of the auxiliary line and the auxiliary circle;

[0039] Determine a target angle of a target angle between each of the ore separators and the adjustment line according to the intersection point coordinates, the rotation fulcrum coordinates of each of the ore separators, the effective arm length, and the first angle;

[0040] Calculating the rotation angle of each of the ore separators according to the second angle and the target angle;

[0041] The adjustment method of each ore separator is determined as rotating each ore separator by the rotation angle so that the end of the rotating arm of each ore separator is at the target position of the end of the rotating arm.

[0042] Further, the target angle of the target angle between each of the ore separators and the adjustment line is determined according to the intersection point coordinates, the rotation fulcrum coordinates of each of the ore separators, the effective arm length, and the first angle, specifically:

[0043] Calculate a first distance between each of the ore separators and the intersection point according to the intersection point coordinates and the rotation fulcrum coordinates of each of the ore separators;

[0044] Determine the intersection point between the auxiliary line and the adjustment line as the auxiliary intersection point of each of the ore separators;

[0045] Calculate the second distance between each of the ore separators and the auxiliary intersection point according to the first distance between each of the ore separators and the intersection point and a preset deviation distance corresponding to each of the ore separators;

[0046] Using the sine theorem, according to the effective arm length of each of the ore separators, the first angle and the second distance, the third angle between the target line segment and the auxiliary line is calculated; wherein the target line segment is a line segment formed by connecting the target position at the end of the rotating arm of each of the ore separators and the rotating fulcrum;

[0047] The target angle of the target angle between each of the separators and the adjustment line is obtained by calculating the first angle and the third angle using the triangle interior angle theorem.

[0048] The present invention provides an intelligent ore dressing method based on machine vision technology, which uses an image collector to collect ore maps in real time; identifies the ore maps and determines the ore boundary line in the ore maps; identifies the position information of several separators in the ore maps, and determines the adjustment line according to the position information of each separator; obtains the intersection point of the ore boundary line and the adjustment line; determines the adjustment method of each separator according to the intersection point and the position information of each separator, combined with the preset deviation distance corresponding to each separator; controls each separator to adjust to the corresponding target position through the corresponding adjustment method. The present invention uses machine vision technology to identify the position of the target ore in real time, automatically adjusts the position and direction of the separator, and realizes fully automatic ore screening. When the type or taste of the ore changes, no human intervention is required, which improves work efficiency and thus improves the recognition accuracy of the target ore.

[0049] Accordingly, the present invention provides an intelligent mineral processing device based on machine vision technology, comprising: a collection module, a boundary line determination module, an adjustment line determination module, an intersection point acquisition module, an adjustment mode determination module and a control module;

[0050] The acquisition module is used to acquire ore images in real time using an image collector;

[0051] The boundary determination module is used to identify the ore map and determine the ore boundary in the ore map; wherein the ore boundary is used to distinguish target ore from non-target ore;

[0052] The adjustment line determination module is used to identify the position information of a plurality of ore separators in the ore map, and determine the adjustment line according to the position information of each ore separator;

[0053] The intersection point acquisition module is used to obtain the intersection point of the ore boundary line and the adjustment line;

[0054] The adjustment mode determination module is used to determine the adjustment mode of each of the ore separators according to the intersection point and the position information of each of the ore separators, combined with the preset deviation distance corresponding to each of the ore separators;

[0055] The control module is used to control each of the ore separators to be adjusted to a corresponding target position through a corresponding adjustment method.

[0056] The present invention provides an intelligent mineral processing device based on machine vision technology. Based on the organic combination of modules, an image collector is used to collect ore maps in real time; the ore maps are identified, and the ore boundary lines are determined in the ore maps; the position information of several separators is identified in the ore maps, and the adjustment lines are determined according to the position information of each separator; the intersection point of the ore boundary line and the adjustment line is obtained; the adjustment method of each separator is determined according to the intersection point and the position information of each separator, combined with the preset deviation distance corresponding to each separator; each separator is controlled to be adjusted to the corresponding target position through the corresponding adjustment method. The present invention uses machine vision technology to identify the position of the target ore in real time, automatically adjust the position and direction of the separator, and realize fully automatic ore screening. When the type or taste of the ore changes, no human intervention is required, which improves work efficiency and thus improves the recognition accuracy of the target ore. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 A schematic diagram of a process flow of an embodiment of an intelligent ore dressing method based on machine vision technology provided by the present invention;

[0058] Figure 2 A schematic diagram of a method for obtaining boundary line coordinates provided by the present invention;

[0059] Figure 3 Another schematic diagram of the method for obtaining the boundary line coordinates provided by the present invention;

[0060] Figure 4 Another schematic diagram of the method for obtaining the boundary line coordinates provided by the present invention;

[0061] Figure 5 A schematic diagram of the rotating arm adjustment method provided by the present invention;

[0062] Figure 6 A schematic structural diagram of an embodiment of an intelligent ore dressing device based on machine vision technology provided by the present invention. DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0065] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0066] Example 1

[0067] See also Figure 1 , is a flow chart of an embodiment of an intelligent ore dressing method based on machine vision technology provided by the present invention, the method includes steps 101 to 106, each step is specifically as follows:

[0068] Step 101: Use an image collector to collect ore images in real time.

[0069] In the first embodiment of the present invention, an image collector such as a camera is used to collect an ore map in real time on the ore dressing equipment during the ore screening or waste disposal process. The ore map includes concentrate and waste, as well as multiple separators for classifying the ore.

[0070] Step 102: Identify the ore map and determine an ore boundary line in the ore map; wherein the ore boundary line is used to distinguish target ore from non-target ore.

[0071] Furthermore, in the first embodiment of the present invention, the ore map is identified, and the ore boundary line is determined in the ore map, specifically:

[0072] Performing image equalization on the ore map, determining a range of target colors in the ore map, and determining an ore boundary line in combination with a preset minimum color band width; wherein the target colors include preset target ore colors and non-target ore colors;

[0073] Alternatively, edge detection is performed on the ore map based on an edge detection algorithm, and the ore boundary line is determined according to the edge detection result; wherein the edge detection result includes the target ore edge and the non-target ore edge;

[0074] Alternatively, boundary line detection is performed on the ore map based on a first target detection algorithm, and the ore boundary line is determined according to the boundary line detection result.

[0075] In the first embodiment of the present invention, determining the ore boundary line in the ore map can be achieved by different algorithms. For example, the boundary line can be determined based on color difference or contrast, and the ore map is equalized. At this time, different colors are displayed in the ore map. By presetting the colors of the target ore and the non-target ore, the different colors in the ore map are identified and classified, and the boundary lines of different colors are obtained. The width of the ore boundary line is determined based on the preset minimum color band width, thereby determining the ore boundary line. For another example, the ore map is edge detected based on the edge detection algorithm, the edges of the target ore and the non-target ore are identified, and the ore boundary line is determined by combining the two edges. Among them, the edge detection algorithm includes a first-order detection operator and a second-order detection operator, and the specific operators include a horizontal difference operator, a vertical difference operator, a Roberts cross operator, a Prewi tt edge detection operator, a Sobel edge detection operator, a Canny edge detection operator, a Laplacian operator, etc. For another example, the ore map is subjected to boundary line target detection based on the target detection algorithm, and the detection result is determined as the ore boundary line. Among them, the target detection algorithms include R-CNN algorithm, Faster R-CNN algorithm, YOLO series algorithms, and SSD algorithm.

[0076] Step 103: Identify the position information of a plurality of ore separators in the ore map, and determine an adjustment line according to the position information of each ore separator.

[0077] Further, in the first embodiment of the present invention, when the ore separator is a movable ore separator slot, the position information is the position coordinates of the ore separator, the position information of several ore separators is identified in the ore map, and the adjustment line is determined according to the position information of each ore separator, specifically:

[0078] Based on the second target detection algorithm, ore separators are identified in the ore map to obtain position coordinates of several ore separators;

[0079] An adjustment line is determined based on the position coordinates of each of the separators.

[0080] Further, in the first embodiment of the present invention, when the ore separator is a rotating arm, the position information is the coordinates of the rotating fulcrum of the ore separator, the position information of several ore separators is identified in the ore map, and the adjustment line is determined according to the position information of each ore separator, specifically:

[0081] Based on the second target detection algorithm, the ore separator is identified in the ore map to obtain the coordinates of the rotation fulcrums of several ore separators;

[0082] The adjustment line is determined based on the coordinates of the rotation fulcrum of each of the separators.

[0083] In the first embodiment of the present invention, the ore separator includes two types, one of which is a movable ore separator slot. In the ore map, the ore separator slot is identified based on the second target detection algorithm that completes the pre-training of the ore separator, and the position coordinates of the ore separator slot can be collected. The adjustment line can be obtained by connecting the position coordinates of each ore separator slot. Another type of ore separator is a rotating arm. The rotating arm is identified based on the second target detection algorithm that completes the pre-training of the ore separator, and the rotation fulcrum coordinates of the rotating arm can be collected. The adjustment line can be obtained by connecting the rotation fulcrum coordinates of each ore separator slot. The present invention can effectively improve the accuracy of the data and the rate of data acquisition by real-time identification of the relevant data of the ore separator through a computer algorithm.

[0084] Step 104: Obtain the intersection point of the ore boundary line and the adjustment line.

[0085] Further, in the first embodiment of the present invention, the intersection point of the ore boundary line and the adjustment line is obtained, specifically:

[0086] Acquire a plurality of boundary line coordinates on the ore boundary line;

[0087] Perform straight line fitting based on the coordinates of each dividing line, and determine the fitted straight line as the dividing line fitting straight line;

[0088] The intersection point of the boundary line fitting straight line and the adjustment line is determined as the intersection point of the ore boundary line and the adjustment line.

[0089] In the first embodiment of the present invention, the ore boundary line obtained by identification and detection on the ore map is not necessarily a straight line segment, but may be an irregular curve. Therefore, before determining the intersection point of the ore boundary line and the adjustment line, it is necessary to first perform a straight line fitting on the ore boundary line. Among them, the ore boundary line includes a large number of coordinate points, and a straight line fitting can be performed by collecting a part of the coordinate points. After completing the straight line fitting, the intersection point of the ore boundary line and the adjustment line can be obtained by a mathematical processing method.

[0090] Further, in the first embodiment of the present invention, several boundary line coordinates are obtained on the ore boundary line, specifically:

[0091] Acquire the coordinates of all points on the ore boundary line identified in the ore map, and determine the coordinates of all points on the ore boundary line as boundary line coordinates;

[0092] Alternatively, according to a preset end determination method, a boundary line end range is determined on the ore boundary line, a plurality of end coordinates are obtained within the boundary line end range, and the plurality of end coordinates are determined as boundary line coordinates;

[0093] Alternatively, inflection points are identified on the ore boundary line, the terminal direction of the ore boundary line is determined according to a preset terminal determination method, the inflection point closest to the terminal direction of the ore boundary line is determined as the terminal inflection point, and the coordinates of all points identified along the terminal direction of the ore boundary line are determined as boundary line coordinates.

[0094] As an example of the first embodiment of the present invention, see Figure 2 , a schematic diagram of a method for obtaining the boundary line coordinates is provided, the coordinates of all points on the ore boundary line are determined as the boundary line coordinates, and a straight line fitting is performed to obtain the intersection point of the ore boundary line and the adjustment line.

[0095] As an example of the first embodiment of the present invention, see Figure 3 , another schematic diagram of a method for obtaining the coordinates of the dividing line is provided, the distances between the two ends of the ore dividing line and the adjustment line are calculated respectively, and the end with the shorter distance is determined as the end of the ore dividing line. A plurality of terminal coordinates are collected at the end of the dividing line as the dividing line coordinates to complete the straight line fitting. Among them, the method for collecting a plurality of terminal coordinates at the end of the dividing line includes: 1. Pre-setting the percentage X of the terminal coordinates, assuming that the number of data points on the ore dividing line is N, then the coordinates of the N*X data points close to the end of the ore dividing line are determined as the terminal coordinates. 2. Pre-setting the terminal length percentage Y, assuming that the length of the ore dividing line is L, then the coordinates corresponding to the data points within the L*Y length close to the end of the ore dividing line are determined as the terminal coordinates.

[0096] As an example of the first embodiment of the present invention, see Figure 4 , another schematic diagram of the method for obtaining the coordinates of the dividing line is provided, and the coordinates corresponding to the data points after the inflection point at the end of the dividing line are determined as the coordinates of the dividing line. Specifically, by respectively calculating the distance between the two ends of the ore dividing line and the adjustment line, the end with the shorter distance is determined as the end of the ore dividing line; the inflection point is identified on the ore dividing line to obtain all the inflection points on the ore dividing line; the inflection point closest to the end of the ore dividing line is determined as the end inflection point, and the coordinates of all the data points between the end inflection point and the end of the ore dividing line are determined as the dividing line coordinates to complete the straight line fitting. Among them, the method for identifying the inflection point on the ore dividing line is to first smooth the ore dividing line, then calculate the maximum value points on the ore dividing line, and determine all the maximum value points as the inflection points of the ore dividing line.

[0097] Step 105: Determine the adjustment method of each of the ore separators according to the intersection point and the position information of each of the ore separators in combination with the preset deviation distance corresponding to each of the ore separators.

[0098] Further, in the first embodiment of the present invention, when the ore separator is a movable ore separator slot, the adjustment method of each ore separator is determined according to the intersection point, the position information of each ore separator, and the preset deviation distance corresponding to each ore separator, specifically:

[0099] Obtaining the coordinates of the intersection points on the ore map;

[0100] According to the intersection point coordinates, combined with the preset deviation distance corresponding to each of the ore separators, the target position coordinates corresponding to each of the ore separators are obtained;

[0101] The adjustment method of each ore separator is determined to be that each ore separator moves along the adjustment line to the target position coordinate.

[0102] In the first embodiment of the present invention, different types of ore separators correspond to different adjustment methods. When the ore separator is a movable ore separator slot, the adjustment method is to translate the ore separator. First, the intersection point coordinates are obtained on the ore map, and then based on the deviation distance corresponding to each ore separator, the target position coordinates corresponding to each ore separator are calculated, and each ore separator is translated on the adjustment line to move each ore separator to the target position coordinates.

[0103] As an example of the first embodiment of the present invention, when the deviation distance corresponding to the separator is positive, it is determined that the target position coordinates of the separator are between the current position coordinates of the separator and the intersection point coordinates. At this time, the actual distance between the separator and the intersection point is calculated based on the current position coordinates of the separator and the intersection point coordinates, and then the actual distance is subtracted from the deviation distance to obtain the translation distance of the separator, and based on the translation distance, the separator is translated on the adjustment line to move the separator to the target position coordinates.

[0104] As an example of the first embodiment of the present invention, when the deviation distance corresponding to the separator is negative, it is determined that the distance between the target position coordinates and the current position coordinates of the separator is greater than the distance between the current position coordinates of the separator and the intersection coordinates. At this time, the actual distance between the separator and the intersection is calculated based on the current position coordinates of the separator and the intersection coordinates, and then the actual distance is added to the deviation distance to obtain the translation distance of the separator, and the separator is translated on the adjustment line based on the translation distance to move the separator to the target position coordinates. Furthermore, in the first embodiment of the present invention, when the separator is a rotating arm, the adjustment method of each separator is determined based on the intersection point and the position information of each separator, combined with the preset deviation distance corresponding to each separator, specifically:

[0105] The coordinates of the intersection point, the coordinates of the rotation fulcrum of each of the ore dividers and the effective arm length, the first angle and the second angle are respectively obtained on the ore map; the first angle is the angle between the ore boundary line and the adjustment line; the second angle is the angle between each of the ore dividers and the adjustment line;

[0106] In combination with the preset deviation distance corresponding to each of the ore separators, construct an auxiliary line corresponding to each of the ore separators and parallel to the ore boundary line;

[0107] An auxiliary circle of each ore separator is constructed with the effective arm length of each ore separator as the radius and the rotation fulcrum as the center;

[0108] Determining the target position of the end of the rotating arm of each of the ore separators at two intersection points of the auxiliary line and the auxiliary circle;

[0109] Determine a target angle of a target angle between each of the ore separators and the adjustment line according to the intersection point coordinates, the rotation fulcrum coordinates of each of the ore separators, the effective arm length, and the first angle;

[0110] Calculating the rotation angle of each of the ore separators according to the second angle and the target angle;

[0111] The adjustment method of each ore separator is determined as rotating each ore separator by the rotation angle so that the end of the rotating arm of each ore separator is at the target position of the end of the rotating arm.

[0112] In the first embodiment of the present invention, for the ore separator with a rotating arm, the adjustment method is to rotate the rotating arm. Each ore separator corresponds to a deviation distance. When determining the target position of the end of the rotating arm, an auxiliary line parallel to the ore boundary line is first constructed based on the deviation distance; the target position of the end of the rotating arm is on the auxiliary line, so the effective arm length of each ore separator is used as the radius and the rotating fulcrum is used as the center of the circle to construct an auxiliary circle of each ore separator. The point closer to the initial flow position of the ore to be screened among the two intersection points between the auxiliary line and the auxiliary circle is the target position of the end of the rotating arm. After determining the target position of the end of the rotating arm, the rotation angle of each ore separator can be calculated by mathematical operation according to the coordinates of the intersection point obtained on the ore map, the coordinates of the rotating fulcrum of each ore separator and the effective arm length, the first angle and the second angle. Based on the rotation angle, each ore separator is controlled to rotate with the rotating fulcrum as the fixed point, so that the end of the rotating arm of each ore separator is at the target position of the end of the rotating arm to adjust the ore separator with a rotating arm. It should be noted that, depending on the different deviation distances corresponding to the various ore separators, the auxiliary line parallel to the ore boundary line may be located on the left or right side of the ore boundary line.

[0113] Further, in the first embodiment of the present invention, the target angle of the target angle between each of the ore separators and the adjustment line is determined according to the intersection point coordinates, the rotation fulcrum coordinates of each of the ore separators, the effective arm length, and the first angle, specifically:

[0114] Calculate a first distance between each of the ore separators and the intersection point according to the intersection point coordinates and the rotation fulcrum coordinates of each of the ore separators;

[0115] Determine the intersection point between the auxiliary line and the adjustment line as the auxiliary intersection point of each of the ore separators;

[0116] Calculate the second distance between each of the ore separators and the auxiliary intersection point according to the first distance between each of the ore separators and the intersection point and a preset deviation distance corresponding to each of the ore separators;

[0117] Using the sine theorem, according to the effective arm length of each of the ore separators, the first angle and the second distance, the third angle between the target line segment and the auxiliary line is calculated; wherein the target line segment is a line segment formed by connecting the target position at the end of the rotating arm of each of the ore separators and the rotating fulcrum;

[0118] The target angle of the target angle between each of the separators and the adjustment line is obtained by calculating the first angle and the third angle using the triangle interior angle theorem.

[0119] As an example of the first embodiment of the present invention, see Figure 5, is a schematic diagram of the rotating arm adjustment method provided by the present invention. The adjustment method of the ore separator of the rotating arm is to rotate the rotating arm. The purpose of the adjustment is to place the end of the rotating arm on the auxiliary line, and the auxiliary line is parallel to the ore boundary line. The second angle between the ore separator and the adjustment line can be obtained on the ore map. Therefore, when calculating the rotation angle of the ore separator, it is only necessary to obtain the target angle of the target angle between the ore separator and the adjustment line, and the difference between the second angle and the target angle can be determined as the rotation angle. To calculate the target angle, the triangle formed by the rotation fulcrum, the intersection point between the adjustment line and the auxiliary line, and the target position at the end of the rotating arm can be used for auxiliary calculation. First, the first angle between the ore boundary line and the adjustment line can be obtained on the ore map. Since the auxiliary line is parallel to the ore boundary line, the angle between the auxiliary line and the adjustment line is also the first angle; secondly, the first distance between the separator and the intersection point is calculated based on the intersection point coordinates and the rotation fulcrum coordinates obtained on the ore map, and then the second distance between the separator and the auxiliary line is calculated based on the deviation distance; the distance between the rotation fulcrum and the target position at the end of the rotating arm is equivalent to the effective arm length of the separator. Therefore, in the auxiliary triangle, under the premise of knowing the effective arm length of the separator, the first angle and the second distance, the sine theorem can be used to calculate the third angle corresponding to the vertex at the target position at the end of the rotating arm. After the third angle is calculated, based on the triangle interior angle sum theorem, 180° is subtracted from the angle sum of the first angle and the third angle to obtain the target angle between the separator and the adjustment line.

[0120] In the first embodiment of the present invention, there are two intersection points between the auxiliary line and the auxiliary circle, and the target position of the end of the rotating arm can be determined according to the initial flow position of the ore to be screened flowing into the mineral processing equipment. In the first embodiment of the present invention, the point of the two intersection points that is closer to the initial flow position of the ore to be screened is the target position of the end of the rotating arm, so that the target ore and non-target ore in the ore to be screened are separated at the end of the rotating arm, so as to achieve the purpose of automatic screening of the ore. Specifically, the distances between the two intersection points between the auxiliary line and the auxiliary circle and the initial flow position of the ore to be screened are calculated respectively, and the intersection point with a closer distance is determined as the target position of the end of the rotating arm.

[0121] In the first embodiment of the present invention, after the angle value of the target angle is calculated, the actual angle value between the rotating arm and the adjustment line is subtracted from the target angle value to obtain the rotation angle, and the direction of each rotating arm is adjusted based on the rotation angle. When the calculated rotation angle is positive, the ore separator is controlled to rotate in the direction toward the adjustment line; when the calculated rotation angle is negative, the ore separator is controlled to rotate in the direction away from the adjustment line.

[0122] Step 106: Control each of the ore separators to adjust to a corresponding target position through a corresponding adjustment method.

[0123] In the first embodiment of the present invention, different adjustment methods are used to adjust each separator according to different types of separators, so that each separator reaches the target position through translation position or rotation direction, thereby achieving a better separation effect and improving work efficiency.

[0124] In summary, the first embodiment of the present invention provides an intelligent mineral processing method based on machine vision technology, which uses an image collector to collect ore maps in real time; identifies the ore maps and determines the ore boundary lines in the ore maps; identifies the position information of several separators in the ore maps, and determines the adjustment lines according to the position information of each separator; obtains the intersection point of the ore boundary line and the adjustment line; determines the adjustment method of each separator according to the intersection point and the position information of each separator, combined with the preset deviation distance corresponding to each separator; controls each separator to adjust to the corresponding target position through the corresponding adjustment method. The present invention uses machine vision technology to identify the position of the target ore in real time, automatically adjusts the position and direction of the separator, and realizes fully automatic ore screening. When the type or taste of the ore changes, no human intervention is required, which improves work efficiency and thus improves the recognition accuracy of the target ore.

[0125] Example 2

[0126] See also Figure 6 , is a structural schematic diagram of an embodiment of an intelligent ore dressing device based on machine vision technology provided by the present invention, the device includes a collection module 201, a boundary line determination module 202, an adjustment line determination module 203, an intersection point acquisition module 204, an adjustment mode determination module 205 and a control module 206;

[0127] The acquisition module 201 is used to acquire ore images in real time using an image collector;

[0128] The boundary determination module 202 is used to identify the ore map and determine the ore boundary in the ore map; wherein the ore boundary is used to distinguish target ore from non-target ore;

[0129] The adjustment line determination module 203 is used to identify the position information of several ore separators in the ore map, and determine the adjustment line according to the position information of each ore separator;

[0130] The intersection point acquisition module 204 is used to obtain the intersection point of the ore boundary line and the adjustment line;

[0131] The adjustment mode determination module 205 is used to determine the adjustment mode of each of the ore separators according to the intersection point and the position information of each of the ore separators, combined with the preset deviation distance corresponding to each of the ore separators;

[0132] The control module 206 is used to control each of the ore separators to be adjusted to a corresponding target position through a corresponding adjustment method.

[0133] Furthermore, in the second embodiment of the present invention, the ore map is identified, and the ore boundary line is determined in the ore map, specifically:

[0134] Performing image equalization on the ore map, determining a range of target colors in the ore map, and determining an ore boundary line in combination with a preset minimum color band width; wherein the target colors include preset target ore colors and non-target ore colors;

[0135] Alternatively, edge detection is performed on the ore map based on an edge detection algorithm, and the ore boundary line is determined according to the edge detection result; wherein the edge detection result includes the target ore edge and the non-target ore edge;

[0136] Alternatively, boundary line detection is performed on the ore map based on a first target detection algorithm, and the ore boundary line is determined according to the boundary line detection result.

[0137] Further, in the second embodiment of the present invention, the ore separator is a movable ore separator slot, the position information is the position coordinates of the ore separator, the position information of a plurality of ore separators is identified in the ore map, and the adjustment line is determined according to the position information of each ore separator, specifically:

[0138] Based on the second target detection algorithm, ore separators are identified in the ore map to obtain position coordinates of several ore separators;

[0139] An adjustment line is determined based on the position coordinates of each of the separators.

[0140] Further, in the second embodiment of the present invention, the ore separator is a rotating arm, the position information is the coordinates of the rotating fulcrum of the ore separator, the position information of several ore separators is identified in the ore map, and the adjustment line is determined according to the position information of each ore separator, specifically:

[0141] Based on the second target detection algorithm, the ore separator is identified in the ore map to obtain the coordinates of the rotation fulcrums of several ore separators;

[0142] The adjustment line is determined based on the coordinates of the rotation fulcrum of each of the separators.

[0143] Further, in the second embodiment of the present invention, the intersection point of the ore boundary line and the adjustment line is obtained, specifically:

[0144] Acquire a plurality of boundary line coordinates on the ore boundary line;

[0145] Perform straight line fitting based on the coordinates of each dividing line, and determine the fitted straight line as the dividing line fitting straight line;

[0146] The intersection point of the boundary line fitting straight line and the adjustment line is determined as the intersection point of the ore boundary line and the adjustment line.

[0147] Further, in the second embodiment of the present invention, several boundary line coordinates are obtained on the ore boundary line, specifically:

[0148] Acquire the coordinates of all points on the ore boundary line identified in the ore map, and determine the coordinates of all points on the ore boundary line as boundary line coordinates;

[0149] Alternatively, according to a preset end determination method, a boundary line end range is determined on the ore boundary line, a plurality of end coordinates are obtained within the boundary line end range, and the plurality of end coordinates are determined as boundary line coordinates;

[0150] Alternatively, inflection points are identified on the ore boundary line, the terminal direction of the ore boundary line is determined according to a preset terminal determination method, the inflection point closest to the terminal direction of the ore boundary line is determined as the terminal inflection point, and the coordinates of all points identified along the terminal direction of the ore boundary line are determined as boundary line coordinates.

[0151] Further, in the second embodiment of the present invention, when the ore separator is a movable ore separator slot, the adjustment method of each ore separator is determined according to the intersection point, the position information of each ore separator, and the preset deviation distance corresponding to each ore separator, specifically:

[0152] Obtaining the coordinates of the intersection points on the ore map;

[0153] According to the intersection point coordinates, combined with the preset deviation distance corresponding to each of the ore separators, the target position coordinates corresponding to each of the ore separators are obtained;

[0154] The adjustment method of each ore separator is determined to be that each ore separator moves along the adjustment line to the target position coordinate.

[0155] Further, in the second embodiment of the present invention, when the ore separator is a rotating arm, the adjustment mode of each ore separator is determined according to the intersection point, the position information of each ore separator, and the preset deviation distance corresponding to each ore separator, specifically:

[0156] The coordinates of the intersection point, the coordinates of the rotation fulcrum of each of the ore dividers and the effective arm length, the first angle and the second angle are respectively obtained on the ore map; the first angle is the angle between the ore boundary line and the adjustment line; the second angle is the angle between each of the ore dividers and the adjustment line;

[0157] In combination with the preset deviation distance corresponding to each of the ore separators, construct an auxiliary line corresponding to each of the ore separators and parallel to the ore boundary line;

[0158] An auxiliary circle of each ore separator is constructed with the effective arm length of each ore separator as the radius and the rotation fulcrum as the center;

[0159] Determining the target position of the end of the rotating arm of each of the ore separators at two intersection points of the auxiliary line and the auxiliary circle;

[0160] Determine a target angle of a target angle between each of the ore separators and the adjustment line according to the intersection point coordinates, the rotation fulcrum coordinates of each of the ore separators, the effective arm length, and the first angle;

[0161] Calculating the rotation angle of each of the ore separators according to the second angle and the target angle;

[0162] The adjustment method of each ore separator is determined as rotating each ore separator by the rotation angle so that the end of the rotating arm of each ore separator is at the target position of the end of the rotating arm.

[0163] Further, in the second embodiment of the present invention, the target angle of the target angle between each of the ore separators and the adjustment line is determined according to the intersection point coordinates, the rotation fulcrum coordinates of each of the ore separators, the effective arm length, and the first angle, specifically:

[0164] Calculate a first distance between each of the ore separators and the intersection point according to the intersection point coordinates and the rotation fulcrum coordinates of each of the ore separators;

[0165] Determine the intersection point between the auxiliary line and the adjustment line as the auxiliary intersection point of each of the ore separators;

[0166] Calculate the second distance between each of the ore separators and the auxiliary intersection point according to the first distance between each of the ore separators and the intersection point and a preset deviation distance corresponding to each of the ore separators;

[0167] Using the sine theorem, according to the effective arm length of each of the ore separators, the first angle and the second distance, the third angle between the target line segment and the auxiliary line is calculated; wherein the target line segment is a line segment formed by connecting the target position at the end of the rotating arm of each of the ore separators and the rotating fulcrum;

[0168] The target angle of the target angle between each of the separators and the adjustment line is obtained by calculating the first angle and the third angle using the triangle interior angle theorem.

[0169] In summary, the second embodiment of the present invention provides an intelligent mineral processing device based on machine vision technology, which is based on the organic combination of modules and uses an image collector to collect ore maps in real time; identifies the ore map and determines the ore boundary line in the ore map; identifies the position information of several separators in the ore map, and determines the adjustment line according to the position information of each separator; obtains the intersection point of the ore boundary line and the adjustment line; determines the adjustment method of each separator according to the intersection point and the position information of each separator, combined with the preset deviation distance corresponding to each separator; controls each separator to adjust to the corresponding target position through the corresponding adjustment method. The present invention uses machine vision technology to identify the position of the target ore in real time, automatically adjusts the position and direction of the separator, and realizes fully automatic ore screening. When the type or taste of the ore changes, no human intervention is required, which improves work efficiency and thus improves the recognition accuracy of the target ore.

[0170] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. An intelligent mineral processing method based on machine vision technology, characterized in that: include: Use image collector to collect ore map in real time; Identify the ore map and determine an ore boundary line in the ore map; wherein the ore boundary line is used to distinguish target ore from non-target ore; Identifying the position information of a plurality of ore separators in the ore map, and determining an adjustment line according to the position information of each ore separator; Obtaining the intersection point of the ore boundary line and the adjustment line; Determine the adjustment method of each of the ore separators according to the intersection point and the position information of each of the ore separators, combined with the preset deviation distance corresponding to each of the ore separators; Control each of the ore separators to adjust to a corresponding target position through a corresponding adjustment method.

2. The intelligent mineral processing method based on machine vision technology according to claim 1 is characterized in that: The identifying of the ore map and determining the ore boundary line in the ore map are specifically as follows: Performing image equalization on the ore map, determining a range of target colors in the ore map, and determining an ore boundary line in combination with a preset minimum color band width; wherein the target colors include preset target ore colors and non-target ore colors; Alternatively, edge detection is performed on the ore map based on an edge detection algorithm, and the ore boundary line is determined according to the edge detection result; wherein the edge detection result includes the target ore edge and the non-target ore edge; Alternatively, boundary line detection is performed on the ore map based on a first target detection algorithm, and the ore boundary line is determined according to the boundary line detection result.

3. The intelligent mineral processing method based on machine vision technology according to claim 1 is characterized in that: The ore distributor is a movable ore distributor slot, the position information is the position coordinates of the ore distributor, the position information of several ore distributors is identified in the ore map, and the adjustment line is determined according to the position information of each ore distributor, specifically: Based on the second target detection algorithm, ore separators are identified in the ore map to obtain position coordinates of several ore separators; An adjustment line is determined based on the position coordinates of each of the separators.

4. The intelligent mineral processing method based on machine vision technology according to claim 1 is characterized in that: The ore separator is a rotating arm, the position information is the coordinates of the rotating fulcrum of the ore separator, the position information of several ore separators is identified in the ore map, and the adjustment line is determined according to the position information of each ore separator, specifically: Based on the second target detection algorithm, the ore separator is identified in the ore map to obtain the coordinates of the rotation fulcrums of several ore separators; The adjustment line is determined based on the coordinates of the rotation fulcrum of each of the separators.

5. The intelligent mineral processing method based on machine vision technology according to claim 1 is characterized in that: The obtaining of the intersection point of the ore boundary line and the adjustment line is specifically as follows: Acquire a plurality of boundary line coordinates on the ore boundary line; Perform straight line fitting based on the coordinates of each dividing line, and determine the fitted straight line as the dividing line fitting straight line; The intersection point of the boundary line fitting straight line and the adjustment line is determined as the intersection point of the ore boundary line and the adjustment line.

6. The intelligent mineral processing method based on machine vision technology according to claim 5 is characterized in that: The coordinates of several boundary lines are obtained on the ore boundary line, specifically: Acquire the coordinates of all points on the ore boundary line identified in the ore map, and determine the coordinates of all points on the ore boundary line as boundary line coordinates; Alternatively, according to a preset end determination method, a boundary line end range is determined on the ore boundary line, a plurality of end coordinates are obtained within the boundary line end range, and the plurality of end coordinates are determined as boundary line coordinates; Alternatively, inflection points are identified on the ore boundary line, the terminal direction of the ore boundary line is determined according to a preset terminal determination method, the inflection point closest to the terminal direction of the ore boundary line is determined as the terminal inflection point, and the coordinates of all points identified along the terminal direction of the ore boundary line are determined as boundary line coordinates.

7. The intelligent mineral processing method based on machine vision technology according to claim 3 is characterized in that: When the ore separator is a movable ore separator slot, the adjustment method of each ore separator is determined according to the intersection point, the position information of each ore separator, and the preset deviation distance corresponding to each ore separator, specifically: Obtaining the coordinates of the intersection points on the ore map; According to the intersection point coordinates, combined with the preset deviation distance corresponding to each of the ore separators, the target position coordinates corresponding to each of the ore separators are obtained; The adjustment method of each ore separator is determined to be that each ore separator moves along the adjustment line to the target position coordinate.

8. The intelligent mineral processing method based on machine vision technology according to claim 4 is characterized in that: When the ore separator is a rotating arm, the adjustment method of each ore separator is determined according to the intersection point, the position information of each ore separator, and the preset deviation distance corresponding to each ore separator, specifically: The coordinates of the intersection point, the coordinates of the rotation fulcrum of each of the ore dividers and the effective arm length, the first angle and the second angle are respectively obtained on the ore map; the first angle is the angle between the ore boundary line and the adjustment line; the second angle is the angle between each of the ore dividers and the adjustment line; In combination with the preset deviation distance corresponding to each of the ore separators, an auxiliary line corresponding to each of the ore separators and parallel to the ore boundary line is constructed; An auxiliary circle of each ore separator is constructed with the effective arm length of each ore separator as the radius and the rotation fulcrum as the center; Determining the target position of the end of the rotating arm of each of the ore separators at two intersection points of the auxiliary line and the auxiliary circle; Determine a target angle of a target angle between each of the ore separators and the adjustment line according to the intersection point coordinates, the rotation fulcrum coordinates of each of the ore separators, the effective arm length, and the first angle; Calculating the rotation angle of each of the ore separators according to the second angle and the target angle; The adjustment method of each ore separator is determined as rotating each ore separator by the rotation angle so that the end of the rotating arm of each ore separator is at the target position of the end of the rotating arm.

9. The intelligent mineral processing method based on machine vision technology according to claim 8 is characterized in that: The target angle of the target angle between each of the ore separators and the adjustment line is determined according to the intersection point coordinates, the rotation fulcrum coordinates of each of the ore separators, the effective arm length, and the first angle, specifically: Calculate a first distance between each of the ore separators and the intersection point according to the intersection point coordinates and the rotation fulcrum coordinates of each of the ore separators; Determine the intersection point between the auxiliary line and the adjustment line as the auxiliary intersection point of each of the ore separators; Calculate the second distance between each of the ore separators and the auxiliary intersection point according to the first distance between each of the ore separators and the intersection point and a preset deviation distance corresponding to each of the ore separators; Using the sine theorem, according to the effective arm length of each of the ore separators, the first angle and the second distance, the third angle between the target line segment and the auxiliary line is calculated; wherein the target line segment is a line segment formed by connecting the target position at the end of the rotating arm of each of the ore separators and the rotating fulcrum; The target angle of the target angle between each of the separators and the adjustment line is obtained by calculating the first angle and the third angle using the triangle interior angle theorem.

10. An intelligent mineral processing device based on machine vision technology, characterized in that: include: Acquisition module, boundary line determination module, adjustment line determination module, intersection point acquisition module, adjustment mode determination module and control module; The acquisition module is used to acquire ore images in real time using an image collector; The boundary determination module is used to identify the ore map and determine the ore boundary in the ore map; wherein the ore boundary is used to distinguish target ore from non-target ore; The adjustment line determination module is used to identify the position information of a plurality of ore separators in the ore map, and determine the adjustment line according to the position information of each ore separator; The intersection point acquisition module is used to obtain the intersection point of the ore boundary line and the adjustment line; The adjustment mode determination module is used to determine the adjustment mode of each of the ore separators according to the intersection point and the position information of each of the ore separators, combined with the preset deviation distance corresponding to each of the ore separators; The control module is used to control each of the ore separators to be adjusted to a corresponding target position through a corresponding adjustment method.

Images