MINING EQUIPMENT INSPECTION SYSTEM, MINING EQUIPMENT INSPECTION METHOD, AND MINING EQUIPMENT INSPECTION DEVICE

Abstract

A computer-implemented point cloud data acquisition method is described for acquiring point cloud data from the interior of a mining rig, the method comprising: acquiring from a sensor, a first data set and a second data set, wherein each data set comprises data points in coordinates; extracting features from the first and second data sets; aligning the first and second data sets using the extracted features; combining the first and second data sets into point cloud data; estimating a geometry of the mining rig based on the point cloud data; and identifying by using the point cloud data a region of the estimated geometry indicating insufficient data.

Description

The present invention relates generally to systems, methods, and devices for inspecting mining equipment. Examples of mining equipment include mills, crushers, and grinders. Furthermore, the present invention relates to systems, methods, and devices for the virtual inspection of mining equipment. BACKGROUND OF THE INVENTION Mining equipment, such as horizontal or vertical mills, crushers, or grinders, is used to reduce the size of mining materials, such as minerals or ore, through a mining process like grinding, crushing, or milling. The mining process typically applies tensile forces to the mining material until it breaks into smaller pieces. Metal objects, such as rods or balls, may be placed in the mining equipment to aid the process. Furthermore, mining equipment can perform dry or wet mining processes, with wet mining providing greater efficiency and minimizing dust formation. However, during the mining process (especially wet mining), the mining equipment and metal objects will experience wear and tear. To protect mining equipment from excessive wear, a lining can be installed on its surfaces. This lining can be made of ceramic, rubber, polymer, or composite material and is typically installed in a way that allows for easy replacement, for example, using bolts, retainers, or hooks, when it reaches the end of its service life. The lining can be shaped to withstand the mining process or material discharge, for example, by incorporating protrusions and recesses that act as scoops. Regular inspections are necessary to assess wear and / or damage to the lining and determine if replacement is required. However, to carry out the inspection, it is necessary for inspection personnel, such as a specialist, to enter a hostile environment, such as the room or space inside the mining equipment, or a space near where the mining procedure takes place. To reduce the possibility of harm to inspection personnel during the inspection, two safety precautions are typically followed. First, the mining equipment is shut down and decontaminated, and then inspected during its downtime, i.e., when the mining equipment is not operating, meaning it is not performing any mining procedure. Second, the inspection should be carried out as quickly as possible to minimize downtime and, more importantly, to reduce the duration of the inspection personnel's exposure to the hostile environment.Once the inspection is complete, the operation can begin, and the data obtained during the inspection can be analyzed to determine the wear condition of the mining equipment, as well as its lining and discharge system. Previous technique Document AU 2016 200024 A1 refers to a system and a method for monitoring the status MA / IOD of surface wear on mining equipment. In this document, surfaces are measured and compared with historical data to determine if surface repair or replacement is necessary (e.g., of a lining). The measurement is performed on a de-energized (and possibly decontaminated) mining rig using a scanning device that sweeps around a horizontal and vertical axis to generate 3D point cloud data. The scanning device is attached to the end of a rod, beam, or boom inserted into the mining rig or mounted on a tripod located inside the rig. The aim here is to permanently or rigidly attach the sensor to prevent it from changing position within the rig during scanning.However, since the exploration apparatus used herein remains stationary, part of the surface to be inspected may still be covered by mining material, such as crushed ore, or other waste, such as mud. Furthermore, AU 2016 200024 A1 aims to explore the entire surface by positioning the exploration apparatus as close as possible to the center of the mining equipment. However, an irregular surface, such as one with protrusions, can result in shadows during the exploration, where part of the explored surface is obstructed by these protrusions. In addition to the mining material and other waste present on the mining equipment during the exploration, these shadows further degrade the quality and completeness of the point cloud data used for analysis and inspection. Technical problem In view of the above, there is the technical problem of how to acquire sufficient and complete data from mining equipment during the inspection, while minimizing the duration of the inspection. In addition, there is the technical problem of how to improve the inspection to identify specific points of interest inside mining equipment and to improve the reporting of these points of interest. Furthermore, since recently shut-down mining equipment may still contain mining material such as minerals, ore, or mud, parts of the structure or surfaces of the equipment may remain covered with this material, preventing inspection. Traditionally, mining equipment must be cleaned—for example, by emptying and decontaminating it—and shut down for inspection, which further prolongs the inspection process. Therefore, an additional technical challenge is to avoid, or at least mitigate, the need for emptying, decontaminating, and / or shutting down mining equipment. Solution The present invention, according to the independent claims, solves this technical problem. The content of the dependent claims describes additional preferred embodiments. Advantageous effects The systems, methods, and devices described in the independent claims improve the performance of mining equipment inspections. More specifically, the inspection time is kept short, which improves the safety of inspection personnel and reduces downtime of mining equipment. Furthermore, data acquisition during the inspection is carried out in such a way that the dataset acquired during the inspection is complete, thereby preventing errors. MA / IOO subsequent inspections. Furthermore, the inspection can be carried out without completely stopping the mining equipment, allowing for continuous operation. In addition, virtual inspection improves the identification of specific points of interest inside the mining equipment, particularly by providing the virtual inspection to multiple on-site and remote users simultaneously inspecting the mining equipment. BRIEF DESCRIPTION OF THE FIGURES Figures 1A to 1E represent examples of mining equipment. Figures 2A to 2D represent a lined rotary mill and data sets acquired to perform a rotary mill inspection. Figures 3A and 3B represent the data acquisition procedure, the missing data identification procedure. Figures 4A to 4E depict the movement of a sensor when inspecting a rotating mill that is in operation. Figures 5A to 5C represent a different method for data acquisition when inspecting a rotary mill. Fig. 6 represents the computer-implemented method for a virtual inspection of the interior of mining equipment. Figure 7 is a block diagram illustrating an example hardware configuration of a computing device for implementing the methods described in this document. Figure 8 represents the computer-implemented method of a guidance procedure for exploring mining equipment for inspection analysis. Figures 9A to 9B represent an inspection system with and without a remote display. Figure 10 represents the computer-implemented method of a feedback procedure for exploring mining equipment based on input from a knowledgeable person guiding the exploration. Figures 11A to 11C represent an example of calculating the gradient change of the obtained data points, by which a region of insufficient data and / or high detection inaccuracy can be determined. Figures 12A and 12B represent an example of guiding the user and / or causing the sensor to move in a direction so that an identified region or insufficient data region is re-explored. DETAILED DESCRIPTION OF THE INVENTION The following describes in detail exemplary embodiments of the invention with reference to the accompanying figures. It should be noted that the following description contains only examples and should not be construed as limiting the invention. Hereafter, similar or identical reference signs indicate similar or identical features or functions. [Mining equipment] With reference to Figures 1A to 1D, the functionality of different mining equipment is explained. Each piece of mining equipment depicted in Figures 1A to 1D is designed to reduce the size of the mining material 10 to produce a smaller material or product 20. MA / IOO Figure 1A depicts a compression crusher 100 as mining equipment. A jaw, gyratory, or cone crusher can be a compression crusher of this type. In this crusher, the ore 10 is compressed between a first surface 110 and a second surface 120. In this crusher, either or both surfaces can move in direction A, approaching and receding from each other, allowing the ore 10 to enter the space between the two surfaces and be compressed and crushed. The resulting product 20 is ejected from the compression crusher 100 by gravity and by the pressure of the ore 10 fed into the crusher. By controlling the momentum in direction A, the size of the product 20 is adjusted. During operation, the surfaces 110 and 120 wear down and can therefore be protected by a lining. Figure 1B depicts an impactor 200 as mining equipment. Mining material 10 is fed into the impactor 200 and thrown against internal surfaces 220 of the impactor 200 by means of rotating blades 210. In the example in Figure 1B, the blades 210 rotate in direction B. Upon impact, the mining material 10 against the internal surfaces 220 breaks into smaller pieces, resulting in the product 20 being ejected from the impactor 200. While the impactor 200 depicted in Figure 1B illustrates a horizontal-type impactor viewed from the side, a vertical-type impactor is constructed similarly when viewed from above. In a vertical-type impactor, the internal surfaces 220 would then represent part of the peripheral walls. By moving the inner surfaces 220 closer to or further from the rotating blades 210, the size of the product 20 is adjusted.Since both the 210 blades and the 210 inner surfaces wear down during operation, they can be covered or constructed with a coating that can be replaced when necessary. Figure 1C depicts high-pressure grinding rolls 300 as mining equipment. In this document, a first roll 310 and a second roll 320 rotate in a first direction B and a second direction B', i.e., in opposite directions. Mining material 10 is fed into the gap between the two rolls 310 and 320 and reduced in size to produce the ejected product 20. The size of the product 20 is adjusted by moving the two rolls 310 and 320 closer together or further apart. To accommodate different mining materials 10 and protect them from wear, the rolls 310 and 320 can be covered or constructed with a lining. Figure 1D represents a stirring grinding mill 400 as mining equipment. The stirring grinding mill 400 rotates a shaft 410 in direction B, thereby rotating rotating beams 420 that agitate the ore 10. This agitation reduces the size of the ore 10 through impact, compression, shear, and attrition forces between pieces of ore 10. Since ore 10 of varying sizes and masses settles or segregates at different heights within the stirring receptacle 430, the required product can be extracted at the appropriate height 401, 402 within the stirring receptacle 430. Screening or filtering the extracted product can further reduce the size variation of the extracted product. The inner surface of the stirring receptacle 430 and the beams 420 wear down during operation. Therefore, they can also be lined. Figure 1E depicts a rotary grinding mill 500 as mining equipment. To aid the mining operation, metal composite rods or balls can be inserted into the rotary grinding mill 500. The mining operation is performed by rotating the rotating receptacle 510 in a predetermined direction B. This exposes the mining material 10 to impact, compression, shear, and attrition forces, thereby reducing its size. Using a discharge structure (not shown in Figure 1E), the finished product of a predetermined size or size distribution can be extracted from the rotating receptacle 510. A liner can be installed to protect the inner surface of the rotating receptacle 510 during the mining operation. The liner can also be shaped accordingly to aid the mining operation. Other examples of mining equipment are a horizontal mill and a vertical mill. In addition to the different types of crushers and mills discussed above, mining equipment may also include screening machines, conveyor belts, power lines, pipes, or flotation machines. Screening machines receive granulated ore material and separate it into multiple particle size categories. By applying the inspection methodology described below to the screening machines—that is, by acquiring point cloud data from the machines or at least parts of them—their continued ore separation functionality is ensured. This reduces both the risk of damaging the screening machine itself (e.g., due to wear, fatigue, and material failure) and the risk of damaging other mining equipment (e.g., due to falsely screened material of incompatible particle size being fed into downstream mining equipment). Conveyor belts can be several kilometers long and are used to transfer mining material between mining equipment. By applying the inspection methodology described below—that is, by acquiring point cloud data from conveyor belts or at least portions thereof—their proper functioning can be ensured. Instead of using an in-depth analysis, as described below, to analyze wear and deformation of mining equipment, a thermal sensor can measure the temperature of bearings and other moving components of mining equipment, particularly a conveyor belt. Regions of the equipment that indicate a higher-than-average temperature provide information, for example, about insufficient lubrication and / or significant material wear, which will result in failure.A drone can be used to carry an inspection sensor along mining equipment when searching in such regions. This eliminates the need for inspection personnel to manually explore mining equipment, reducing health and safety risks and improving the accuracy of the search by minimizing human error. Power lines can be several kilometers long and supply mining equipment with electricity for its operations. By applying the point cloud data acquisition methodology described below to power lines, interruptions, power outages, and faults can be detected. Additionally, a thermal sensor can measure the temperature of power lines and electrical equipment, including transformers, generators, and power electronics, to identify areas where the ML / IOOO power lines or electrical equipment may overheat. These regions can indicate a short circuit, component degradation, or equipment overload. A drone can be used to carry an inspection sensor along the power line and electrical equipment when searching for such regions. Additionally, using a depth analysis similar to that described above, deformation or damage to the power line and electrical equipment can be inspected to ensure that operating and insulation standards are maintained. Pipelines are used to move mining materials such as ores, including coal and iron ore, or mining waste, known as tailings, over long distances. These pipelines can range from tens to hundreds of kilometers in length. By applying the inspection methodology described below to pipelines, deformation and wear that pose a risk of rupture and leakage can be detected. This detection allows for preventative maintenance to be performed before pipeline failure and before the failure can damage mining equipment connected to the pipeline. A drone can be used to carry a sensor along the pipeline when searching for areas of deformation and wear. This search can be expanded to also cover pumps, filters, compressors, and other piping equipment used in conjunction with the pipeline. Flotation machines are used to selectively separate hydrophobic materials from hydrophilic materials. Applying the inspection methodology described below to flotation machines ensures their continued operation and guarantees that the output product has a composition suitable for further processing. [Data Acquisition] To better illustrate and explain the embodiment(s) described herein, the 500 rotary grinding mill and its geometry are used to explain the procedure for inspecting mining equipment. However, other types of mining equipment may also be used (as described above). Figure 2A represents a rotary grinding mill 500 as mining equipment, shown open for illustrative purposes. The rotary grinding mill 500 comprises a liner 520 with protrusions and / or recesses and a discharge system 530. During mining operations, when the rotary grinding mill is in operation, the mill 500 is rotated, for example in direction B, to reduce the size of the ore material 20 in a manner similar to the mining operation depicted in Figure 1E. In preparation for the inspection, the rotary grinding mill 500 slows down and comes to a stop, allowing the inspection personnel to insert a sensor 30 into the rotating receptacle 510 and begin the inspection. Within the rotating receptacle 510, the sensor 30 (for example, a depth sensor, which detects the distance from the sensor to a surface as depth, thus performing a depth analysis) can be positioned to scan the inner surface of the rotary grinding mill 500. In this document, the sensor 50 outputs data sets comprising data points 540* in corresponding coordinates. The sensor 30 can be portable, which requires that the rotary grinding mill 500 be stopped and thoroughly decontaminated and / or cleaned before inspection personnel are allowed to enter the rotary receptacle 510. Alternatively, the sensor 30 can be supported by a rod, robot, or flying drone that enters the rotary receptacle 510. For this latter alternative, it may not be necessary to stop, decontaminate, and / or empty the rotary grinding mill 500. An inspection method for this latter option will be described later. Figure 2B represents a point cloud dataset comprising the 540 data points mentioned above, which can be represented and / or stored as coordinate vectors. The coordinate vector can be a three-dimensional vector in a Cartesian coordinate system that defines points in space related to mining equipment (e.g., related to the position of a surface or lining of mining equipment). The expert understands that the distance between the sensor and the mining equipment points can be obtained from time-of-flight information using a laser or similar device (depth information data).Alternatively, the coordinate vector can be a four-dimensional vector, where the first three values ​​are a three-dimensional vector in a Cartesian coordinate system (as just explained) and the fourth value refers to a reflection property from the scanned points of the mining equipment (e.g., the laser light reflection intensity from the sensor off a surface texture or surface composition at the respective points of the mining equipment). Alternatively, or in addition, the fourth value can be related to a thermal property from the scanned points of the mining equipment (e.g., a surface temperature measured by a thermal sensor used in conjunction with the aforementioned scan device). For clarity, the asterisk “*” added to some reference symbols and used in the following description indicates a data representation or a point cloud representation of the corresponding component. For example, reference 500* identifies point cloud data for mining equipment, reference 520* identifies a feature within point cloud data 500*, reference 540* identifies a data point within point cloud data 500*, and reference 550* identifies a data-insufficient region within point cloud data 500*. As shown in Fig. 2C, sensor 30 may have a limited scan range 31 and may be prone to scan shadows 32. In this document, scan shadows 32 may be due to protrusions or recesses, for example, in the 520 lining, that block part of a surface to be scanned and that would be in the line of sight of sensor 30, for example, within the scan range 31 of sensor 30, where there are no protrusions or recesses. Fig. 2D shows, for illustrative purposes, an enlargement of such a scan shadow 32 in section AA of Fig. 2C. Surface information within such a scan shadow 32 may be reflected as a gap in the point cloud data or as missing / inaccurate data, which could result in an inaccurate analysis of mining equipment.Using the method explained below, a complete 500* point cloud dataset of a piece of mining equipment (e.g., a 500 rotary grinding mill) can be obtained for analysis, such as wear and / or damage analysis, which also provides surface information that would otherwise be missing. Examples of wear or damage patterns obtained from such an analysis include defects, porosity, cracks, voids, discontinuities, missing or defective parts, corrosion, and damage. MA / IOO by impact, detachment (e.g., from the coating), and similar. Figure 3A illustrates the data acquisition procedure for the method of acquiring a complete point cloud dataset 500*. As shown in Figure 3A, the sensor 30 first acquires a first dataset 501* and then a second dataset 502*. In this document, each dataset comprises data points 540* at corresponding coordinates, for example, on a surface of the mining equipment. The acquisition is performed by moving the sensor 30 relative to a surface of the rotating receptacle 510, within the rotating receptacle 510, i.e., from position (a) to position (b), as illustrated in Figure 3A. With reference to Fig. 3A, the letters (a) to (f) indicate different times and locations of sensor 30 that extend beyond the acquisition of the first and second data sets 501* and 502*. In this document, (a) to (f) indicate different positions of sensor 30 within the rotating grinding mill 500 during scanning, when it is moving (from left to right) essentially along the axis of rotation of the rotating grinding mill 500. Sensor 30 can also (or alternatively) be rotated, for example in direction C, as shown in Fig. 2C. Therefore, the movement of sensor 30 can include translational and / or rotational movement. The sensor 30 can thus be a mobile sensor, preferably portable, flying, hovering, or suspended. In this respect, a flying drone, a rod, or a robotic suspension device can be used, for example.Furthermore, since sensor 30 progressively acquires sets 501*, ... 506* of individual data, the second set 502* of data is acquired after the first set 501* of data and after sensor 30 has moved. Similarly, the third set 503* of data is acquired after the first and second sets 501* and 502* of data and after sensor 30 has moved, and so on. This procedure of progressively acquiring sets 501*, ... 506* of data to produce the point cloud data 500* is also called “virtual painting” of the interior of the mining equipment. To produce data sets 501*, ... 506*, sensor 30 can acquire information about the distance from sensor 30 to a surface within the mining equipment, for example, the rotary grinding mill 500, as depth information. Laser, radar, sonar, or stereoscopic imaging, a time-of-flight sensor, or a combination thereof can be used to acquire this depth information. The data obtained by sensor 30 can also include information related to surface texture or composition. For example, while the time of flight of the emitted signal and its reflection can indicate a distance to the measured surface, a property related to the intensity of the reflected and measured signal can indicate the type of material to which the distance is being measured. For example, rubber may absorb more light from a laser-based scanning device than a metal surface. Furthermore, sensor 30 can obtain orientation and / or position information (e.g., by using odometry) from sensor 30. In this document, orientation information may include roll, pitch, and / or yaw information from sensor 30, and position information may include x, y, and z coordinates from sensor 30. A gyroscope and an accelerometer sampling at high frequencies, e.g., at least 100 Hz, may be used to obtain orientation and position change. Since this provides information about the position and orientation of the ML / IOD sensor 30, and since depth information is also acquired, corresponding coordinates of data points 540* representing the explored surface can be derived, such as the acquired data sets 50Γ, ... 506*. Therefore, the data points 540* include coordinates indicating a location on a surface detected by sensor 30. The point cloud data 500* is used for analysis since it is a set of data points 540* each representing location information or location-intensity information of a point on a surface within the mining equipment 500* as previously mentioned. Thus, each data point 540* represents information about the internal surface structure of the mining equipment 500. However, since the scan range 31 may limit the size of each data set 50Γ, ... 506* acquired by sensor 30, and since the position and location of sensor 30 cannot be tracked with perfect accuracy, it may be necessary to combine or “join” the data sets 501*, ... 506* together to produce the point cloud data 500* representing the structure inside the rotary grinding mill 500, which is needed for the analysis. As described below, each data set 501*, ... 506* is first positioned and aligned before being combined into the point cloud data 500* used for the analysis. Returning to the generation of the point cloud data 500* represented in Fig. 2B, the combination of datasets 501* and 502* is performed as follows. After acquiring the two datasets 501* and 502*, features 520* are extracted from the first and second datasets. In this document, features 520* may represent markers, edges, surface structure patterns, and / or surface reflectivity patterns of the explored surfaces, and are illustrated by a dotted surface in Fig. 2B for simplicity. That is, the combination of datasets can be performed based on positional or structural features and / or reflection property features. Although the first and second datasets 501* and 502* may have already been approximately aligned during the scan procedure described above, discrepancies due to discontinuous or erroneous sampling of orientation and position information (e.g., due to integration errors) still need to be corrected. Furthermore, if either or both orientation and position information cannot be obtained, the positioning and alignment of datasets 501* and 502* cannot be achieved during the scan procedure described above and may need to be performed differently. Therefore, the first and second datasets 501* and 502* are positioned and aligned using the extracted features 520* and combined into the point cloud data 500*.More specifically, when part of the explored surface is represented by both data sets 501*, 502* (for example, when data sets 501*, 502* overlap as shown in Fig. 3A), the data sets 50Γ, 502* can be scaled, translated, and / or rotated to overlap their corresponding features 520* until they are correctly positioned and aligned. This achieves and / or improves the positioning and alignment of the two data sets 501*, 502* before combining them into the point cloud data 500*. In this respect, the 520* characteristics mentioned above may be markers ML / IOO markers placed in predetermined locations within the rotating receptacle 510 may have the shape of the lining 520 itself and / or may be a pattern of a surface texture, surface composition, or surface material indicated by the intensity information of the data points 540*. Since the markers, lining 520, and materials within the mining equipment are of a definite and identifiable shape and property that are also represented in the acquired data sets 501*, 502*, feature detection, edge detection, line tracing, or segmental interpolation fitting can be performed along the data points 540* or a surface represented by the data points 540* in the data sets 501*, 502* to extract such features 520*.In this respect, positioning and alignment may involve a linear transformation, preferably rotating, scaling, and / or translating the first and / or second data sets 501* and 502* to maximize feature correlation, alignment, and / or matching. Based on a feature difference 520* between the first and second data sets 501* and 502*, feature correlation, alignment, and / or matching can be quantified. For example, a least-squares error can be used as a quantifier for feature correlation, alignment, and / or matching. Based on point cloud data 500*, changes in the structure or shape of the internal surface of mining equipment, such as the rotating receptacle 510, can be detected. For example, changes can be detected compared to a previous inspection, in the original structure or shape, or similar. These changes may indicate wear and / or deformation of the mining equipment, the liner 520, an inlet system (not shown), and / or the discharge system 530. As a result, it can be assessed whether replacement or maintenance of the liner 520, the inlet system, or the discharge system 530 of the mining equipment is necessary to maintain the operation and safety of the mining equipment, such as the rotating grinding mill 500. The visual inspection methods described below can be used to perform this assessment and determine the point cloud data 500*. To enable the assessment of changes in structure or shape, the entire structure of the 500 rotary grinding mill must be explored. Alternatively, if a specific area of ​​the mining equipment is of interest, then a corresponding portion of the entire structure must be explored. In either case, the exploration must be a complete scan of the structure or shape of interest and have a specified quality / resolution. Otherwise, the assessment may fail due to incomplete or low-quality / low-resolution data. To ensure that the exploration is complete and of at least a given quality / resolution, a 510* geometry of the mining equipment, e.g., the 500 rotary grinding mill, is estimated based on the 500* point cloud data, and a 550* region of the estimated 510* geometry indicating insufficient data or a region of interest is identified using the 500* point cloud data (see also Fig. 3B).Furthermore, when the position and orientation information of sensor 30 is provided, an indication of (or an indication of a direction towards) the region indicating insufficient data or the region of interest can be provided without having to first estimate the geometry. Regarding geometry estimation, this can be performed by positioning a basic geometry 510*, for example, a cylinder in the case of the rotary grinding mill 500, onto the point cloud data 500* (consisting of the data sets 50Γ,... 506* in Fig. 3B). A basic geometry can be considered as a collection of three-dimensional points that can be joined by edges to form faces between the edges. The number of points in the basic geometry 510* should be kept as low as possible to minimize the computational load, while still achieving a basic representation of the point cloud data 500*. In this paper, an R-squared error between the basic geometry 510* and the data points 540* from the point cloud data 500* can be 0.75, preferably 0.8 or 0.9. The basic 510* geometry can be translated, rotated, and scaled until the difference between the basic 510* geometry and the 540* data points of the 500* point cloud data is minimized (e.g., by using least squares regression or maximizing correlation). It should be noted that the impactor 200, the high-pressure grinding rolls 300, the agitated grinding mill 400 (represented in Figs. 1B to 1D), and the horizontal or vertical mill can also use one or more cylinders as basic 510* geometries, while the compression crusher 100 (represented in Fig. 1A) can use a pair of planes as its basic 510* geometry. In this document, a basic 510* geometry with a low number of faces, for example, below a certain number of faces, such as below 100, is used when estimating the geometry of mining equipment to ensure that manipulation and comparison with the basic 510* geometry is not computationally intensive. It should also be mentioned that the point cloud data can be meshed first, and then the basic geometry can be positioned on and compared to the mesh. During meshing, the coordinate information of each data point can be treated as a vertex and connected to its neighboring vertices (for example, based on the coordinate information of other data points) via edges to form faces. By applying smoothing filters and / or vertex merging filters to the mesh, the number of edges, vertices, and faces is reduced. Consequently, comparing the basic geometry to the filtered mesh to align the basic geometry becomes even less computationally intensive. By using basic geometry 510*, gaps or missing data in point cloud data 500* can be identified and reported. For example, when data-deficient points 540* are located on or near the surface of basic geometry 510*, a data-deficient region 550* can be determined. In other words, such gaps indicate missing data that can be identified using basic geometry 510*. A region 550* indicating insufficient data can be identified as follows. Data sets 501*, ... 506* can be mapped onto the surface of the basic geometry 510*, and regions of the basic geometry 510* not covered by data sets 501*, ... 506* can be identified as the region 550* indicating insufficient data. In this document, the circumference of each data set 501*, ... 506*, based on the scan range 31 of sensor 30, can be used to maintain tracking of the scanned and unscanned surface of the basic geometry, allowing for a determination of the (missing or) insufficient data region. Similarly, the number of data points 540* within an area, i.e., the “point density of MA / Ί OO mode, the xy function can be determined by normalizing the 500* point cloud data based on the basic 510* geometry. When any of the above methods are applied, the expert understands that if a change in the distance dy or in the mathematical gradient / differentiation of the xy function exceeds a certain threshold, this region is determined to be a region of high detection inaccuracy. This region of high detection inaccuracy can also be mapped onto the surface of the basic geometry 510* as region 550*, indicating insufficient data. Similarly, the scan shadows 32 that produce discontinuities in the data sets 501*, ... 506* and the point cloud data 500* can also be identified on the surface of the basic geometry 510* and determined to be region 550*, indicating insufficient data. Given region 550* indicating insufficient data, if inspection personnel are “virtually painting” with sensor 30, information about the scan can be transmitted to enable personnel to correct the “virtual painting.” For example, a display can indicate the location of region 550* indicating insufficient data. In this document, region 550* indicating insufficient data may be referred to as an identified region 550* (e.g., one that has been identified on the surface of basic geometry 510*) and may be color-coded or otherwise highlighted to notify inspection personnel of its location relative to the position and orientation of sensor 30. The display then instructs and / or guides inspection personnel to move sensor 30 so that the identified region 550* is rescanned.In addition, the identified region 550* can also be used to automatically reorient and / or move sensor 30 to re-explore the identified region 550*. The following describes a procedure for guiding a user or inspection personnel to region 550*, identified in reference to Fig. 8. In this document, if the total area of ​​the identified region 550* is equal to or greater than a predetermined size (e.g., above a predetermined value), the guiding procedure is repeated to continue exploring the identified region 550*. Once the area of ​​the identified region 550* is smaller than the predetermined size (or below the predetermined value), the guiding procedure concludes that sufficient data of sufficiently high quality has been obtained to perform the analysis. More specifically, during the guiding procedure, the screen visually displays a portion of the basic geometry 510* (S11) and identifies an area of ​​the identified region 550* (S12). However, based on the orientation of the displayed view, for example, due to the position and rotation of sensor 30, the identified region 550* may be outside the scanning range 31 of sensor 30. Therefore, if the area of ​​the identified region 550* is greater than or equal to a predetermined size (S13: YES), the guiding procedure determines a “next coordinate” (S14). A next coordinate is associated with or lies within the identified region 550* and is preferably located on the surface of the basic geometry 510*.This next coordinate is extracted and highlighted (S15), for example by visually presenting part of the surface of the basic geometry 510* near the next coordinate in a different color, or by animation with an arrow on the screen pointing in a direction in which the sensor 30 should be rotated and / or translated, i.e., moved, so that its scan region 31 covers the next coordinate. MA / Ί OO Figures 12A and 12B illustrate an example of a visual representation of a next coordinate. In Figure 12A, a scan comparable to that in Figure 2B has been performed, in which an identified region 550* must be scanned to complete the scan procedure. A next coordinate 541* has been identified within the identified region 550* and serves as the target for further scanning. Assuming the scanning device is currently pointing toward the region marked CC in Figure 12A, the scan range of this device does not cover the next coordinate. More specifically, an example visual representation corresponding to the scan region as depicted in Figure 12B includes neither the identified region 550* nor the next coordinate within the field of view. Therefore, an arrow 542* can be superimposed on the visual representation in Figure 12B.12B to indicate a direction in which the sensor should move to cover the next coordinate 541* and explore the identified region 550*. Thus, the guidance procedure causes sensor 30 to move, or be made to move, in a direction toward the next coordinate until the next coordinate falls within a scan range 31 of sensor 30 (S16). As a result, the identified range 550* is re-scanned, thereby adding more data to the point cloud data 500* and reducing the size of the identified region 550* area (e.g., the data-insufficient region 550*). It is worth noting that by determining the location of the next coordinate within the identified region 550* as close as possible to the edge of the sensor 30's scan range 31, the movement required to re-scan the identified range 550* is minimized. Determining the next coordinate in this way speeds up the scan procedure, as it minimizes the movement of sensor 30. This can be particularly beneficial when sensor 30 is controlled automatically, for example, by a robot or drone with limited battery life and time to perform the scan.Alternatively, when sensor 30 is moved manually, and a user or inspection personnel is notified of the position of a next coordinate and instructed to move sensor 30 in a direction toward the next coordinate until the next coordinate falls within the scanning range 31 of sensor 30, the physical work and strain on the user or inspection personnel is reduced when the necessary movement is minimized as described above. When the next coordinate falls within the scan range 31 of sensor 30, sensor 30 acquires an additional data set 503*, for example, a third set, comprising data points 540* at coordinates as described above (S17). To then combine this third data set 503* with the already acquired point cloud data 500*, features 520* are extracted from the point cloud data 500* and the third data set 503* as described above (S18). The third data set 503* is then positioned and aligned with the point cloud data 500* and combined to yield the point cloud data 500* as described above (S19). The guidance procedure then re-estimates the basic geometry 510* and re-guides the scan of the remaining identified region 550* (S19 to S11). Since more geometry information and details of the mining equipment are captured and represented by the 500* point cloud data, the subsequent 510* geometry estimate is improved. The basic ML / IOO of the mining equipment is based on the updated point cloud data 500*. Furthermore, since the point cloud data 500* has increased or changed, the region 550* indicating insufficient data may have decreased or changed as well. Therefore, the region 550* identified in the re-estimated geometry 510* associated with insufficient or low-quality data is also re-identified as described above (S12), but using the updated point cloud data 500*. As a result, the area of ​​the identified region 550* may decrease or change. The guiding procedure described above, from re-estimating and visually presenting the basic geometry (S11) to updating the point cloud data, is repeated as long as the identified area of ​​the identified region (S12) is greater than or equal to the default value (S13: YES). If multiple identified regions have been identified, the guiding procedure described above is repeated as long as the sum of the areas of all the identified regions is greater than or equal to this default value. Once the identified 550* region area falls below the predetermined value (S13: NO), analysis (e.g., damage, wear, and / or degradation analysis) is performed based on the 500* point cloud data, and the exploration procedure ends (S20). This ensures that the completeness and quality / resolution of the 500* point cloud data are maintained because the 550* data area is below a certain threshold. As a result, the inspection duration remains short, improving the safety of inspection personnel and reducing mining equipment downtime. Without this human-machine guidance procedure, data may be omitted, insufficient, or erroneous, which will only be discovered during the subsequent analysis of the acquired point cloud data. Therefore, unnecessary repetitions of the scanning procedure are avoided. For the human-machine guided procedure, the aforementioned display can be installed with sensor 30, for example, if the scanning device comprising the display and sensor 30 is portable. When the position and orientation of sensor 30 are remotely controlled from outside the mining equipment, the display can be part of an augmented reality (AR) or virtual reality (VR) kit worn by personnel. VR can also be used if sensor 30 is supported by a flying drone or a robotic suspension device mounted on the mining equipment. As a result, inspection personnel can still perform the “virtual painting” but do not need to enter the hazardous environment inside or near the mining equipment. If the movement of sensor 30 is controlled autonomously, for example by a control system that directs the flight drone or the suspension device, the flight or movement plan can be corrected dynamically, based on the identified coordinates. [Main / Independent Component Alignment] When a new dataset 501*, ... 506* is combined with another dataset 501*, ... 506* or point cloud data 500*, principal components (PCs) or independent components (ICs) can be extracted from the features 520* for alignment of the new dataset 501*, ... 506* ML / IOO data (hereafter, PCs may also include ICs). After all, PCs are unique indicators for each 520* feature that indicate the orientation and scale of the corresponding 520* feature. Therefore, with low data and processing requirements, PCs can be linearly transformed to bring them into alignment, allowing for faster alignment of the 520* features and, consequently, the new 501*, ... 506* dataset. For example, alignment between the datasets 501*, ... 506* and / or the point cloud data 500* can be indicated by a dot product of the features 520*, and preferably the PCs. If multiple features 520* and / or PCs have been extracted, alignment between the datasets 501*, ... 506* and / or the point cloud data 500* can be indicated by convolution and / or correlation of the features 520*, and preferably the PCs. Since dot product, convolution, and / or correlation can provide (in addition to the previously mentioned least-squares regression) an indication of alignment or matching, the operation on the PCs can be performed with a significantly lower computational load compared to the same operations performed on the data points 540* of the extracted features 520*. With regard to this, and as previously described, the alignment of the PCs also comprises a linear transformation, preferably rotation, scaling and / or translation of the data set 501*, ... 506* and / or the point cloud data 500* to maximize alignment and / or matching. [Data acquisition during operation] As described above with reference to Figs. 2A to 2D and Figs. 3A and 3B, point cloud data can be acquired by moving a sensor 30 relative to mining equipment (e.g., the rotary grinding mill 500) to acquire complete, high-quality point cloud data using an automated procedure or a continuously guided human-machine interaction (e.g., the guiding procedure in Fig. 8). The embodiment described above refers to inspecting mining equipment during downtime. A further embodiment for inspecting mining equipment while it is in operation is described below. To better illustrate and explain the following embodiment, the 500 rotary grinding mill and its geometry are used to explain the procedure for inspecting operating mining equipment. However, other types of mining equipment can be used equally well (as described above or depicted in Figs. 1A to 1E). Figures 4A to 4E depict a sensor 30 within a rotary grinding mill 500, i.e., the rotating receptacle 510 thereof. In this case, the rotary grinding mill 500 is in operation and rotates, for example, in direction B, thereby performing its mining operation on the mining material 10 with the aid of a liner 520, which is installed inside the rotary grinding mill 500. The sensor 30 is moved through the interior of the mining equipment, for example, by rotating it, for example, in direction C (see Figures 4A to 4C) and / or by moving it essentially parallel to the axis of rotation of the mining receptacle 510 (see Figure 4D (non-rotating sensor) and Figure 4E (rotating sensor)). In this case, the mining equipment, i.e. the 500 rotary grinding mill, rotates around its axis of rotation when it is in operation.Using sensor 30, first point cloud data and second point cloud data from the mining equipment are acquired in a manner similar to the procedure described above and shown in Figs. 3A and 3B, in which multiple sets 501*, ... 506* of partially overlapping data are acquired, positioned, aligned, and combined to give each of the 500* point cloud data. In the present embodiment, the first and second point cloud data represent different passes or explorations of a surface within the mining equipment. This surface may be the structure of the mining equipment (or its cladding 520) or it may be mining material 10 (e.g., rocks or mud) on or covering the surface of the mining equipment structure. An overlap of the first and second point cloud data represents the same part of the mining equipment, but at different times and / or orientations. Figures 4A to 4C are used to illustrate how different point cloud data (representing different passes or scans of the same surface of the mining equipment) can be obtained. For example, to acquire the first point cloud data, sensor 30a can begin scanning the interior of the rotating receptacle 510 with a scanning range 31 oriented as shown in Figure 4A. Sensor 30 is then rotated 360°*n+90° in direction C (where n is a natural number including zero), and the rotating receptacle is rotated 270° in direction B until the situation depicted in Figure 4B is reached. In this document, the scanning range 31 of sensor 30 has been rotated at least (n+1)*360° with respect to the mining equipment.By continuously exploring—for example, by acquiring, positioning, aligning, and combining datasets—throughout the entire rotation, sensor 30 can explore the entire inner surface of the rotating receptacle 510 at least once. Therefore, based on the output of sensor 30 during the transition from Figs. 4A to 4B, the first point cloud datasets are acquired. The same procedure is repeated when transitioning from Fig. 4B to 4C, and the second point cloud datasets are acquired. In other words, the second point cloud datasets are acquired after the first point cloud datasets and after sensor 30 and / or the mining equipment have been moved.As a result, the first and second point cloud data acquired represent the same parts of the mining equipment structure (e.g., the 500 rotary grinding mill), but with different obstructions of the explored surface caused by mining material such as rocks and mud (the latter not represented). It should be noted that sensor 30 may also have rotated faster, achieving a total rotation of 90° + n * 360° (for example, where n is a natural number greater than zero) in Fig. 4B, compared to Fig. 4A. In this way, sensor 30 scans the unobstructed inner surface of the mining equipment (at least partially) more than once. This allows for the acquisition of higher-quality initial point cloud data, particularly since the occurrence of shadows 32 can be avoided (see Figs. 2C and 2D). Avoiding shadows can be achieved particularly when sensor 30 is not located at the center of rotation of the mining equipment (for example, the rotating receptacle 510) but in an offset arrangement. In this arrangement, sensor 30 scans surfaces at different angles, allowing for compensation of scan shadows, for example, due to a lining 520 without MA / 1000 obstructions protruding into the rotating receptacle 510 at a specific angle. For example, in Figs. 4A to 4C, the sensor can be positioned further to the upper right to extend the scanning range 31 into a region behind the liner protrusions 520. In this way, sufficient and high-quality initial point cloud data can be obtained. The same applies to the subsequent point cloud data. Furthermore, if there is no significant exploration shadow, for example, if no liner 520 is present or if its protrusions are negligible for the exploration operation, sensor 30 may not rotate at all, and only the rotating receptacle 510 may rotate during the acquisition of the first and second point cloud data. To minimize the possibility that the surface of the mining equipment explored by sensor 30 is covered or obstructed by the mining material 10, sensor 30 can be made to point in a direction where most of the mining material 10 has most likely been shed or slid off the surface (e.g., Figure 4A).Additionally, when using a stationary or non-rotating sensor 30 of this type, rigid protection against the mining material 10, such as a cage, can be installed around the sensor 30, but without extending into the exploration range 31. To avoid synchronizing the rotation of the sensor 30 and the rotating receptacle 510, the sensor 30 is preferably rotated in a direction C opposite to the direction of rotation B of the mining equipment. When rotating in opposite directions, the sensor 30 can rotate at any angular velocity, for example, faster than, as fast as, or slower than an angular velocity of the mining equipment. However, point cloud data acquisition is terminated once the interior of the mining equipment has been explored at least once. Furthermore, the method explained in the [Data Acquisition] section can also be used to acquire the point cloud data 500*. In this document, the identified region 550* can be explored when the surface of the mining equipment associated with the identified region 550* is less likely to be covered or obstructed. For example, the surface of the mining equipment within exploration range 31, as shown in Fig. 4A, is less likely to be covered by mining material 10, whereas the surface of the mining equipment within exploration range 31, as shown in Fig. 4C, is more likely to be covered by mining material 10.Therefore, the rotation of sensor 30 can be automatically adjusted so that the alignment of the exploration range 31 with the identified region 550* (or the next coordinate mentioned above) occurs at a time when the surface of the mining equipment associated with the identified region 550* is least likely to be covered or obstructed by the mining material 10 (e.g., Fig. 4A). Furthermore, to prevent the mining material 10 from moving excessively and / or unnecessarily obstructing the exploration range 31, the mining equipment 500 can rotate at an angular velocity equal to or less than a certain angular velocity during normal operation. In this document, the mining equipment 500 can be continuously “moved slowly” (e.g., moved forward at a very slow angular velocity), thus avoiding the need to stop and fix the mining equipment 500 between each exploration iteration.To protect sensor 30 from mining material, for example trapped and falling from the liner 520, a cage surrounding sensor 30 can be provided. MA / Ί OO After acquiring the first and second point cloud data from sensor 30, data points constituting the surface of the mining equipment are derived from the first and second (i.e., multiple) point cloud data. This paper utilizes the fact that the mining equipment continues to rotate during exploration, as its rotation reveals a surface of the mining equipment that would be covered by rocks or mud if the equipment were explored while stationary. An example of a method for determining the data points that constitute the surface of the mining equipment is described. First, surfaces within the mining equipment are determined based on each of the first and second point cloud datasets. Then, based on the determined surfaces, a location for the data points that represent a surface within the mining equipment is estimated, and point cloud datasets are generated based on this estimate. For example, for each point cloud data point, a surface of the interior of the mining equipment is determined and stored. The surfaces determined from each point cloud data point are then aligned and compared to classify or estimate which parts of the surfaces represent the structure of the mining equipment and which parts represent the mining material (e.g., rocks or mud) covering the structure. In this document, the alignment can be performed similarly to the feature extraction and alignment described earlier. However, information regarding the relative rotation of the sensor and the mining equipment can be used for the initial alignment, while the fine alignment is performed using the previously described alignment procedure that uses extracted features.For example, to aid in alignment, a reference marker on the mining rig and sensor 20 can provide information regarding their respective orientations. Additionally, control commands can be used to rotate the mining rig and / or sensor 30 to determine their current orientation. Therefore, the first and second point cloud data acquired are rotationally corrected based on the rotation angles of the sensor and the mining rig. Based on this classification or estimation, only the portions of the surfaces that represent the structure of the mining equipment are extracted, combined, and used to estimate the geometry or data points corresponding to an interior surface of the mining equipment. An example of this estimation is explained below. Referring to Fig. 5A, it is assumed that first and second point cloud data (e.g., Figs. 5A(a) and (b)) are acquired using the method described above. For simplicity, the mining material and lining are omitted, and only a section of the rotating receptacle 510 and the mud 11 is shown in Fig. 5A. However, the same procedure can be applied equally to mining material 10 other than mud 11. Since the rotating receptacle 510 rotates and is subjected to changing or variable forces from the mining material 10 and / or the mud 11, the coating or lining on the inner surface of the rotating receptacle 510 changes from a first scan to a second scan. Therefore, the corresponding first and second point cloud data indicate different inner surfaces even though they scan (at MA / IOOO less partially) the same surface of the mining equipment. Based on the first and second point cloud data (and / or additional point cloud data, for example some third to fifth point cloud data in figs. 5A (c) to (e)) multiple explored surfaces corresponding to the same surface of the mining equipment are aligned and compared. For example, as shown in Fig. 5B, a probability density or frequency 11* can be acquired from the multiple point cloud data indicating the frequency or probability of a surface being at a certain distance from sensor 30. More specifically, focusing on region BB in Fig. 5B, a Weibull-type distribution like the one depicted in Fig. 5C can be produced. In this paper, the probability density or frequency p of a surface varies with changes in the distance d to sensor 30. In the example in Fig. 5C, the highest probability density is at distance d(1). In this case, it is assumed that the closer distances toward d(2) may have been caused by mud 11 adhering to the surface of the mining equipment structure.Furthermore, it is assumed that the closer distances to d(0) may have resulted from measurement errors or from measurements taken on a cleaner surface than usual. In a case where the measurement error is sufficiently small, for example, achieving a measurement tolerance of ±0 mm to ±50 mm, preferably ±1 mm to +10 mm or ±1 mm to ±5 mm, the distance between d(0) and d(1) can be reduced to zero. Based on this probability density distribution, the distance from sensor 30 to the surface of the mining equipment can be classified as being between or above the distances d(0) and ad(1). When the measurement error is negligible, the distance from sensor 30 to the surface can be determined to be d(1). When this classification is applied not only to region BB but to the entire circumference or surface of the mining equipment, the surface area of ​​the mining equipment, and therefore the geometry of data points representing a surface within the mining equipment, can be estimated even while the mining equipment is in operation. The resulting point cloud data comprising these estimated data points can then be used in subsequent analysis. As a result, the estimation can be performed without stopping the mining equipment.Therefore, not only is downtime of the mining equipment reduced, but it can even be avoided. [Inspection system] As previously mentioned, a display portion of a computer monitor, AR kit, or VR system can be used to assist in the inspection of mining equipment. Further details regarding inspection using an inspection system 50 with a display 60 are presented below, with reference to Fig. 9A. In this document, the inspection system 50 further comprises a sensor 30 configured to detect a distance to a surface (also referred to as “scanning”), for example, inside mining equipment, a tracker 51 configured to track the location and orientation of the sensor 30, and a point cloud generator 52 configured to generate point cloud data based on the detected distance and the location and orientation tracked by the tracker 51. In this document, the tracker 51 may be implemented with the sensor 30 and output as tracking information from the sensor 30, or the tracker 51 may not be implemented with the sensor 30. MA / IOD example alongside point cloud generator 52. Most importantly, sensor 30 and tracker 51 are configured to send their data to the point cloud generator, which can be configured to sample, for example at regular sampling intervals, coordinate values ​​and angle values ​​related to the location and orientation of sensor 30. In addition, point cloud generator 51 is configured to calculate the coordinates of the surface detected by sensor 30. These calculated coordinates constitute the individual data points of the point cloud data.When sensor 30 is configured to detect various distances to a surface, for example by producing a depth image or depth map, each detected distance can be used to calculate a coordinate of the surface, allowing multiple coordinates to be calculated simultaneously, which increases the scanning speed. In other words, if a depth image is produced, each pixel location in this depth image corresponds to a horizontal and vertical angle with respect to the sensor's central detection axis, and each pixel value corresponds to the distance from sensor 30 to the surface (sensor 30 in other embodiments can similarly use a depth image). Therefore, the point cloud generator 52 can be configured to generate a data point associated with each pixel when calculating the coordinates that constitute data points from the point cloud data. The inspection system 50 further comprises a surface estimator 53 configured to estimate one or more surfaces based on point cloud data and a geometry estimator 54 configured to estimate a (basic) geometry of the mining equipment based on the estimated surface(s). The display 60 is configured to visually present the estimated surface and / or estimated geometry. In this document, the display 60 can be combined with the point cloud generator 52, the surface estimator 53, and the geometry estimator 54, but alternatively, it can be a standalone device. The surface estimation and geometry estimation can be performed similarly to what is described above, for example, in the [Data Acquisition] section.The (basic) geometry of the mining equipment can be used to indicate a 550* region that indicates insufficient data (e.g., the identified 550* region) in order to ensure the completeness and / or quality of the acquired point cloud data. Preferably, different shading, contouring, coloring, or similar methods can be used to indicate differences in point cloud data density and / or differences in the certainty of estimated surfaces and / or geometry as visual feedback. In this document, uncertainty can be based on the coefficient of determination or R² value of an estimated portion of a surface and / or geometry.More specifically, this visual feedback provides information to the user or inspection personnel, for example, information about a 550* region indicating insufficient or low-quality data. This allows the user or inspection personnel to quickly identify the region and ensure that the acquired point cloud data is sufficiently populated with high-quality data for subsequent analysis; for example, by re-exploring the mining equipment parts corresponding to that region as described above. Visually presenting the estimated surface and / or geometry in this way is also beneficial during inspection. MA / IOO mining equipment remotely, for example when it is operational and the user or inspection personnel in charge of the inspection cannot enter the mining equipment. Furthermore, tracker 51 can be configured to also track the location and orientation of screen 60, and screen 60 can be configured to visually present the estimated surface area (of the mining equipment) based on the location and orientation of screen 60. Consequently, the use of AR or VR kits allows the user or inspection personnel to better control or direct the location and rotation of sensor 30 in order to acquire point cloud data that is sufficient for subsequent analysis. However, in some cases, the user or inspection personnel performing the inspection and / or targeting of sensor 30 to acquire point cloud data may rely on the expertise of others to ensure that the acquired point cloud data is sufficient for subsequent analysis. Similarly, other individuals may wish to focus the subsequent analysis on regions of interest. Regions of interest might include, for example, areas anticipated to be subject to excessive wear or that have not been inspected for an extended period. Therefore, the point cloud data can be transmitted to a terminal, computer, or VR / AR kit belonging to the expert, allowing that individual to indicate the location(s) of the region(s) of interest on the mining equipment.A virtual flashlight can be implemented and used by the expert to color an area in the (basic) geometry and mark this area as an identified region 550* and / or region of interest. Information about this region(s) of interest is then returned to the inspection system and displayed visually on screen 60, similar to a region 550* indicating insufficient data (e.g., identified region 550*). The user or inspection personnel can then be informed about this region and can perform the exploration based on expert knowledge. However, transmitting point cloud data from the entire mining rig may not be an option, for example, when the communication link between the inspection system and the expert is insufficient for large data transmissions. Therefore, at least the region of interest to the mining rig should be explored, and its data transmitted to reduce the overall amount of data sent. Accordingly, and as illustrated in Fig. 9B, the inspection system 50 may further comprise a remote display 61, for example, where the expert is located, a mining equipment database 55, a subcloud determiner 56, and a data transceiver 57. In this document, the mining equipment database 55 is configured to store a template geometry of the mining equipment, for example, based on CAD data of the mining equipment, and a region of interest of the mining equipment. The subcloud determiner 56 is configured to extract a subset of data from the point cloud data as subcloud data based on the region of interest. The mining equipment database 55 and the subcloud determiner 56 may be located next to the tracker 51, the point cloud generator 52, the surface estimator 53, and the geometry estimator 54, as depicted in Fig.9B. ML / IOOO In this document, data transceiver 57 is configured to transmit subcloud data to and from remote display 61. This transmits the region of interest to the expert and returns their input (e.g., input via an input device near the remote display 61) to enable the display of the input on display 60. Alternatively, the mining rig database 55 and the subcloud determinator 56 may not be located next to the tracker 51, etc., as described above. For example, when large servers are required to store the template geometry for all mining rigs, it may not be feasible to house them on a device next to the tracker 51, etc. In this document, the transmitter 57 transmits data, including the estimated geometry and an indication of the explored surface, to the subcloud determinator 56. In this document, the indication of the explored surface may be a difference in the color or parameterization of the estimated geometry based on the explored point cloud data. In this way, it is not necessary to transmit all the point cloud data to indicate which region / part of the estimated geometry has been explored.After receiving this data, subcloud determiner 56 extracts the mining rig template geometry from the mining rig database 55 and overlays it with the received data. Then, subcloud determiner 56 causes screen 61 to visually display the template geometry with overlaid data, informing the person at the remote screen 61 which part(s) of the mining rig have been explored. Furthermore, the person providing expert knowledge can enter into the mining equipment database which part of a mining equipment template geometry constitutes a region of interest. This entry can be done in advance, before the inspection, or remotely during the inspection. In the latter case, entering and specifying a region of interest and transmitting information about that region requires a relatively small amount of data, which can still be transmitted over the previously mentioned communication link. Consequently, a remote computer can be located next to the remote display, configured to receive inputs for defining another region of interest and to store that region of interest in the mining equipment database. In the case where the mining equipment database 55 and the subcloud determiner 56 are configured with the crawler 51, etc., the subcloud determiner 56 can locate, based on a comparison between the template geometry and the estimated geometry, the region of interest in the estimated geometry and extract a subset from the point cloud data 500* as subcloud data to be transmitted. In this document, the subcloud data can be transmitted each time it is updated by the scan (e.g., continuously) or once the scan is complete, for example, when the identified region 550* is sufficiently small.When subcloud data is transmitted each time it is updated, new mining equipment information can be visually displayed on the remote screen 61, allowing the expert to determine whether a new point of interest can be added to the mining equipment database 55. Therefore, collaborative exploration by the user or inspection personnel can be achieved based on feedback from the expert, ensuring that the exploration covers all regions of interest before performing the mining equipment analysis. Furthermore, the amount of data transmitted by transceiver 57 is reduced. Additionally, screen 60 can be configured to highlight the region(s) of interest to indicate the region of interest to the user or inspection personnel acquiring the point cloud data. Therefore, particular emphasis can be placed on acquiring the point cloud data that constitutes the subcloud data. As a result, the user is guided in performing the data acquisition or exploration to ensure that the point cloud data that constitutes the subcloud data is of sufficient quality and complete. This emphasis can be particularly important if different quality thresholds are applied to different regions of interest (for example, by determining a different maximum variance of data points from different regions of interest). If the 500* point cloud data does not include any data points in the region of interest, the estimated surface and / or geometry(ies) can be highlighted at a location within the region of interest. This highlighting can be visually represented on screen 60 using colors or an arrow, as previously described. To detect regions that do not include (enough) data points, a gap detector can be used. This detector is configured to detect coordinates in the estimated geometry where the number of point cloud data points falls below a predetermined value. Alternatively, the surface gradient is calculated as previously described, and a gap is identified where the gradient exceeds a predetermined value.Therefore, these detected coordinates constitute “gaps” in the 500* acquired point cloud data that can be highlighted in the estimated geometry that is visually presented on screen 60. The above is summarized in the feedback procedure depicted in Fig. 10. In this document, the inspection system 50 acquires one or more regions of interest from the mining equipment database 55 (S101). Next, the mining equipment is explored (e.g., following a procedure described above), and point cloud data 500* of the mining equipment is generated (S102). The estimated surface area and / or estimated geometry are then visually displayed on screen 60 with an indication of the region of interest (S103). In this document, the indication can be colors or an arrow pointing in the direction of the region of interest. Finally, point cloud data 500* is transmitted to the remote screen 61 (S104).In this document, all the aforementioned 500* point cloud data or subcloud data (corresponding to the 500* point cloud data in the region(s) of interest) can be transmitted. The region of interest can then be updated and inserted into the mining equipment database (S105), for example, if the expert identifies new regions of interest during exploration. If the 500* point cloud data is determined to be sufficient (e.g., sufficiently dense) and of sufficiently high quality (e.g., with low data point variance) in all regions of interest (S106: YES), the inspection analysis (S107) is performed. Otherwise (S106: NO), the procedure re-triggers or reacquires the points of interest (including any new points of interest) and continues the guided exploration. [Virtual inspection] According to another embodiment, a computer-implemented method is provided, as shown in Fig. 6, for a virtual inspection of the interior of mining equipment (as described above). Virtual inspection refers to a method and technology for the maintenance, examination, testing, monitoring, fault detection, and provision of information regarding the interior of mining equipment from one or more locations outside the equipment by using virtual reality technology, also called augmented reality (AR) or virtual reality (VR) equipment, worn by personnel, such as VR headsets or head-mounted devices like the Oculus Rift, or VR glasses or headsets, which can provide a stereoscopic view to a user. This type of analysis can be performed during or after step S20 in Fig. 8 or step S107 in Fig. 10. According to the first stage (S1) of the computer-implemented method shown in Fig. 6, a first dataset (point cloud data as described above) is acquired. This first dataset comprises coordinate data points of the interior of the mining equipment, such as a horizontal or vertical mill, crusher, grinder, or other mining equipment as previously described. The data points preferably define, in three-dimensional space, the interior of the mining equipment, for example, geometric shapes, surfaces, directions, orientations, alignments, or similar features that define the physical appearance of the equipment's interior. The data points may also include data points of a lining installed on respective surfaces of the mining equipment to protect it from excessive wear.The data points may also include information regarding a reflection property from the explored points of the mining equipment (e.g., a reflection intensity of the sensor's laser light from a surface texture or surface composition at the respective points of the mining equipment), i.e., a reflection property of the material that forms the surface of the mining equipment. Preferably, the first dataset can be acquired using one or more sensors, for example, a sensor 30 described above, a three-dimensional scanning device, a mobile scanning device such as a flying or mobile drone, or a robotic suspension device as described above, or from another source. The first dataset can also include data points from the specified manufacturing dataset, i.e., the definition of the interior of the mining equipment as it was or was originally planned to be manufactured, for example, as defined by a CAD dataset or similar. The expert understands that any of these example datasets can be acquired by entering the datasets into a computing device, such as a laptop computer, a computer workstation, a cloud computer, a computer data server, or similar. According to a second stage (S2) of the computer-implemented method in Fig. 6, the first acquired dataset is subsequently converted into a second dataset that is adapted (e.g., has a suitable format) for use by a virtual or augmented reality device, such as VR headsets, VR glasses, VR helmets, or other mounted VR device ML / I OO in the head as explained above. The expert understands that this conversion mechanism generates a virtual geometry dataset (software-based) that will be used by the virtual or augmented reality device so that the user of the virtual or augmented reality device is given the impression, that is, has the visual perception, of looking at or inside the mining equipment. In other words, the user of the virtual or augmented reality device is given a three-dimensional virtual reality view of the interior of the mining equipment, and can virtually look at and move around inside the mining equipment by moving the virtual or augmented reality device or an external input device to the virtual or augmented reality device in order to inspect the interior of the mining equipment.Furthermore, the virtual reality view can be coordinated with shading or color based on the reflectivity information of the data points to better illustrate which part of the mining equipment is made of which material(s). For example, each pixel in the second dataset can be provided with 3D information that defines the points in space related to the mining equipment, as well as a color or shade value related to the reflectivity information. This improves visual perception when virtually inspecting the mining equipment. Such an external input device can be an external motion controller (such as a control stick), a haptic input controller, recorded movement and rotation of the head-mounted device, or the like. In this case, the previous conversion stage, which can also be considered a post-processing stage of the first acquired dataset, can automatically include a check to verify whether all required or relevant data points (e.g., for the purpose of virtual inspection) have actually been acquired from inside mining equipment. Such a check can be performed with respect to identifying (n)sufficient data, as described earlier. That is, the conversion can be combined with the point cloud data acquisition method described above.In other words, based on the known physical geometry of the mining equipment as manufactured, for example, post-processing can identify missing data points and request those missing data points, for example, by asking the sensor, 3D scanning device, mobile scanning device, or robotic suspension device to acquire them. This avoids a delay in providing the virtual inspection to users. According to a third stage (S3) of the computer-implemented method in Fig. 6, one or more users are guided through the virtual inspection of the interior of the mining equipment based on the second data set by moving a visual perception of the user(s) to one or more points of interest (POI), also referred to as regions of interest above, inside the mining equipment. In this case, POIs inside mining equipment may refer to specific sites inside the mining equipment that are critical wear areas, areas that are specifically prone to wear, specific areas of the lining, areas that have already been inspected in the past and for which the user wishes to obtain updated information regarding a current wear status before making a replacement or similar decision. ML / IOD The movement of the user's visual perception can be achieved in such a way that the user operates the virtual or augmented reality device or an external input device to the virtual or augmented reality device so that a user has the visual impression of moving or looking around the interior environment of the mining equipment and specifically looking or hovering over different POIs. Multiple users can also be represented in virtual or augmented reality as their respective virtual avatars. These virtual representations can follow user inputs to move around the mining rig, for example, by tracking changes in visual perception. This provides an enhanced ability to recognize whether other users are looking at and / or moving toward other parts of the mining rig. The second dataset can additionally include data specifying the POIs so that the VR environment generated for the virtual inspection already includes pointers to the POIs in visual perception. That is, the second dataset can identify areas of the POIs that should be highlighted for visual perception, similar to the highlighting of a previously identified 550* region. Such identification can be achieved, for example, by adding indicators or markers to the POIs defined within the second dataset, and also by defining how the pointers should be generated within the VR environment—for example, a pointer shape, color, orientation, or similar. When multiple users have entered the virtual or augmented reality environment, a change in the appearance of part of the mining equipment presented visually within the virtual reality can be triggered, for example, by using a virtual flashlight. This allows individual users to quickly point out and make other users aware of additional (possibly unmarked) points of interest (POIs). The user(s) can then be guided through the virtual inspection by following the pointers provided for virtual perception. This enables the user(s) to quickly inspect critical areas of the mining equipment, such as areas of specific concern regarding excessive wear. Furthermore, the user can shift visual perception to other areas inside the mining equipment that they identify. For example, during a virtual inspection of the mining equipment's interior, the user can use an external input device connected to the virtual or augmented reality device to add pointers to the second set of data. The expert understands that these added pointers identify three-dimensional positions of specific areas within the VR environment that need to be highlighted in a specific way (specific color, specific symbol, or similar).Such additional pointers can be provided, for example, for areas where an initial wear process is identified by the user (e.g., by observing new cracks or similar) and which should be monitored more closely in the future or should be observed more closely by other users (e.g., remote users) who are simultaneously guided through the virtual inspection. Furthermore, by using an external input device connected to the virtual or augmented reality device, the user can additionally input text information (notes or similar), data, and MA / Ί OO image, audio, or voice data related to the identification of specific sites or areas inside the mining equipment. The expert understands that this added data (e.g., text, image, audio, voice, or similar data) can enhance the user's perception when virtually inspecting the interior of the mining equipment. Therefore, such added data can be introduced to enhance virtual inspection capabilities. Such additional data can also be entered or recorded during the virtual inspection. In particular, multiple users (e.g., on-site and off-site / remote users) can enter different additional data during the virtual inspection regarding specific points of interest (POIs). This additional data, which can be added to the second dataset and thus enhance visual perception, can also include ID tags for specific mining equipment components, part numbers, installation date information, batch information indicating when a component was produced or replaced, stock levels or order status for specific components, component weight information, and similar data. Furthermore, this enhanced parameter information can include details of tests performed on specific mining equipment components, such as test dates, test parameters, and the like. According to another embodiment, the virtual inspection of the interior of mining equipment can be coordinated between two or more users. In this case, by using a motion tracking mechanism for the first user, for example, using a head motion tracking sensor (e.g., using an accelerometer, gyroscope, or similar), and thus identifying a virtual path of the first user in the virtual perception of the inspection of the interior of the mining equipment—for example, moving from a first POI to a second POI, for example, in the context of tracking the propagation of specific cracks in the lining or other forms of wear as described above—the same virtual path is also provided in the virtual or augmented reality device of the second user.In other words, by coordinating the virtual inspection for users, all users are given the same visual perception of the mining rig's interior—that is, they look at the same points of interest (POIs) at the same time. This allows one user to guide others through the virtual inspection of the mining rig and also enhances the other users' visual perception by pointing to specific POIs and adding additional text, image, audio, and voice data, as explained previously. The expert understands that this coordination mechanism can be implemented so that the motion-tracking sensor input from the first user's virtual or augmented reality device is also used by the other users' virtual or augmented reality devices. This can be achieved by enabling the virtual or augmented reality devices to communicate with each other. For example, the first virtual or augmented reality device transmits the motion-tracking sensor input data (received by this device) to the other virtual or augmented reality devices via a wired or wireless connection, so that the other virtual or augmented reality devices access the second set of data based on this motion-tracking sensor input data. MA / Ί OO The expert also understands that coordination between the two users can be applied equally when the first user performs the exploration / acquisition of the initial dataset and the second user conducts a live inspection. In this way, missing or insufficient data can be indicated with a Point of Interest (POI) by the second user, who then guides the first user to that POI to acquire additional data. Simultaneously, inspection of mining equipment regions represented by sufficient data can already take place. According to another embodiment, the second dataset (as explained above) can be transferred to one or more remote users. Remote (or off-site) users can be, for example, users who are not present at the actual geographic location of the mining equipment. Therefore, the second dataset can be generated on-site, for example, when the first dataset is acquired using a 3D scanning device, sensors, and / or mobile devices for the mining equipment, and subsequently shared with other remote users. Thus, the virtual inspection, as described here, can be performed remotely, so that technical experts and engineers do not need to be physically present. According to another embodiment, the virtual inspection can be further enhanced by acquiring additional data points from the initial dataset of the mining equipment's interior, based on a first virtual inspection of one or more points of interest within the equipment. This defines a feedback mechanism, advantageously initiated by a remote user, to acquire additional information regarding the actual interior of the mining equipment, such as geometric shapes, surfaces, directions, orientations, alignments, or similar features that define its physical appearance. This feedback mechanism can be applied, for example, if the virtual inspection identifies a potential wear area within the mining equipment that requires further investigation, for which higher-resolution (spatial) data is needed.This feedback mechanism can also be applied if the virtual inspection identifies specific areas where the actual physical appearance (as acquired using the first dataset) needs to be acquired differently—for example, if a sensor needs to take a measurement from a different angle due to a shadow or similar obstacle, as described earlier. The expert understands that, after acquiring the additional data points, the conversion to the second dataset can be provided for these additional data points from the first dataset. Therefore, the user can receive visual feedback on the additional data points as perceived during the virtual inspection. In other words, the updated virtual inspection can easily indicate whether sufficient additional data points (of higher or similar spatial resolution) have been acquired. According to another embodiment, the first dataset (as described above) can be acquired at different points in time, for example, over the lifetime of the mining equipment, over the course of a month or a year. Defining the first dataset as DS1, it can therefore be acquired at different times t, for example, at three points in time, namely DS1(t1), DS1(t2), and DS1(t3). As such, physical parameters of the actual interior of the mining equipment are acquired, for example, geometric shapes, surfaces, directions, orientations, MA / IOOO alignments or similar, which define the physical appearance of the interior of the mining equipment over time. In addition, the first dataset at these different time points becomes a plurality of the second dataset DS2, i.e., DS2(t1), DS2(t2), and DS2(t3) in this example. Based on these datasets, a virtual inspection of the mining equipment's interior can be provided, enhancing the visual perception of the physical parameter and / or a physical parameter simulation at one or more points of interest. More specifically, based on changes in datasets over multiple time points and when and where points of interest (POIs) have been identified, an artificial intelligence (AI) can be trained to classify the degree or pattern of dataset change at which a POI is likely to occur. Consequently, an initial estimate of POIs can be provided during exploration without requiring input from a second user regarding potential additional POIs. For example, with respect to one or more specific points of interest (POIs), a temporal wear profile or a temporal trend profile can be determined based on lining dimensions, a heat map, or similar data, and this information can be provided during the virtual inspection when the user moves to the specific POI. Therefore, the virtual inspection can be delivered in a way that allows for a virtual inspection of the current state of the mining equipment's interior, along with a real-time visual understanding of the temporal development of specific POIs within the equipment over time. This can also be enhanced by comparing the specific POIs to their original design (e.g., using a comparison of CAD models, alternative designs, or similar). A simulation of a physical parameter can be performed based on its known development, such as measured lining dimensions, lining cross-sections, or similar, by applying a simulation algorithm that predicts the parameter's further development. For example, by determining a time constant that identifies how the physical parameter (lining thickness at a point of interest, etc.) has decreased over time, a simulation algorithm can be applied to predict how the parameter is likely to develop. Experts understand that this provides an improved mechanism for informing the user about a predicted time when specific mining equipment components need replacing. This improves the coordination of mining equipment downtime, which can be comparatively lengthy and lead to significant operating costs. Furthermore, the second dataset can also be augmented with additional physical parameter information regarding one or more points of interest (POIs) within the mining equipment. This additional physical parameter information could be, for example, a video sequence showing the appearance of the mining equipment components or how they behave under real-world operating conditions, such as during the grinding, crushing, or milling of minerals or ore. This can also include additional simulations of load movement, material flow, grinding, size reduction, or similar processes, providing the user with further information on shear distribution, impact, power consumption, and similar factors throughout the mining equipment's interior, and thus, its lifespan. This additional physical parameter information can also include a MA / Ί OO comparison of the current state of the coating with the original coating design. Virtual inspection can be further enhanced by providing a virtual measuring device or tape measure. The virtual measuring device can be used by the user to determine a dimension within the provided VR environment, as perceived by the user visually. For example, a user can place the virtual tape measure along an identified crack (or other forms of wear as described above) inside the mining equipment and specify the dimension (e.g., a length) of the crack. The computer then processes the specified dimension data (in the virtual space defined by the second set of data) and performs a conversion to provide a dimension in the real space as defined by the first set of data.As such, the user can be provided with direct feedback regarding the actual size of a newly identified crack inside the mining equipment. Furthermore, virtual inspection can be enhanced by providing a virtual cross-section analyzer that visually displays a cross-section or outline of a mining equipment surface. For example, a user can draw or project a line onto the mining equipment surface, and any bulges or depressions identified along this line can be visually represented as a diagram within the virtual environment. This makes it easier to identify deformations or damage to the mining equipment surface. Figure 7 is a schematic illustration of a computer device 40, which, as in the prior embodiments, can be configured to implement the computer-implemented methods described above and defined in the claims, and thus function as a mining equipment inspection device. The computer device 40, which may also be referred to as programmable signal processing hardware 40, comprises a communication interface 41 (I / F) for acquiring, in embodiments such as the present embodiments, mining equipment data from a sensor 30, exploration apparatus, or mobile device, as described above.The computer device 40 further comprises a processor 42 (e.g., a central processing unit, CPU, or graphics processing unit, GPU), a working memory 43 (e.g., random access memory), and an instruction store 44 that stores a computer program comprising computer-readable instructions that, when executed by the processor 42, cause the processor 42 to perform various functions, including those defined in the computer-implemented methods described above and defined in the claims. The instruction store 44 may comprise a ROM (e.g., in the form of an electrically programmable and erasable read-only memory (EEPROM) or flash memory) that is pre-loaded with the computer-readable instructions.Alternatively, the instruction store 44 may comprise RAM or a similar type of memory, and the computer-readable instructions of the computer program may be fed into it from a computer program product, such as a computer-readable non-transient storage medium 45 in the form of a CD-ROM, DVD-ROM, etc., or a computer-readable signal 46 carrying the computer-readable instructions. In either case, the computer program, when executed by the processor, causes the processor to execute at least one of the computer-implemented methods for point cloud data acquisition, inspection of the interior surface of an operating mining rig, and virtual inspection of a mining rig interior as described herein.However, it should be noted that device 40 can alternatively be implemented on non-programmable hardware, such as an application-specific integrated circuit (ASIC). It will be evident to those skilled in the art that various modifications and variations can be made to the entities and methods of this invention, as well as to the construction of this invention, without departing from the scope of the invention. The invention has been described in relation to particular examples and embodiments intended to be illustrative rather than restrictive in all respects. Those skilled in the art will appreciate that many different combinations of hardware, software, and / or firmware will be suitable for implementing the present invention. The following is provided according to aspects of this disclosure: A1. A computer-implemented point cloud data acquisition method for acquiring point cloud data from mining equipment, preferably from the interior or a region of mining equipment, the method comprising: acquire from a sensor, a first set of data and a second set of data, wherein each set of data comprises data points in coordinates; extract features from the first and second datasets; align the first and second datasets using the extracted features; Combine the first and second aligned datasets to give point cloud data. A2. The computer-implemented point cloud data acquisition method of A1, wherein the features include structural features of the mining equipment and / or reflective property features of the mining equipment. A3. The computer-implemented point cloud data acquisition method of any of A1 - A2, further comprising: Estimate a mining equipment geometry based on point cloud data. A4. The computer-implemented point cloud data acquisition method of any of A1 - A3, further comprising: Use point cloud data through a virtual or augmented reality device to provide a visual perception of the mining equipment. A5. The computer-implemented point cloud data acquisition method of any of A1 - A4, further comprising: Identify, using point cloud data, a region of the estimated geometry that indicates insufficient data. A6. The computer-implemented point cloud data acquisition method according to any of A1 - A5, wherein if an area of ​​the identified region is above a predetermined area, a next coordinate is extracted from within the identified area, wherein the next coordinate is preferably a coordinate closer to a sensor scan direction, and ML / IOOO causes the sensor to move in a direction toward the next coordinate until the next coordinate falls within the sensor's scan range, or a user is notified of the next coordinate and instructed to move the sensor in a direction toward the next coordinate until the next coordinate falls within the sensor's scan range. A7. The computer-implemented point cloud data acquisition method according to A6, wherein if the following coordinate falls within the sensor's scanning range, the method further comprises: acquire from the sensor, a third set of data comprising data points in coordinates; extract features from the point cloud data and the third dataset; align the third dataset with the point cloud data; combine the third aligned dataset to give the point cloud data; re-estimate the geometry of the mining equipment as the estimated geometry based on the point cloud; Re-identify, using point cloud data, a region of the estimated geometry that indicates insufficient data as the region indicating insufficient data. A8. The computer-implemented point cloud data acquisition method according to any one of A1 to A7, wherein if an area of ​​the identified region is below a predetermined area, a fault analysis is performed based on the point cloud data. A9. The computer-implemented point cloud data acquisition method according to any one of A1 to A8, wherein the sensor is a mobile, preferably handheld, flying or suspended sensor. A10. The computer-implemented point cloud data acquisition method according to any one of A1 to A9, wherein the sensor is a depth sensor, which detects the distance from the sensor to a surface as depth. A11. The computer-implemented point cloud data acquisition method according to any one of A1 to A10, wherein the sensor detects information about a distance from the sensor to a surface of the mining equipment, preferably from the interior or region of the mining equipment as depth information. A12. The computer-implemented point cloud data acquisition method according to any one of A1 to A11, wherein the sensor detects information about a property related to the intensity of the reflected and measured signal. A13. The computer-implemented point cloud data acquisition method according to any one of A1 to A12, wherein the second data set is acquired after the first data set and after the sensor has been moved. A14. The computer-implemented point cloud data acquisition method according to any one of A1 to A13, wherein the sensor obtains information about the sensor's orientation and / or odometry. A15. The computer-implemented point cloud data acquisition method according to any one of A1 to A14, wherein the orientation information includes roll, pitch and / or yaw information of the sensor; and the odometry information includes x, yyz information of the sensor. A16. The computer-implemented point cloud data acquisition method according to any one of A1 to A15, wherein the data points are coordinates indicating a location on a surface detected by the sensor. A17. The computer-implemented point cloud data acquisition method according to any one of A1 to A16, wherein features are extracted by using one of feature detection, edge detection, line tracing, or segmental interpolation fitting on a surface represented by the data points. A18. The computer-implemented point cloud data acquisition method according to any one of A1 to A17, wherein the extraction extracts principal feature components for alignment. A19. The computer-implemented point cloud data acquisition method according to any one of A1 to A8, wherein the alignment comprises linearly transforming, preferably rotating, scaling and / or translating, the first, second and / or third data sets to maximize alignment and / or matching. A20. The computer-implemented point cloud data acquisition method according to A19, wherein the alignment between the first, second and / or third datasets and / or point cloud data is indicated by a scalar product of the features, preferably of the principal components. A21. The computer-implemented point cloud data acquisition method according to A19 or A20, wherein the alignment of the first, second and / or third datasets and / or point cloud data is indicated by convolution and / or correlation of features, preferably of the main component. A22. The computer-implemented point cloud data acquisition method according to any one of A1 to A21, wherein the point cloud data are meshed before estimating the geometry of the mining equipment. B1. A computer-implemented inspection method for inspecting the surface of an operating mining machine, the method comprising: move a sensor through the interior or along the length of the mining equipment; acquire, by using the sensor, first point cloud data and second point cloud data, wherein the point cloud data represents a surface within or along the mining equipment; determine, based on each of the first and second point cloud data, surfaces within or along the mining equipment; Estimate, based on the determined surfaces, a geometry of the mining equipment, preferably an interior geometry of the mining equipment. B2. The computer-implemented inspection method according to B1, in which the mining equipment is rotating or moving during the acquisition. B3. The computer-implemented inspection method according to B1 or B2, wherein the sensor rotates in a direction opposite to a direction of rotation of the mining equipment. B4. The computer-implemented inspection method according to any one of B1 - B3, wherein the sensor rotates at an angular speed faster than the angular speed of the mining equipment. B5. The computer-implemented inspection method according to any one of B1 to B4, wherein the mining equipment rotates at an angular velocity equal to or less than an angular velocity during normal operation. B6. The computer-implemented inspection method according to any one of B1 to B5, wherein the first point cloud data and the second point cloud data are acquired according to the method of any one of A1 to A22. B7. The computer-implemented inspection method according to any one of B1 to B6, wherein the sensor moves essentially parallel to a rotation axis of the mining equipment. B8. The computer-implemented inspection method according to any one of B1 to B7, wherein the mining equipment rotates around its axis of rotation when operated. B9. The computer-implemented inspection method according to any one of B1 to B8, wherein the second point cloud data are acquired after the first point cloud data and after the sensor and / or mining equipment has been moved. B10. The computer-implemented inspection method according to any one of B1 to B9, wherein the first and second point cloud data acquired are rotationally corrected based MA / 1OO in the rotation angles of the sensor and the mining equipment. C1. A human-machine guidance system for inspecting mining equipment, preferably an interior or region of the mining equipment, the system comprising: a screen; a sensor configured to detect a distance to a surface of the mining equipment; a tracker configured to track the sensor's location and orientation; a point cloud generator configured to generate point cloud data based on the detected distance and the tracked location and orientation of the sensor; a surface estimator configured to estimate a surface based on point cloud data; and a geometry estimator configured to estimate a mining rig geometry based on the surface. C2. The human-machine guidance system according to C1, in which the screen is configured to visually present the estimated surface based on the location and orientation of the sensor. C3. The human-machine guidance system according to any of C1 to C2, wherein the tracker is further configured to track the location and / or orientation of the display; and the display is configured to visually present the estimated surface based on the location and / or orientation of the display. C4. The man-machine guidance system according to any of C1 to C3, wherein the sensor is further configured to detect a reflective property of the mining equipment. C5. The human-machine guidance system according to any of 01 to C4, wherein the sensor is further configured to detect a property related to the intensity of the reflected and measured signal. C6. The human-machine guidance system according to any of C1 to C5, which further comprises: a mining equipment database configured to store a template geometry and a region of interest for the mining equipment; a subcloud determiner configured to extract a subset of the point cloud data as subcloud data based on the region of interest; and a data transceiver configured to transmit the subcloud data to a remote display. C7. The human-machine guidance system according to any of 01 to C6, wherein: if the point cloud data does not comprise data points in the region of interest, the estimated surface and / or geometry(s) is / are highlighted at a location in the region of interest. 08. The human-machine guidance system according to any of 01 to 07, which further comprises: a remote computer, preferably located next to the remote display, configured to: receive inputs to define another region of interest, and store the region of interest in the mining equipment database. ML / IOD C9. The human-machine guidance system according to any of C1 to C8, which further comprises: A void detector configured to detect coordinates in the estimated geometry for which the number of point cloud data points is below a predetermined value, or the surface gradient is above a predetermined value. C10. The human-machine guidance system according to any one of C1 to C9, wherein the screen is a virtual or augmented reality screen. D1. A computer-implemented method for a virtual inspection of mining equipment, preferably an interior or region of the mining equipment, the method comprising: acquire a first dataset, wherein the first dataset comprises data points in coordinates of the mining equipment; convert the first acquired data set into a second data set, the second data set being adapted for use by a virtual or augmented reality device; Guide at least one user through the virtual inspection of the mining equipment based on the second data set by moving a visual perception of at least one user of the virtual or augmented reality device to one or more points of interest on the mining equipment. D2. The computer-implemented method of D1, wherein the first data set further comprises a reflection property of the mining equipment at the mining equipment coordinates. D3. The computer-implemented method according to any of D1 to D2, wherein the first data set further comprises a property related to the intensity of the reflected signal measured at the coordinates of the mining equipment. D4. The computer-implemented method according to any of D1 - D3, further comprising: coordinate the virtual inspection between at least two users. D5. The computer-implemented method according to any of D1 - D4, further comprising: transfer the second set of data to one or more remote users. D6. The computer-implemented method according to any of D1 - D5, further comprising: Acquire additional data points from the first set of mining equipment data based on an initial virtual inspection of one or more points of interest from the mining equipment. D7. The computer-implemented method according to any of D1 - D6, further comprising: acquire a plurality of the first data set at different points in time; convert the acquired plurality of the first data set into a plurality of the second data set, MA / IOO provide virtual inspection of mining equipment based on the plurality of the second data set, wherein the virtual inspection provides a development of physical parameters and / or a simulation of physical parameters and / or a cross-section and / or a contour at one or more points of interest of the mining equipment. D8. The computer-implemented method according to any of D1 - D7, further comprising: augment the second data set with additional information on physical parameters with respect to one or more points of interest of the mining equipment. D9. The computer-implemented method according to any of D1 - D7, further comprising: using a virtual flashlight in visual perception. E1. A computer program that, when executed by a computer (40), causes the computer to perform the method according to any of A1 to A22 or B1 to B10 or D1 to D9. E2. A computer-readable non-transient storage medium (45) that stores a computer program according to E1. E3. A signal (46) that carries a computer program according to E1.

Claims

1. A computer-implemented point cloud data acquisition method for acquiring point cloud data from the interior of a mining rig, the method being characterized in that it comprises: acquiring from a sensor, a first data set and a second data set, wherein each data set comprises data points in coordinates; extracting features from the first and second data sets; aligning the first and second data sets using the extracted features; combining the aligned first and second data sets to yield point cloud data; estimating a geometry of the mining rig based on the point cloud data; and identifying, by use of the point cloud data, a region of the estimated geometry that indicates insufficient data.

2. The computer-implemented point cloud data acquisition method according to claim 1, further characterized in that if an area of ​​the identified region is above a predetermined area, a next coordinate is extracted from within the identified area, wherein the next coordinate is a coordinate closer to a sensor scan direction, and the sensor is caused to move in a direction toward the next coordinate until the next coordinate falls within a scan range of the sensor, or a user is notified of the next coordinate and instructed to move the sensor in a direction toward the next coordinate until the next coordinate falls within the scan range of the sensor.

3. The computer-implemented point cloud data acquisition method according to claim 2, further characterized in that if the following coordinate falls within the sensor's scanning range, the method further comprises: acquiring from the sensor a third data set comprising data points at coordinates; extracting features from the point cloud data and the third data set; aligning the third data set with the point cloud data; combining the aligned third data set to yield the point cloud data; re-estimating the geometry of the mining equipment as the estimated geometry based on the point cloud; and re-identifying, using the point cloud data, a region of the estimated geometry that indicates insufficient data as the region indicating insufficient data.

4. The computer-implemented point cloud data acquisition method according to any one of claims 1 to 3, further characterized in that if an area of ​​the identified region is below a predetermined area, a fault analysis is performed based on the point cloud data. MA / IOD 5. The computer-implemented point cloud data acquisition method according to any one of claims 1 to 4, further characterized in that the sensor is a mobile sensor, preferably portable, flight-mounted or suspended.

6. The computer-implemented point cloud data acquisition method according to any one of claims 1 to 5, further characterized in that the sensor is a depth sensor, which detects the distance from the sensor to a surface as depth.

7. The computer-implemented point cloud data acquisition method according to any one of claims 1 to 6, further characterized in that the sensor detects information about a distance from the sensor to a surface within the mining equipment as depth information.

8. The computer-implemented point cloud data acquisition method according to any one of claims 1 to 7, further characterized in that the second data set is acquired after the first data set and after the sensor has been moved.

9. The computer-implemented point cloud data acquisition method according to any one of claims 1 to 8, further characterized in that the sensor obtains information about the sensor's orientation and / or odometry.

10. The computer-implemented point cloud data acquisition method according to any one of claims 1 to 9, further characterized in that the orientation information includes roll, pitch and / or yaw information of the sensor; and the odometry information includes x, yyz information of the sensor.

11. The computer-implemented point cloud data acquisition method according to any one of claims 1 to 10, further characterized in that the data points are coordinates indicating a location of a surface detected by the sensor.

12. The computer-implemented point cloud data acquisition method according to any one of claims 1 to 11, further characterized in that the features are extracted by the use of one of feature detection, edge detection, line tracing, or segmental interpolation fitting on a surface represented by the data points.

13. The computer-implemented point cloud data acquisition method according to any one of claims 1 to 12, further characterized in that the extraction extracts principal features for alignment.

14. The computer-implemented point cloud data acquisition method according to any one of claims 1 to 13, further characterized in that the alignment comprises linearly transforming, preferably rotating, scaling and / or translating the first, second and / or third data sets to maximize alignment and / or matching.

15. The computer-implemented point cloud data acquisition method according to claim 14, further characterized in that the alignment between the first, second and / or third data sets and / or point cloud data is indicated by a scalar product of the features, preferably of the main components.

16. The computer-implemented point cloud data acquisition method according to claim 14 or 15, further characterized in that the alignment of the first, second and / or third data sets and / or point cloud data is indicated by convolution and / or correlation of features, preferably of the main component.

17. The computer-implemented point cloud data acquisition method according to any one of claims 1 to 16, further characterized in that the point cloud data is meshed before estimating the geometry of the mining equipment.

18. A computer-implemented inspection method for inspecting the interior surface of an operating mining machine that is performing its mining operation on mining material, the method being characterized in that it comprises: moving a sensor through the interior of the mining machine; acquiring, by means of the sensor, first point cloud data and second point cloud data, wherein the point cloud data represent a surface within the mining machine; determining, based on each of the first and second point cloud data, surfaces within the mining machine; estimating, based on the determined surfaces, an interior geometry of the mining machine.

19. The computer-implemented inspection method according to claim 18, further characterized in that the mining equipment is rotating during the acquisition.

20. The computer-implemented inspection method according to claim 18 or 19, further characterized in that the sensor rotates in a direction opposite to a direction of rotation of the mining equipment.

21. The computer-implemented inspection method according to claim 18 or 20, further characterized in that the sensor rotates at a faster angular speed than the angular speed of the mining equipment.

22. The computer-implemented inspection method according to any one of claims 18 to 21, further characterized in that the mining equipment rotates at an angular velocity equal to or less than an angular velocity during normal operation.

23. The computer-implemented inspection method according to any one of claims 18 to 22, further characterized in that the first point cloud data and the second point cloud data are acquired according to the method according to any one of claims 1 to 17.

24. The computer-implemented inspection method according to any one of claims 18 to 23, further characterized in that the sensor moves essentially parallel to a rotation axis of the mining equipment.

25. The computer-implemented inspection method according to any one of claims 18 to 24, further characterized in that the mining equipment rotates about its axis of rotation when operated.

26. The computer-implemented inspection method according to any one of claims 18 to 25, further characterized in that the second point cloud data are acquired after the first point cloud data and after the sensor and / or mining equipment has been moved.

27. The computer-implemented inspection method according to any one of claims 18 to 26, further characterized in that the first and second point cloud data acquired are rotationally corrected based on the rotation angles of the sensor and the mining equipment.

28. A human-machine guidance system for inspecting the interior of a mining rig, the system being characterized in that it comprises: a display; a sensor configured to detect a distance to a surface; a tracker configured to track the location and orientation of the sensor; a point cloud generator configured to generate point cloud data based on the detected distance and the tracked location and orientation of the sensor; a surface estimator configured to estimate a surface based on the point cloud data; and a geometry estimator configured to estimate a geometry of the mining rig based on the surface, wherein the display is configured to visually present the estimated surface based on the location and orientation of the sensor.

29. The human-machine guidance system according to claim 28, further characterized in that the tracker is additionally configured to track the location and orientation of the display; and the display is configured to visually present the estimated surface based on the location and orientation of the display.

30. The human-machine guidance system according to claim 28 or 29, further characterized in that it additionally comprises: a remote display; a mining equipment database configured to store a template geometry MA / 1000 and a region of interest of the mining equipment; a subcloud determiner configured to extract from the point cloud data a subset as subcloud data based on the region of interest; and a data transceiver configured to transmit the subcloud data to the remote display.

31. The human-machine guidance system according to claim 29, further characterized in that: if the point cloud data does not comprise data points in the region of interest, the estimated surface and / or geometry(s) is / are highlighted at a location in the region of interest.

32. The human-machine guidance system according to claim 29 or 31, further characterized in that it additionally comprises: a remote computer located together with the remote display, configured to: receive inputs to define another region of interest, and store the region of interest in the mining equipment database.

33. The human-machine guidance system according to any one of claims 28 to 32, further characterized in that it additionally comprises: a gap detector configured to detect coordinates in the estimated geometry for which the number of point cloud data points is below a predetermined value, or the surface gradient is above a predetermined value.

34. The human-machine guidance system according to any one of claims 28 to 33, further characterized in that the screen is a virtual or augmented reality screen.

35. A computer-implemented method for a virtual inspection of the interior of a mining rig, the method being characterized in that it comprises: acquiring a first dataset, wherein the first dataset comprises data points at coordinates of the interior of the mining rig; converting the first acquired dataset into a second dataset, the second dataset being adapted for use by a virtual or augmented reality device; and guiding at least one user through the virtual inspection of the interior of the mining rig based on the second dataset by moving the visual perception of the at least one user of the virtual or augmented reality device to one or more points of interest within the mining rig.

36. The computer-implemented method according to claim 35, further characterized in that it additionally comprises: coordinating the virtual inspection between at least two users.

37. The computer-implemented method according to any one of claims 35 to 36, further characterized in that it additionally comprises: transferring the second set of data to one or more remote users.

38. The computer-implemented method according to any one of claims 35 to 37, further characterized in that it additionally comprises: acquiring additional data points from the first data set of the interior of the mining equipment based on a first virtual inspection of one or more points of interest within the mining equipment.

39. The computer-implemented method according to any one of claims 35 to 38, further characterized in that it additionally comprises: acquiring a plurality of the first data set at different time points; converting the acquired plurality of the first data set into a plurality of the second data set; providing a virtual inspection of the interior of the mining equipment based on the plurality of the second data set, wherein the virtual inspection provides a development of physical parameters and / or a simulation of physical parameters at one or more points of interest within the mining equipment.

40. The computer-implemented method according to any one of claims 35 to 39, further characterized in that it additionally comprises: augmenting the second data set with additional physical parameter information with respect to one or more points of interest inside the mining equipment.

41. A computer-readable non-transient storage medium, characterized in that it comprises the method as claimed in any of claims 1 to 27 or 35 to 40.

Images