Method and material removal system

Abstract

According to various embodiments, a material removal system (200) can have: a material removal machine (202) which has a machine chisel (5) and is designed to remove material by means of the machine chisel (5); an infrared camera (6) for capturing temperature-based image data which represent a machine chisel (5); a data processing device (106) which is designed to: determine (101) an indication which represents at least one geometrical property of the machine chisel (5) on the basis of the temperature-based image data; determine (103) a state of the machine chisel (5) on the basis of the indication.

Description

[0001] Description

[0002] Process and removal system

[0003] Various embodiments relate to a method and a removal system.

[0004] In mining, tunneling, or civil engineering, the rock or a valuable mineral, including the surrounding rock, is sometimes removed using mechanical rock-cutting machines such as roadheaders, continuous miners, surface miners, and tunnel boring machines. This so-called cutting extraction method is established in coal mining, salt mining, and the extraction of soft minerals such as clay, gypsum, or limestone, but is increasingly being used for gangue minerals as well. In tunneling and civil engineering, profiles, shafts, and trenches are created using special rock-cutting machines.

[0005] Tool wear is a major challenge in this area and therefore requires considerable effort. Monitoring wear and the effort to replace worn cutting tools at an optimal time in terms of high cutting performance and the use or number of required tools require a considerable amount of labor and time, which in practice is often accomplished manually, i.e., without any form of automation.

[0006] Mechanical excavation or mining using rock cutting machines is carried out primarily with rotatably mounted machine chisels (hereinafter also referred to simply as chisels) mounted on rotating cutting heads, whereby two basic types are distinguished.

[0007] Especially in the coal sector, mining is also carried out with fixed bits (so-called flat bits) in so-called shearing machines or shearer loaders. Wear is caused by the continuous abrasion of the machine bit against the rock or by the chipping or even breaking off of parts of the bit head or bit edge due to overloading during cutting. Due to friction, the bits heat up to a normal operating temperature, which can exceed 100°C, and even up to 400°C at the tip or edge. However, due to overloading, this thermal heating can relatively quickly lead to the melting point of the material. Avoiding this is therefore a key goal of operational management and has so far required primarily experienced operators.

[0008] Tool wear is typically addressed through an inspection cycle tailored to local conditions and the operator's experience, sometimes including a detailed visual inspection of each individual bit. The machine is stopped, sometimes roughly cleaned, and lighting may be required to inspect each individual bit from all sides. To do this, the bits are rotated by hand in their holders, and if necessary, loosened with a hammer if material has become jammed in the holders and prevents wear-distributing bit rotation (also known as bit jamming). When cutting in very hard rock, it may be necessary to perform the inspection cycle hourly. Even in anhydrite-rich rock salt, this inspection is performed up to four times per shift, i.e., every two hours.Frequent inspection cycles result in significant time losses, which reduce the utilization of expensive machines and thus increase production costs. Conventional inspection automation concepts are based on measurements on the drive train, acoustic emission measurements, or measurements on the bit itself, for example, by measuring the bit profile with an optical camera or laser, or by non-contact temperature measurements on the bit tips. These concepts can deliver adequate results under favorable operating conditions, for example, in road construction and open-pit mining, but are significantly compromised under difficult operating conditions, such as those typical in tunnel construction or underground mining.

[0009] Measurements on the drive train do not allow any conclusions to be drawn about which specific bit is worn, to what extent, or in what way. Increased power consumption of the drive train can only indicate a significant number of heavily worn bits, since the power consumption of the drive train is averaged across all machine bits.

[0010] Measurements on the bit itself, such as its temperature, are often subject to a multitude of influencing factors, such as rock hardness and contact forces. Of these, the wear condition of the bit (also referred to as bit wear condition) is only one factor and is therefore difficult to distinguish from the other factors as a cause. Even the total loss of a single bit may go unnoticed, even by experienced personnel, but it immediately causes serious damage to the bit holder, which can lead to machine failure. Therefore, an inspection after a fixed cycle is often insufficient to prevent damage to the machine that has already occurred due to unfavorable wear.Measuring acoustic emissions is problematic because, on the one hand, there are many noise sources when operating a rock cutting machine. On the other hand, the confined space and the sometimes jagged walls underground can lead to a variety of overlapping noises, which severely hamper analysis and clear classification. Changing cutting parameters by the operator or altered rock conditions also significantly alter these noises. Therefore, it's difficult to determine which bit is causing them.

[0011] According to various embodiments, it has been clearly recognized that conventional imaging measurements rely on good visibility and lighting conditions, e.g., by means of external lighting, which is why they are very sensitive to dust development, dust deposits, water mist, and water accumulation, which significantly limits their possible applications, for example, in conditions of lack of light, and particularly underground. For example, external lighting is ineffective in conditions of high dust development and water mist. Furthermore, the chisel tip or edge is often barely distinguishable from the image background due to dust development, dust deposits, and / or the similar coloring of rock, dust, and machine chisels (hereinafter also referred to simply as chisels).

[0012] In this context, it was recognized that infrared radiation is less subject to these limitations than visible light. It was clearly recognized that machine tools become very hot during normal operation and thus themselves become a source of infrared radiation without the need for external illumination, and that the infrared radiation emitted by the tool penetrates dust better and is less subject to distorting influences than visible light. The infrared radiation emitted by a heated tool is therefore easier to distinguish from the (relatively cold) image background in the infrared image (also colloquially known as a thermal image) than the reflections of visible light in conventional imaging techniques. It was also recognized that conventional infrared measurement methods primarily focus on exceeding absolute temperature thresholds.However, the measured values ​​of the absolute temperature are comparatively sensitive to the interference caused by dust and water that is typical for construction (e.g. mining), which is why such methods have not yet been brought to practical use.

[0013] According to various embodiments, the present invention is used to determine the spatial geometry (e.g. the profile) of a machine chisel (also referred to herein as chisel geometry for short), e.g. the geometry of the parts influencing its cutting performance, on the basis of the infrared radiation emitted (i.e., emitted) by it (also colloquially referred to as thermal radiation). On the basis of the determined chisel geometry, the condition of the machine chisel, e.g., its state of wear and / or its comparison to a defined good condition (also referred to as the reference condition), is in turn determined. This determination of the chisel geometry on the basis of infrared radiation must be distinguished from a pure measurement of the temperature of the machine chisel (also referred to as chisel temperature), even if this chisel temperature is determined using an infrared camera (also colloquially referred to as a thermal imaging camera).In contrast to bit temperature, bit geometry depends exclusively on the wear condition of the machine bit and is therefore subject to fewer influencing factors than bit temperature. This also applies to the temporary adhesion of material, as this quickly detaches due to contact with the rock, allowing a clear measurement result to be obtained, e.g., by simple statistical averaging over several revolutions of the cutting head.

[0014] Thus, determining the chisel geometry enables a more reliable determination of the condition of the machine chisel than, for example, if only the temperature of the machine chisel is taken into account.

[0015] The mechanical interaction that occurs at the contact points between the machine bit and the rock during the removal process, on the one hand, removes the rock and, on the other hand, releases heat energy. This causes the bit temperature to rise during the removal process until an equilibrium is reached between frictional heat input during the actual cutting and heat radiation during the empty bit rotation, and the machine bit itself is worn (also known as bit wear). Bit wear is a consequence of the bit being mechanically stressed at its contact points with the rock during the removal process and is thereby worn down, eroded, deformed and / or broken (also known as bit breakage). This bit wear changes the bit geometry (e.g. the bit contour) and can enlarge the contact area between the machine bit and the rock, so that the bit temperature can continue to rise as bit wear progresses.The temperature of the chisel tip or edge can reach over 1000°C and even lead to softening or melting of parts of the chisel tip or edge. This, in turn, accelerates chisel wear, so that chisel wear does not necessarily occur linearly over time, but rather accelerates, for example, exponentially, over time.

[0016] This is counteracted by the fact that a heavily worn machine bit penetrates the rock less deeply than a neighboring, less worn machine bit. However, this only shifts the cutting forces onto the less worn machine bits, causing them to wear more quickly than, for example, if all machine bits were worn evenly. In addition, if machine bits are worn unevenly, the fluctuating cutting forces can cause the cutting head to oscillate, significantly reducing cutting performance. For the same reason, an imbalance in load distribution can occur, leading to faster wear of new machine bits and excessive vibrations at the cutting head. If a bit breakage goes undetected, there is also a risk that the valuable bit holder will come into contact with the rock and be damaged.

[0017] In normal operations, round shank bits are therefore mounted so that they can rotate, so that the resulting friction surface does not increase in size, but is twisted by the resulting lateral forces of the bit. In this way, the tip of round shank bits is worn evenly until the bit head with the carbide tip is largely ground round. This so-called symmetrical wear condition can be identified visually during regular inspections, so that the affected bit is replaced regularly. However, the inevitable penetration of dust into the bit holder regularly leads to bit blockage. A round shank bit can then no longer rotate, so that a rapidly growing, larger wear surface develops. The force required to push the bit as deeply into the rock as when it is only slightly or regularly worn increases in proportion to its size.This so-called asymmetrical wear then leads in a very short time, considerably shorter than any control cycle, to overheating, melting, partial or complete breakage of the chisel head and the serious consequential damage described above.

[0018] Therefore, access to and monitoring of bit wear is crucial for efficient, and especially cost-effective, rock cutting. This facilitates the timely detection of significantly worn machine bits that, for example, would need to be replaced or would otherwise no longer function, thus saving costs that could otherwise arise due to damage to other bits, the bitholder, repair times, and reduced cutting performance. This can prevent, for example, not only the bit from becoming worn, but also the bitholder from becoming damaged to the point of complete removal, which would result in significant repair and thus downtime.

[0019] This and the previously described circumstances are taken into account according to various embodiments. The method, computer implementations thereof, and removal system provided according to various embodiments facilitate the condition monitoring (e.g., wear monitoring) of machine bits. This includes the early detection of progressive wear on the bits, but also the timely detection of individual broken or otherwise heavily worn bits, even outside of fixed inspection intervals, so that the machine's operating time and its power consumption lead to optimal removal performance.In particular, severe wear can be prevented, which, for example, due to the breakage of a chisel tip, can lead to extreme wear and overloading of the chisel within a few minutes, even leading to the breakage and removal of the valuable chisel holder welded to the cutting drum, as well as to the overloading and severe wear of other chisels. Since such and similar accidents can result in very lengthy repairs and, due to the lost loosening quantities, very costly downtime for expensive machines, which are usually only available in small numbers in a mine, costs can also be avoided. Downtime costs of ten thousand euros per hour or more are realistic in certain operations.

[0020] The failure of bits in tunnel boring machines (TBMs) is similarly serious. In these cases, an inspection requires not just a brief stop, but reversing the entire machine, which weighs hundreds of tons and is strung out in the tunnel, in order to access the excavation site from inside the machine and inspect the bits.

[0021] The method provided according to various embodiments of the present invention and a correspondingly equipped removal system facilitate the condition monitoring (e.g. wear monitoring) of machine chisels, in particular under conditions of severely restricted visibility, release of dust and water mist and possibly also in the case of temporary sinking in the excavated loose material or in the case of considerable contamination of the working tools.

[0022] The embodiments explained herein are applicable to any type of removal machine (e.g., rock cutting machines), especially those in which rotating cutting drums with round-shank picks are mounted. Examples of such removal machines include so-called roadheaders, continuous miners, shearer loaders, horizontal milling machines, surface miners, and mounted milling machines. Removal machines of these types are used in coal, salt, silicate, or ore mining, underground and open-cast mining, tunneling, road and hydraulic engineering, quarries, and building demolition.

[0023] The embodiments explained herein generate significant economic advantages over conventional concepts for a single mine using cutting methods. These advantages arise from the significantly higher potential utilization of the highly complex mining machinery, as the invention significantly reduces the number of regular, periodic cutter head inspections and makes accidents following a bit breakage almost entirely avoidable. They also increase operational safety, as personal inspections of the cutter head, directly at the mining site, are required less frequently. When widely applied, the embodiments explained herein generate significant economic benefits in the form of increased efficiency of rock removal processes in mining and civil engineering, combined with lower producer prices for the extracted raw materials for industry and lower construction costs for civil engineering structures.The embodiments explained herein thus also promote the expanded use of the rock- and resource-saving technology of cutting extraction at the expense of drilling and blasting operations with subsequent comminution and processing. This, in turn, has the potential to have a significant positive impact on the economic viability, the ecological footprint, and ultimately also on the public's acceptance of the indispensable mining of various raw materials in industrial society. The present invention thus also represents a contribution to long-term resource security.

[0024] One basic type, known from but not limited to so-called full-face machines or tunnel boring machines (TBMs), uses so-called roller bits (e.g., disc bits), which are arranged on a cutting head rotating in the direction of advance at various distances from the center and are pressed against the rock by rolling on the rotating, hardened cutting edge. The other basic type uses so-called round-shank bits on cutting heads that preferably rotate vertically, but sometimes also in the direction of advance, which are pressed against the rock with friction by the hardened tip. However, the round-shank bits themselves can and should rotate around their axis of attack in order to even out wear and thus increase service life.

[0025] Figure 1 shows a method according to various embodiments in a schematic flow diagram;

[0026] Figures 2, 3 and 4 each show a removal system according to different embodiments in different representations;

[0027] Figures 5A and 5B each show a removal system according to various embodiments in a schematic perspective view;

[0028] Figures 6A and 6B each show a removal system according to various embodiments in a schematic perspective view;

[0029] Figure 7 shows a removal system according to various embodiments in a schematic perspective view;

[0030] Figures 8, 9, 10 and 11 each show various components of the method according to various embodiments in a diagram;

[0031] Figures 12 and 19 each show a configuration of the camera system during image capture according to various embodiments in a schematic perspective view;

[0032] Figures 13, 14, 15 and 16 each show a machine chisel according to various embodiments in a schematic side view;

[0033] Figures 17A and 17B and 20A and 20B each show machine tools of different states in a schematic perspective view and resulting geometry representations in a schematic view according to various embodiments; and

[0034] Figure 18 is a graphical user interface of the ablation machine in a schematic top view. In the following detailed description, reference is made to the accompanying drawings, which form a part hereof, and in which is shown by way of illustration specific embodiments in which the invention may be practiced. In this regard, directional terminology such as "top", "bottom", "front", "back", "fore", "rear", etc., is used with reference to the orientation of the described figure(s). Since components of embodiments can be positioned in a number of different orientations, the directional terminology is for purposes of illustration and is in no way limiting. It is to be understood that other embodiments may be utilized and structural or logical changes may be made without departing from the scope of the present invention.It is understood that the features of the various exemplary embodiments described herein may be combined with one another, unless specifically stated otherwise. The following detailed description is therefore not to be construed in a limiting sense. The scope of the present invention is defined by the appended claims.

[0035] In this description, the terms "connected," "attached," and "coupled" are used to describe both a direct (e.g., positive or material connection) and an indirect connection (e.g., through a signal path), a direct or indirect connection, and a direct or indirect coupling. In the figures, identical or similar elements are provided with identical reference numerals where appropriate.

[0036] The actual state of an entity (e.g. a device, an object, a system or an operation or process) can be understood as the actual or sensory detectable state of the entity. The desired state of the entity can be understood as the desired state, i.e. a specification that can optionally be stored, for example in a data storage device. Control can be understood as an intentional influencing of the current state (also referred to as the actual state) of the entity. The current state can be changed according to the specification (also referred to as the desired state), e.g. by changing one or more operating parameters (then also referred to as manipulated variables) of the entity, e.g. by means of an actuator. Regulation can be understood as control, whereby a change in state caused by disturbances is additionally counteracted.To this end, the actual state is compared with the desired state, and the entity is influenced, e.g., by means of an actuator, in such a way that the deviation of the actual state from the desired state is minimized. In contrast to purely forward-directed sequential control, the control thus implements a continuous influence of the output variable on the input variable, which is effected by the so-called control loop (also referred to as feedback). In other words, this can be understood as meaning that, alternatively or in addition to open-loop control (or actuation), closed-loop control can be used, or that, alternatively or in addition to open-loop control, closed-loop control can be used.

[0037] The term "data processing device" can be understood as any type of logic-implementing entity, which can, for example, comprise circuitry and / or a processor capable of executing software stored in a storage medium, firmware, or a combination thereof, and issuing instructions based thereon. The data processing device can, for example, be configured using code segments (e.g., software) to control the operation of a system (e.g., its operating point), e.g., a machine or a plant, e.g., its components. The term "processor" can be understood as any type of entity that allows the processing of data or signals. The data or signals can, for example, be processed according to at least one (i.e., one or more than one) specific function performed by the processor.A processor may include or be formed from an analog circuit, a digital circuit, a mixed-signal circuit, a logic circuit, a microprocessor, a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), a programmable gate array (FPGA), an integrated circuit (IC), or any combination thereof. Any other type of implementation of the respective functions, which are described in more detail below, may also be understood as a processor or logic circuit. It is understood that one or more of the method steps described in detail herein may be carried out (e.g., realized) by a processor, through one or more specific functions performed by the processor. The processor may therefore be configured to carry out one of the methods described herein or its components for information processing.

[0038] According to various embodiments, a data storage device (more generally also referred to as a storage medium) may be a non-volatile data storage device. The data storage device may, for example, comprise or be formed from a hard disk and / or at least one semiconductor memory (such as read-only memory, random access memory, and / or flash memory). The read-only memory may, for example, be an erasable programmable read-only memory (also referred to as EPROM). The random access memory may be a non-volatile random access memory (also referred to as NVRAM - "non-volatile random access memory").For example, the data storage may store one or more of the following: a database (may also be referred to as a reference database); a processing algorithm; a criterion; and code segments that implement, for example, one or more processing algorithms (simply referred to as algorithms). The database may have one or more data records, each of which associates a product identifier with payment information and / or a sales restriction. This can be read by the data processing device.

[0039] Various embodiments relate to a machine chisel (also referred to simply as a chisel herein) and its condition. The term “machine chisel,” as used herein, can be understood as a machine tool that can consist of components that are (e.g., rigidly) connected to one another (e.g., by a material fit, a force fit, and / or a form fit). Examples of a machine chisel include: a roller chisel (e.g., a disc chisel or a warp chisel), a round shank chisel (e.g., of a road construction machine, a roadheader, or a surface miner), a flat chisel (e.g., of a cutting machine), an excavation tooth (e.g., of an excavating machine, e.g., an excavator, e.g., a bucket wheel excavator), a roller chisel, e.g., of the disc chisel type (e.g., but not limited to, a tunnel boring machine, a mobile miner).Two or more of the components of the machine bit can optionally be part of a monolithic body, e.g., manufactured from a single piece. Examples of the components of the machine bit include: an assembly component and a cutting component.

[0040] In the case of a round shank chisel or flat chisel, the mounting component can be shaft-shaped (then also referred to as the chisel shank or shank for short) and the cutting component can be head-shaped (then also referred to as the chisel head). The chisel head and / or the chisel shank can, for example, be rotating bodies. The round shank chisel or flat chisel can be elongated along a longitudinal axis (also referred to as the chisel axis) (e.g., from its back to its front). The round shank chisel or flat chisel can have the chisel tip (illustratively on the front), through which, for example, the chisel axis can run. In the case of a roller chisel (e.g., disc chisel), the mounting component can have a shaft (or at least be configured to receive a shaft) and the cutting component can be annular (then also referred to as the roller body).

[0041] The cutting component (e.g., the bit head) has a cutting edge, e.g., a cutting edge or cutting point (also called a bit point), (e.g., on the front of the machine bit). In the case of a roller bit (e.g., a disc bit), the cutting edge may be annular (then also called a cutting ring). The cutting component of the roller bit (e.g., a disc bit) may have one or more cutting rings.

[0042] The chisel tip (e.g., of a round-shank chisel) forms the front edge of the chisel and can have a tapered (e.g., conical) shape toward the front. The chisel head can be connected to the shank (which extends toward the back) on the side opposite the chisel tip or the side facing the back of the machine chisel, e.g., by a material connection. The chisel head can optionally have a thickened portion protruding from the chisel tip and / or the chisel shank.

[0043] Optionally, the cutting component (e.g. the chisel head) can consist of several materials, one of which material (also referred to as the cutting edge material) provides the cutting edge. In the case of a round shank chisel, the cutting edge material can be pin-shaped (then also referred to as the chisel pin). The cutting edge material preferably has a greater hardness than the rest of the cutting component (e.g. the chisel head) and / or than the mounting component (e.g. the chisel shank). The chisel pin can, for example, be embedded, e.g., pressed into the rest of the chisel head. The chisel pin can be conical, parabolic, or stepped. The chisel pin can, for example, be ceramic or comprise or be made of at least one ceramic (e.g., a carbide, such as tungsten carbide, and / or nitride). The chisel head and / or the chisel shank can be metallic or comprise or be made of at least one metal, e.g., steel.

[0044] In another embodiment, for example a so-called roller chisel (e.g. disc chisel), the chisel extends concentrically from its chisel axis (in this case also referred to as central axis), about which the chisel can be rotatably mounted, for example, and has a chisel edge made of hardened material.

[0045] Reference is made here to image data and their processing. The image data can be a digital (e.g. data-based) image of reality (e.g. within a field of view) at one or more times when the image data is captured (also referred to as image capture). The mapping of reality can, for example, be carried out by means of a lens (also referred to as a camera lens) which projects electromagnetic radiation (e.g. visible or infrared light) onto the surface of an image capture sensor (e.g. an infrared sensor of an infrared camera). The capture of the image data can comprise reading the image capture sensor while the radiation (e.g. infrared radiation) is projected onto its surface. The image data thus obtained can initially be in the so-called raw data format (also referred to as RAW), which stores the read-out measured values ​​(e.g.an intensity of light) of the image acquisition sensor and / or processed as such. The image data can optionally be converted into a different image format during processing, e.g. into a raster graphic (different from RAW as raster graphic) or a vector graphic, so that their further processing takes place in this image format, or can be converted between them as desired. The conversion can optionally include interpolating the measured values ​​of the image acquisition sensor (e.g. by means of demosaicing), e.g. in order to obtain complete multi-colored color information for each pixel or to require less storage space or computing power. The image data can optionally be compressed (e.g. in order to require less storage space or computing power) or uncompressed (e.g. in order to avoid corruption). The respective image format can also define the color space according to which the color information is specified.

[0046] The simplest case is the monochrome color space, which can be a binary color space, for example, in which a black and white value is stored for each pixel. In a somewhat more complex monochrome color space (also known as a grayscale color space), intermediate levels between black and white are also stored (also known as gray values). In a monochrome color space, the absorbed radiant energy (e.g. from infrared radiation) is summed pixel by pixel and mapped to a gray value of the monochrome color space, which represents the intensity of the detected radiation at the wavelength or wavelength range (e.g. infrared range) to which the monochrome image sensor is sensitive. The color space can also be spanned by several (i.e. two or more) reference colors, such as red, green and blue.If a wavelength-sensitive image sensor (also known as a polychrome image sensor) is used, the measured values ​​per pixel can contain the radiant energy and, in addition, a wavelength associated with the radiant energy. This improves the accuracy of an optional temperature measurement based on the image data. Such measured values ​​can be displayed using a multicolor color space or converted to a monochrome color space. Similarly, a value from a monochrome color space can also be converted to a polychrome color space, for example, in the case of so-called false color representation.

[0047] For visual reproduction of image data on a display device, it is converted into the image format specified by the graphics card's image memory. For ease of understanding, the image data described herein is presented as such a visual reproduction. In general, the image data, e.g., stored on a storage medium, can be present as a file (also referred to as a digital image or image file) in the respective image format.

[0048] The image data can have one or more than one individual image (e.g. from different perspectives) as a digital (e.g. data-based) image of reality (e.g. within a field of view), each individual image corresponding to a point in time of capture. For example, the image data can have one or more than one individual image for each point in time of capture, which is the image of reality at that point in time (also referred to as the image capture time). For example, the image data can have one individual image or several individual images (e.g. from different perspectives) for each point in time of a sequence comprising several points in time, for example in the form of a video. Several individual images (e.g. from different perspectives or from different points in time) can alternatively or additionally be combined to form a new individual image, for example along a time axis and / or a spatial axis.For example, several individual images captured during the rotation of a cutting head, each of which represents only a part of the cutting head, can be combined to form a new individual image, to which any point in time within the duration of the rotation is assigned as the time point.

[0049] A camera can be understood as an optical device comprising the camera lens and the image acquisition sensor, which interact in such a way that light from the camera's field of view (also referred to as the image acquisition area) is projected onto the surface of the image acquisition sensor by means of the camera lens. Furthermore, the camera can comprise a processor configured to provide the measured values ​​read by the image acquisition sensor as image data, e.g., to output them.

[0050] An image sensor (also referred to as an image sensor) is of the optoelectronic type and may have one or more photoelectrically active areas (also referred to as pixels) that generate and / or modify an electrical signal, for example, in response to electromagnetic radiation (e.g., infrared light). The image sensor may, for example, have a number B of 10 2 pixels (also called image resolution) or more, e.g. 10 3 pixels or more, e.g. 10 4 pixels or more, e.g. 10 5 pixels or more. Alternatively or additionally, the image acquisition sensor may have a grid R of [k x I] pixels (e.g. with B=kl), where k and / or I are greater than approximately 50, than approximately 100 or than approximately 1000. In general, the image resolution can also be greater than B.

[0051] In some embodiments, the infrared camera (also referred to as a thermal camera) and / or the image acquisition sensor are configured (e.g., arranged and / or aligned) such that the portion of the image acquisition sensor that captures the machine tool has the number B and / or the grid R of pixels. If the portion is smaller, individual images from multiple infrared cameras and / or image acquisition sensors can be overlaid to increase the resolution and / or the grid per machine tool. Alternatively or additionally, a camera lens with a longer focal length can be used.

[0052] The image acquisition sensor can, for example, comprise or be formed from a CCD sensor (charge-coupled device sensor) and / or an active pixel sensor (also referred to as a CMOS sensor). Optionally, an image acquisition sensor can be configured to be wavelength-sensitive (e.g., for capturing color information), e.g., using multiple color filters (e.g., in grid form), thus distinguishing between different wavelengths.

[0053] An infrared camera can be understood as a camera which (e.g. whose image capture sensor) is sensitive (e.g. only) to infrared radiation (colloquially also referred to as thermal radiation) and does not necessarily have to be wavelength-sensitive (ie it can be a monochrome camera). The infrared camera can, for example, have a greater sensitivity (ie

[0054] sensitivity) to infrared radiation (e.g. in the range from about 3.5 pm to about 15 pm) than to visible light (or at least to radiation with a wavelength of less than 0.78 pm).

[0055] The infrared radiation to which the infrared camera is sensitive may comprise light with a wavelength in a range of approximately 0.78 pm (micrometers) to approximately 1000 pm, e.g., mid-infrared (e.g., 3 pm to 50 pm) and optionally near-infrared (e.g., 0.78 pm to 3 pm) and / or far-infrared (e.g., 50 pm to 1000 pm). The infrared radiation to which the infrared camera is sensitive may, for example, comprise light with a wavelength in a range of approximately 3.5 pm to approximately 15 pm, which best corresponds to the expected temperatures of the machine tool bit.

[0056] In general, a body can emit infrared radiation, e.g. alternatively or in addition to visible light, for example from its surface. According to Planck's radiation law, the emitted infrared radiation (e.g. the distribution of the electromagnetic radiation power as a function of the wavelength) depends on the temperature of the body. The measured values ​​read out by the image sensor of the infrared camera (e.g. representing the pixel-by-pixel recorded intensity of the infrared radiation) are thus a function of a spatial temperature distribution, in particular a spatial distribution of infrared radiation, which in turn is a function, but not exclusively, of the temperature of the surface emitting the infrared radiation, in the field of view of the infrared camera. Further examples of parameters that influence the spatial distribution of infrared radiation include: the (e.g.material-dependent and / or roughness-dependent) reflectance and / or emissivity of the surface emitting infrared radiation. For example, there are materials that reflect infrared radiation almost totally, e.g. glass or still bodies of water, but also bare metal surfaces, and can therefore produce different “color values” even at the same temperature. Surface roughness, for example, influences the so-called emissivity, for example for infrared radiation. For example, rusty or scratched steel emits considerably more infrared radiation than bare steel of the same temperature. These parameters have a significant influence on the absolute temperature measurement. In other words, the image data captured by the infrared camera is based on sensor-detected infrared radiation, which is a function of the temperature of the source of the infrared radiation, i.e. this image data is based on infrared radiation (also referred to as infrared radiation-based).The image data can optionally be assigned to a temperature value or (after an optional error correction of reflections or material parameters and / or surface parameters) converted into the temperature value.

[0057] The color information in the image data can, for example, represent the intensity of infrared radiation recorded pixel by pixel or encode the temperature information. For example, the color information in the image data can be monochrome or polychrome (e.g., in the case of false color representation).

[0058] Optionally, the infrared camera can be part of a camera system comprising multiple infrared cameras whose fields of view, for example, overlap. The multiple infrared cameras can optionally be configured to provide image data of the camera system's field of view from multiple optical perspectives (e.g., provided by multiple lenses), e.g., stereoscopic image data. Stereoscopic image data makes it easier to distinguish between symmetrical and asymmetrical bit wear. However, stereoscopic image data can also be provided by a single infrared camera, as described in more detail later.

[0059] A sensor (also referred to as a detector) can be understood as a transducer that is set up to record a property of its environment (e.g. qualitatively or quantitatively) corresponding to the sensor type as a measured variable, e.g. a physical property, a radiation intensity, a chemical property and / or a material condition. The measured variable is the physical quantity (also referred to as the controlled variable) to which the measurement by means of the sensor applies. An example of a quantitatively recorded measured variable is a radiation intensity, the actual state of which can be converted into a measured value by means of the sensor. Each sensor can be part of a measuring chain that has a corresponding infrastructure (e.g. processor, storage medium and / or bus system and the like). The measuring chain can be set up to detect the corresponding sensor (e.g.To control a sensor (e.g., an image acquisition sensor), process its acquired measurement value as an input value, and, based on this, provide an electrical signal as an output value that represents the acquired input value. For example, the output value can indicate the measured value. The measurement chain can be implemented, for example, using a data processing device.

[0060] Reference is made here to the condition of a machine tool bit (also referred to as the bit condition). The condition of the machine tool bit may depend on one or more wear parameters, for example, the degree of wear (also referred to as the progress of uniform, symmetrical wear) of the machine tool bit as a wear parameter and / or the wear symmetry of the machine tool bit as a wear parameter (then also referred to as the wear type). The target condition of a tool bit may, for example, be the condition of an unused machine tool bit. The actual condition of the tool may deviate from the target condition depending on its usage time and usage intensity.

[0061] In various embodiments, the bit condition may be specified numerically (e.g., as a percentage or absolute value). Alternatively or additionally, the bit condition may be specified as a class from a group of classes (e.g., having the class "unworn" and the class "worn"). Then, determining the bit condition may comprise selecting one or more classes from the group of classes (also referred to as classifying). It can be understood that the group of classes, e.g., per wear parameter, may comprise two or more classes, for example, "high degree of wear," "medium degree of wear," and / or "low degree of wear." Further examples of classes include those representing one or more of the following: the presence of the bit ("e.g., chisel missing"), a need for maintenance of the bit (e.g.,in the event of a chisel blockage and / or the beginning of asymmetrical chisel wear), a need to replace the chisel (e.g. when the wear of the chisel is critical and / or when the remaining service life is zero), or the remaining service life of the chisel (e.g. "machine chisel is OK" or "machine chisel at 75% of the expected service life").

[0062] Analogous to the degree of wear, the wear symmetry can be specified numerically and / or as a class from the group of classes (e.g. class "asymmetric" and class "symmetric" and optionally having intermediate levels thereof). Then, determining the bit condition can involve classifying the actual wear symmetry, e.g. as "asymmetric" or "symmetric". Symmetrical wear (e.g. abrasive wear) can occur, for example, if the machine bit is continuously worn and / or if the machine bit rotates about its bit axis during the stock removal process. Non-symmetrical (also referred to as asymmetric) wear can occur, for example, if a brittle fracture (e.g. of the carbide pin) occurs, the carbide pin falls out due to faulty bedding, or if one rotation of the machine bit around its bit axis is blocked during the stock removal process (also referred to as bit blockage).

[0063] According to various embodiments, condition monitoring (e.g., bit wear monitoring) is implemented automatically using an infrared imaging process, particularly for underground working conditions where there is no visual view of the bits during cutting. Due to the extreme friction during cutting, the contact points of the bit with the rock heat up considerably. The resulting heat is usually distributed from the bit tip through the bit head and the bit shaft by thermal conduction to the bit holder, resulting in a different temperature distribution that is clearly distinguishable from the more distant components, which are recorded by one or more high-resolution infrared cameras. Due to continuous wear, the shape of the bit head, as well as its surface roughness, changes significantly during installation compared to its new condition (e.g., the target condition), not only in the case of sudden wear (e.g.,in the event of excavation or total demolition). During cutting, the shapes of the bit heads are clearly visible in the infrared image (also colloquially known as a thermal image); the corresponding contours can therefore be extracted using an image processing algorithm and compared with the product image (corresponding to the target state). If a bit gets lost during the cutting process, this is represented by the infrared image. For example, a dark area will be present at the position where the bit should be in the infrared image. For example, instead of the bit, the infrared image shows its background, e.g. other parts of the cutting head or the mining environment, until the bit holder itself comes into contact with the rock and heats up. This situation can also be identified early on by comparing it with the product image, so that wear of the bit holder can be completely avoided.

[0064] Various embodiments are based on high-resolution, fast infrared cameras and an analysis system (implemented, for example, by means of a processor) configured to immediately process (e.g., analyze) the image data (also referred to as recordings) provided by the infrared cameras (e.g., during or after the cutting phase) of the bits, some of which have been considerably heated due to the massive interaction with the rock, and to visualize the result of the condition analysis in the form of an evaluation map of the cutting drum with the bit positions (e.g., using a graphical user interface). The recording after the cutting phase can be performed while the cutting head is warm or cooling down (e.g., 2 to 5 minutes or even more after cutting). In this case, the period in which the machine is not cutting can be used to perform the recording (during which the cutting head can be scanned by sensors).

[0065] In various embodiments, all chisels are identified with each rotation of the cutting head, quasi cyclically, for example in conjunction with an angle sensor that detects the position of the cutting head, or also based on their (e.g. stored) position and / or relative arrangement on the same, their geometric profile, which is clearly distinguishable due to the temperature difference, is determined, if necessary from several viewing angles (also referred to as perspectives), and compared with the target state.

[0066] The evaluation map (also called a condition map) can be visualized in the operator's cab, making it easier for the user to monitor the condition of each bit (e.g., almost) in real time and detect problematic signs of wear early on. This does not require the absolute temperature of the bits themselves to be determined. Optional markers on the bit head surface significantly facilitate image processing.

[0067] According to various embodiments, one or preferably several infrared cameras are arranged near the cutting head equipped with chisels, preferably but not limited to round-shank chisels (for example, protected from rockfall), and continuously or periodically (for example, after completion of a cutting process across the entire face height and / or width) record infrared images (colloquially also referred to as thermal images) of the chisels, which enter the recording area of ​​the infrared camera from the cutting area with the thermal signature of the cut just made or the completed cutting cycle. The shape or, for example, the three-dimensional profile of each chisel is derived from the infrared images obtained and compared with the good image upon installation of the chisel. Depending on the result of this comparison, a wear status is assigned and visualized on a cutting drum map as a status map, e.g.using colored dots, numbers, codes, or similar. If predefined values ​​are exceeded, an acoustic and / or visual alarm can be triggered, alerting the user to the detected condition. Alternatively or additionally, the alarm can trigger an emergency stop, for example, if a chisel blockage or a broken chisel is detected as the chisel condition.

[0068] Various embodiments are configured to distinguish between different types of wear when determining the chisel condition, which can have different effects on the urgency of a chisel change, and thus contribute to a significant optimization of the operation of the removal machine.

[0069] In contrast to conventional concepts, various embodiments evaluate geometric profiles using imaging processes. This allows both the type of wear and the extent of the affected area to be identified early on, allowing the removal machine to be operated proactively and / or without fixed inspection stops. Ideally, chisels are changed at an optimal time when the increased contact forces caused by wear and the decreasing removal performance are in a favorable relationship. Conventional concepts that use infrared cameras ignore the geometric shape (also referred to as geometry) and wear surface of worn chisels, determining only absolute temperature values ​​of the chisel.According to various embodiments, the chisel condition can be reliably determined based on image data even if this image data originates from a chisel that is not currently fully engaged in cutting and is already cooling down, or if cut material adheres to it. This significantly improves the detectability of chisel shape changes.

[0070] According to various embodiments, infrared-based shape detection of the bit heads is carried out during operation. In contrast to conventional concepts, which use infrared cameras to only record the absolute temperature of the bit tip, which is dependent on both the rock type and operational management, according to various embodiments, even small temperature differences can be sufficient to reliably determine the bit condition, which is therefore considerably more robust against disruptive influences (such as dust and water). Another aspect according to various embodiments is spatial shape detection of the rotatably mounted bits, which further improves the data basis for determining the bit condition.

[0071] According to various embodiments, the individual degree of wear of each chisel on the cutting head is determined, for example, quantitatively during operation, and a corresponding gradual rating is assigned to each chisel. In addition, the type of wear can be identified, for example, distinguishing between asymmetrical wear (e.g., when parts of the chisel tip break off) and symmetrical wear (e.g., normal wear on all sides). The condition analysis can be performed during operation, and the results can be transmitted both visually to the operator and directly to the drive train, for example, to trigger an emergency stop after a chisel breakage or to indicate the specific chisels that need to be replaced to avoid more serious damage.

[0072] Conventional concepts require the actual temperature distributions and / or infrared images, for example by searching for the peak temperature value based on them.

[0073] In contrast, according to various embodiments, no temperature is evaluated (e.g., absolute temperature), but rather an identification of the contour, for example, of gradients, based on image data representing a spatial distribution of the infrared radiation intensity (illustratively, an infrared radiation intensity image), for example, representing the associated radiation values. In some embodiments, one or more than one chisel head is determined (e.g., its position and / or identity) based on the image data. Based on the image data, an extraction of the 3D profile of the chisel head can be performed in order to compare this 3D profile, which is invariant with temperature, with a good profile (e.g., profile of the reference state).

[0074] This takes into account the fact that infrared images and temperature readings based on them can be susceptible to interference, for example, due to differences in the emissivity of infrared radiation (also referred to as IR radiation), which can depend on the material and surface condition. In contrast, various embodiments have found that determining a contour is less susceptible to interference than temperature readings (absolute values) or assessments of the bit condition based on them.

[0075] Fig. 1 illustrates a method 100 according to various embodiments in a schematic flow diagram. The method comprises, in 101 (also referred to as geometry determination 101), determining an indication (also referred to as geometry indication) that represents at least one (i.e., one or more than one) geometric property of the bit; and in 103 (also referred to as state determination 103), determining a state (also referred to as chisel state) of the bit based on the indication. The chisel geometry can be determined based on image data 807i, which, for example, comprises one or more than one individual image of the chisel and / or represents the chisel from multiple perspectives. The result of state determination 103 can comprise the actual state (also referred to as determined state) of the chisel (also referred to as actual chisel state).For ease of understanding, reference is made here to a wear condition as an example of a chisel condition. The description can also apply analogously to other types of chisel conditions.

[0076] To condense the description, reference is made herein, among other things, to a condition analysis 807 (e.g., implementing condition monitoring), which includes geometry determination 101 and condition determination 103. Furthermore, it can be understood that what is described herein for an individual bit (e.g., processing image data and the like) can apply analogously to each bit in a group of bits (also referred to as a monitoring group).

[0077] Optionally, the method comprises one or more than one of the following: in 801, reading the image data 807i from the infrared camera (also referred to as readout process 801); in 803, capturing the image data by means of the infrared camera (also referred to as image capturing 803 or optical capturing); in 805, generating instructions (also referred to as instructing 805) based on a result of the state determination 103; in 809, removing a material (also referred to as removal material) by means of the chisel (also referred to as removal process 809 or cutting process 809); and / or, in 811, comparing the geometry information with a reference state of the chisel (also referred to as geometry comparison 811).

[0078] During the removal process 809 (e.g., rock removal processes), the chisel 5 can be moved (also referred to as chisel movement), e.g., repeatedly according to a removal sequence comprising a first phase 809a (also referred to as cutting phase or cutting for short), in which the chisel is in contact with the material to be removed, and a second phase 809b (also referred to as idle phase), in which the chisel 5 is at a distance from the material to be removed. In the idle phase, the chisel 5 can, for example, be moved along a self-contained path (also referred to as chisel path) away from the material to be removed and / or towards the material to be removed. If the removal process 809 is ended (e.g., interrupted), the chisel can continue to be moved along the chisel path, but without touching the material to be removed (also referred to as idle operation).

[0079] If the chisel is attached to a so-called cutting head, the chisel path can be circular (also referred to as circular motion) or defined by the rotation of a carrier chain equipped with chisels. Alternatively or additionally, the (e.g., circular) chisel path along which the chisel 5 is moved can lie in a so-called rotation plane 1002 of the chisel (see, for example, Fig. 11).

[0080] The chisel movement can occur, for example, repeatedly according to the removal sequence, while the readout process 801 and / or the image acquisition 803 is taking place. Alternatively, the chisel movement can be interrupted for the duration of the image acquisition 803.

[0081] In some embodiments, the instructions may be generated according to a network communication protocol, e.g., as a message or in the form of another signal. The instructions may optionally include an indication of the result of the state determination 103 (e.g., the determined state).

[0082] In a first exemplary implementation of the instructing 805, the instructions instruct the output of the result of the state determination 103 or at least provide a human-perceivable output based on the result of the state determination 103. Then, the instructions can be addressed, for example, to a user interface that is controlled by the instructions.

[0083] In the first or an alternative second exemplary implementation of instructing 805, the instructions instruct to change a movement of the chisel, e.g., to stop, slow down, or accelerate. Then, the instructions can be addressed, for example, to a drive train that is controlled by the instructions. The drive train can be configured, for example, to supply kinetic energy to the chisel 5 (in order to drive the chisel movement). For example, the instructions can instruct the drive train to bring the chisel to a standstill in a predefined position and / or to change its movement speed. For example, the predefined position can be configured to facilitate accessibility to the chisel (e.g., for inspection or replacement).

[0084] Optionally, the image capture 803 can be synchronized with the chisel movement (also referred to as synchronized image capture), e.g., such that their frequencies are interdependent. The synchronized image capture can be implemented, for example, by means of a sensor (e.g., a rotation angle sensor) configured to detect the chisel movement (e.g., circular movement). For example, the rotation angle sensor can be configured to detect a rotation (e.g., the rotation frequency and / or rotation speed) of the cutting head. The control of the infrared camera can then be based on data originating from the sensor and / or representing the chisel movement.

[0085] The duration of the complete circular motion can, for example, correspond to the duration of the removal sequence. Reference is made here, among other things, to the circular motion, although it should be understood that the description can apply analogously if the chisel path is shaped differently.

[0086] However, the frequency of the recording can also be controlled by a specific position (height, lateral deflection) of the movable cutting head carrier or by a signal provided by the machine control system, for example to always record the bit status after a complete cut across the entire face and for this purpose to expose the camera to the harsh environmental conditions only for a short time, outside of the active cutting process.

[0087] In the following, various implementations of the method 100 using an ablation system are explained, which are to be understood as exemplary.

[0088] Fig.2 illustrates an ablation system 200 according to various embodiments in a schematic construction diagram.

[0089] The removal system 200 comprises a removal machine 202 and an infrared camera 6. The removal machine 202 comprises the chisel 5 and is configured to remove the material to be removed using the chisel 5, for example, by pressing the chisel 5 against the material to be removed. The infrared camera 6 can be configured to capture image data. During operation of the removal system 200, for example, when the removal process 809 is carried out using the removal machine 202, the infrared camera 6 can be directed at the removal machine 202, e.g., its chisel 5 or at least the chisel path, so that image data of the chisel 5 can be captured using the infrared camera 6.

[0090] The ablation system 200 further comprises a data processing device 106 configured to carry out the method 100. For this purpose, the data processing device 106 can be communicatively coupled 204 to the infrared camera 6 during operation, e.g., wirelessly and / or wired.

[0091] An exemplary implementation of the removal machine 202 has a cutting head 2, which is configured to hold one or more than one chisel 5. For this purpose, the cutting head 2 can, for example, have one or more than one so-called chisel holder 8, each of which is configured to hold a chisel 5. The chisel holder 8 can, for example, have a cavity (also referred to as a chisel pocket) for receiving the chisel 5 and an optional locking device (not shown). The locking device is configured to positively lock the chisel 5 received in the cavity. This allows the chisel 5 to be changed quickly and cost-effectively. The cavity can optionally have an insert made of wear-resistant material, a so-called wear bushing.

[0092] The cutting head 2 can form the last link in the drive train of the removal machine 202 (i.e., its kinematic chain). The drive train can further comprise one or more drives configured to supply kinetic energy to the chisel 5, for example, by supplying a torque to the cutting head 2 or by displacing the cutting head 2. The rotational movement of the cutting head 2 sets the chisel 5 in its circular movement around the rotation axis 201 of the cutting head 2. The frequency of the rotational movement of the cutting head 2 and the frequency of the circular movement of the chisel 5 (also referred to as the rotational frequency of the chisel 5) can be identical. The rotational frequency at which each chisel appears in the field of view of the camera can range from approximately 0.2 Hz to approximately 2 Hz, for example, approximately 0.5 Hz (which corresponds to 30 drum revolutions per minute).

[0093] The cutting head 2 is rotatably mounted about the rotational axis 201 (which is arranged within the cutting head 2). For example, the removal machine 202 can have a bearing device that has a pivot bearing that provides the rotational axis 201 (also referred to as the head axis 201). The head axis 201 can be transverse to the rotational plane 1002 of each chisel 5 that is moved by the cutting head 2.

[0094] Optionally, the support device may comprise an arm (also referred to as a boom) that holds the cutting head 2. In this case, the support device, e.g., its arm, may be configured to move the rotation axis 201 of the cutting head 2, e.g., to translate and / or rotate it, along a direction of movement (in the case of rotation, also referred to as a pivoting movement).

[0095] If the chisel is a so-called round-shank chisel, it can be configured to rotate in the chisel pocket around its chisel axis 203 (also referred to as self-rotation of the chisel or, simply, as self-rotation). This improves the symmetry of wear of the chisel 5. The self-rotation of the chisel can occur (e.g., only) during the cutting phase and / or be stimulated by the interaction with the material being removed (e.g., rock).

[0096] Examples of the removal machine 202 include: a cutting machine, an excavator, a roadheader, a so-called continuous miner, a so-called surface miner, or a tunnel boring machine. Some implementations of the removal system 200 will first be explained below, followed by specific embodiments of the method 100. Reference is made to image data, on which the geometry determination 101 is based, which is provided by a camera system. It can be understood that what has been described for the image data from the camera system can apply analogously to image data provided by exactly one or more than one infrared camera. Fig. 3 illustrates a removal system 200 according to various embodiments 300 in a schematic perspective view, in which the removal machine 202 is configured as a so-called continuous miner 7 (also referred to as a "continuous cutting machine").The continuous cutting machine 7 has one or more cutting heads 2 configured as a cross-cutting head. The cutting head can be cylindrical (then also referred to as a cutting roller).

[0097] The pivoting movement 301b of the removal machine 202 can be about a rotation axis 301 arranged parallel to the head axis 201 and outside the cutting head 2. Alternatively or additionally, the bearing device 3 can be configured to displace the head axis 201 along one or more translation axes and / or to rotate it about one or more additional rotation axes (see arrows).

[0098] Furthermore, the removal system 200 may include one or more infrared cameras 6, exemplary mounting positions of which include: on the boom 3 (e.g., a front or rear of the boom 3), on the user cabin 4 of the removal machine 202, next to the removal machine 202 (e.g., supported on a base of the removal machine 202), on a chassis of the removal machine 202.

[0099] An exemplary implementation of the infrared camera 6 arranged next to the ablation machine 202 can be supported by a frame 352 having one or more bases (e.g., a tripod) arranged on a surface on which the ablation machine 202 stands. Alternatively or in addition to the base, the frame 352 can also have a handle for carrying by the user. This improves the flexibility of the ablation system 200.

[0100] In general, it should be noted that any other mounting position can be selected, provided it allows an infrared camera 6 mounted there to be directed at a chisel 5, so that the chisel path is at least partially located within the infrared camera's field of view. The geometry determination 101 can be based on the image data from only one infrared camera 6 or on the image data from multiple infrared cameras 6 that differ from one another in their mounting position. The more infrared cameras 6 or different mounting positions used, the better the data basis for the geometry determination 101, as will be explained in more detail later.

[0101] Optionally, the image data can be displayed directly using a graphical user interface, e.g. its display device in cabin 4, or on a remote control and monitoring unit.

[0102] As shown, the cutting head 2 can have a plurality of bits 5 that differ from one another in the bit path along which they are moved. Alternatively or additionally, the cutting head 2 can have a plurality of bits 5 that coincide in the bit path along which they are moved. It should be noted, however, that it is not absolutely necessary for the movement path of each bit 5 on the cutting head 2 to be arranged within the field of view of an infrared camera 6 of the camera system. In other words, the monitoring group does not have to include all bits. A type of random condition analysis 807 can just as easily be performed.

[0103] Analogous to embodiments 300, Fig. 4 illustrates the removal system 200 according to various embodiments 400 in a schematic perspective view, in which the removal machine 202 is configured as a so-called roadheader 1. The roadheader 1 has one or more cutting heads 2 configured as cross-cutting heads. For example, the boom 3 can be arranged between two cross-cutting heads.

[0104] Here, reference is made by way of example to the roadheader and also to the continuous cutting machine, whereby it can be understood that what is described for the roadheader can apply analogously to the continuous cutting machine and vice versa and also to a removal machine of a different type.

[0105] 5A and 5B each illustrate the ablation system 200 according to various embodiments 500a, 500b in a schematic perspective view looking toward the cutting head 2, which differ from one another in the configuration of the camera system 502. As indicated above, the camera system 502 can comprise a plurality of infrared cameras 6, which are mounted, for example, on the boom 3 and from which the image data on which the geometry determination 101 is based originate.

[0106] According to embodiments 500a, the camera system 502 is configured (e.g., arranged and aligned) such that each bit 5 of the monitoring group is moved through the field of view of more than one infrared camera 6 of the camera system 502 per rotation of the cutting head 2. The image data then includes several individual images of the bit per bit and per circular movement of the bit, which differ from one another in their viewing angle (also referred to as perspective). This facilitates the more reliable determination of the degree and / or type of wear, as will be explained in more detail later.

[0107] In an exemplary implementation of embodiments 500a, camera system 502 is configured to capture stereoscopic image data of one or more than one chisel 5. For example, immediately adjacent infrared cameras 6 of camera system 502 (also referred to as a camera pair) are configured such that their fields of view overlap on cutting head 2. The stereoscopic image data comprise, for example, two individual images of chisel 5 (e.g., in the same position and / or at the same time) per chisel 5 and per circular movement of chisel 5, which individual images differ from one another in their respective viewing angle (also referred to as perspective). According to embodiments 500b, camera system 502 is configured to capture only monoscopic image data of one or more than one chisel 5.For example, directly adjacent infrared cameras 6 of the camera system 502 are configured such that their fields of view are adjacent to one another at the cutting head 2 or at least spaced apart. Embodiments 500b are advantageous, for example, when fewer infrared cameras 6 are available per chisel, when a higher image resolution is required, or when the available infrared cameras 6 have too low a resolution to capture multiple chisels 5 with sufficient accuracy.

[0108] According to embodiments 500b, for example, each chisel 5 can be moved through the field of view of exactly one infrared camera 6 per rotation of the cutting head 2. For example, the chisel can only be captured from one perspective per rotation of the cutting head 2.

[0109] Image capture 803 according to embodiments 500b may be sufficient (e.g., equivalent to embodiments 500a) if the chisel 5 is configured for self-rotation (which may be the norm for round-shank chisels). In this case, the rotational position of the chisel relative to the infrared camera 6 at the time of image capture differs at least slightly during successive circular movements due to the chisel's self-rotation. The successive individual images thus also differ in the perspective from which the chisel 5 was optically captured.

[0110] If the chisel's rotation is blocked (also referred to as a chisel blockage), the chisel is repeatedly detected in the same position in both embodiments 500b and 500a. This chisel blockage can therefore be determined by comparing the successively acquired image data or by geometric comparison 811, as will be explained in more detail later. For example, determining the state as a chisel state can identify the chisel blockage if the result of a comparison of the successively acquired image data or the result of geometric comparison 811 falls below a threshold value.

[0111] In an exemplary implementation of embodiments 500a (not shown), the ablation system 200 comprises a plurality of camera systems 502 according to embodiments 500b, between which the boom 3 is arranged. Clearly, one of the camera systems 502 can be directed at a lower portion of the cutting head 2 and one of the camera systems can be directed at an upper portion of the cutting head 2.

[0112] Figs. 6A and 6B each illustrate the removal system 200 according to various embodiments 600a, 600b in a schematic perspective view looking toward the cutting head 2, which differ from each other in the configuration of the camera system 502, analogous to embodiments 500a, 500b. In contrast, the support device 3 additionally has a cross member 602 that protrudes beyond the boom and supports the camera system 502. The cross member 602 improves the perspective of the camera system 502 and therefore improves the data basis for the geometry determination 101.

[0113] For example, each cutting head 2 can be assigned an infrared camera 6, which is directed toward the cutting head 2, for example, such that its field of view covers the (e.g., entire) cutting head 2. For example, the entire cutting head 2 can be arranged in the field of view of the infrared camera 6 assigned to it (see embodiments 600b).

[0114] Analogous to the embodiments 500a, the camera system 502 according to the embodiments 600a is configured (e.g. arranged and aligned) such that the or each chisel 5 is moved through the field of view of more than one infrared camera 6 of the camera system 502 per revolution of the cutting head 2, e.g. such that stereoscopic image data of at least one (ie one or more than one) chisel 5 is captured.

[0115] Analogous to the embodiments 500b, the camera system 502 according to the embodiments 600b is configured (e.g. arranged and aligned) such that the at least one chisel 5 is moved through the field of view of exactly one infrared camera 6 of the camera system 502 per revolution of the cutting head 2, e.g. so that only monoscopic image data of the at least one chisel 5 are captured.

[0116] Fig. 7 illustrates the ablation system 200 according to various embodiments 700 in a schematic perspective view looking toward the cutting head 2, analogous to embodiments 600a, 600b, but with the difference that each cutting head 2 is assigned two infrared cameras 6 (also referred to as a camera pair), which are directed toward the cutting head 2, for example, such that their field of view covers the (e.g., entire) cutting head 2. This further improves the data basis. Of course, more than two infrared cameras can be present per cutting head 2 and directed toward the cutting head 2.

[0117] Analogous to the embodiments 600a, each camera pair whose infrared cameras 6 are directed at a cutting head 2 can be configured (e.g., arranged and aligned) such that stereoscopic image data of the cutting head 2 is captured.

[0118] In the following, various exemplary implementations of the method for the embodiments of the camera system mentioned herein are explained.

[0119] Fig. 8 illustrates the geometry determination 101 according to various embodiments in a schematic diagram 800. The geometry determination 101 can be configured to process the image data 807i as input and output the geometry information 852 (as a result of the geometry determination 101). The geometry determination 101 can comprise, in 851, determining a data-based representation 13 (also referred to as geometry representation 13) of a geometry of the chisel 5 (e.g., here, by way of example, the contour 13 of the chisel head) based on the image data. The geometry representation 13 can represent one or more of the following geometric properties of the chisel (e.g., the chisel head): a contour; a cross-sectional area enclosed by the contour of the chisel (e.g., the chisel head) and / or a planar projection (from the viewing angle of the infrared camera) thereof; a geometric extent.

[0120] The determination 851 of the geometry representation 13 can be carried out, for example, using one or more than one image processing algorithm. The image processing algorithm can, for example, have a filter (also referred to as an image filter or graphics filter) that is configured to output, for each individual image, several image components (e.g., pixel coordinates) of the individual image that satisfy a predetermined criterion (also referred to as filtering out). Examples of the image processing algorithm include: edge detection, a Fourier high-pass filter, a threshold filter, a Fourier low-pass filter, a color value difference analysis, object recognition, geometry recognition, and a trained algorithm. The trained algorithm can, for example, be trained using machine learning, for example based on training data that includes image data of chisels of known geometry.

[0121] The trained algorithm can be, for example, a single-layer or multi-layer artificial neural network (ANN) combined with a gradient descent method. The network can be a feedback or feedforward multilayer perceptron, for example. The ANN can perform self-learning classification, for example, using learning vector quantization; it can incorporate random or statistical learning variables (probabilistic ANN), or it can process time-delayed inputs from previous runs to achieve a better classification (time-shifted ANN).

[0122] The geometry representation 13 can alternatively or additionally be determined in general by means of any planimetry process.

[0123] The color value difference analysis can, for example, have a difference criterion as a criterion, which is met for an image component (e.g., a pixel) when the difference between the pixel's color value and adjacent pixels exceeds a threshold value. This makes it easier to determine the contour of the geometric representation 13. Analogously, a threshold value of a gradient of a fitting calculation based on multiple color values ​​can serve as a criterion. Alternatively or additionally, those image components can be filtered out whose color value exceeds a threshold value and / or whose difference between the pixel's color value and adjacent pixels falls below a threshold value (also referred to as a homogeneity criterion). This makes it easier to determine the area of ​​the geometric representation 13.The geometry specification may comprise one or more than one property of the data-based geometry representation 13 (also referred to as a geometry property) or at least be derived therefrom. Examples of the geometry property include: a circumference 13u of the geometry representation 13; a (e.g. geometric) center of gravity 13m (preferably of the planar projection enclosed by a contour of the chisel), e.g. its position; an area of ​​the surface 13a (e.g. representing the cross-sectional area of ​​the chisel); an angle 13w enclosed by two edges of the geometry representation 13 (e.g. at the chisel tip, also referred to as wedge angle 13w); an extension 13d of the geometry representation 13 (e.g. starting from the chisel tip, e.g.along the bit axis, also called bit height); one or more than one geometric property of a thermal mark (also called a mark property), which will be discussed in more detail later.

[0124] Each of these geometric properties can, in itself, be a sufficient basis for performing a reliable state determination 103. However, it can be understood that the reliability of the state determination 103 can be improved if the geometric specification 852 includes multiple geometric properties that can optionally be weighted. Weighting achieves an additional degree of freedom to adapt the method 100 to different types of interference sources and thus compensate for them.

[0125] Shown is a multi-component geometry specification 852 that has multiple numerical values ​​as components (here, for example, w1,..., wn; m1,..., mn; d1,..., dn; a1,..., an) and is expressed vectorially for shortening the notation. The multi-component geometry specification 852 improves the reliability of the information on which the state determination 103 is based. Expressed in this vectorial notation, the multi-component geometry specification 852 can have one or more dimensions, each dimension referencing a property in which the values ​​differ from one another (e.g., a time, a type, etc.).

[0126] For example, a first dimension 852a of the geometry specification 852 can reference a type of geometry property. Alternatively or additionally, a second dimension 852b of the geometry specification 852 can reference the individual image (here, for example, #1, #2, etc.) on which the geometry specification 852 is based, e.g., its image number and / or its time, and / or reference a temporal progression in another way. Of course, more or fewer properties of the geometry specification 852 can also be referenced. For example, the perspective on which the component is based can be referenced, e.g., for each chisel and / or circular movement of the chisel.

[0127] In the exemplary matrix shown, all entries in column 1 can be based on the same single image or multiple single images from the same time. Alternatively or additionally, all entries in the angle 13w row can specify the value of an angle 13w enclosed by two edges of the geometry representation 13 (e.g., at the chisel tip). The entries along the second dimension 852b then represent the temporal progression of the geometry properties, which makes it easier to detect small changes in the chisel geometry.

[0128] Optionally, the state determination 103 can be based on a numerical value that is a function of the (e.g., weighted) values ​​of multiple geometry properties of different types and / or different points in time. This improves the reliability of the information on which the state determination 103 is based. Weighting the values ​​of multiple geometry properties of different types and / or different points in time facilitates the adaptation of the method to the specific application.

[0129] Optionally, the image processing algorithm can comprise an algorithm configured to convert a preliminary stage of the geometry representation 13 into the geometry representation 13. An example of this is the smoothing of the surface 13a, the contour 13u, or the like. An alternative or additional example is a fitting calculation that converts a collection of pixel coordinates into a vector-based path. The path can, for example, be a polyhedron, which is used as the contour 13u, and / or can be smoothed. The same applies analogously to the nodes of the path.

[0130] As explained above, the method 100 optionally comprises the geometry comparison 811. In this case, the state determination is based on a result (also referred to as a comparison result) of the geometry comparison 811. In a first exemplary implementation thereof, the geometry specification 852 is compared with a (e.g. stored) target state of the chisel as a reference state (also referred to as an absolute comparison), e.g. with a target geometry specification. In the first or an alternative second exemplary implementation thereof, the geometry specification is compared with a previous (e.g. stored) geometry specification of the same chisel as a reference state (also referred to as a relative comparison). This may optionally be necessary if a newly inserted, practically unused chisel has different surface properties than a used chisel and contour recognition is therefore more difficult.The target geometry specification could then, for example, be determined after a defined low number of operating hours. Alternatively or additionally, the relative comparison may involve comparing several components of the geometry specification of the same type with each other, provided the geometry specification is time-dependent.

[0131] The absolute comparison facilitates the comparison of several bits with each other and / or allows the remaining service life of a bit to be determined. The relative comparison improves the reliability of the method. In an example scenario, the geometric property (e.g. contour) of the bit is superimposed by adhering rock material. Errors due to this superimposition can, however, be avoided by a statistical comparison with the previous images as a relative comparison and an instruction to issue a slightly delayed warning (as a signal). Alternatively or additionally, the adhering material can appear darker even in the absolute comparison due to the lower thermal conductivity and differences in emissivity and can therefore be distinguished from the actual bit.

[0132] The method 100 can optionally include classifying the determined geometry information 852 and / or the underlying image data as invalid (also referred to as discarding) based on a result of the geometry comparison 811. In this case, the state determination 103 can optionally be configured to ignore all geometry information 852 classified as invalid. In an exemplary implementation of the discarding, this can be done based on the result of the relative comparison, for example, if a deviation of the actual geometry information from the previous geometry information exceeds a threshold value. For example, a chisel contour can only be classified as valid if it occurs repeatedly in a similar form and can otherwise be discarded as an outlier.

[0133] In the following, various implementations of the method 100 are explained in which the geometry representation 13 is determined.

[0134] Fig. 9 illustrates the method 100 according to various embodiments in a schematic flow diagram 900. The image capture 803 and / or the camera system 502, by means of which the image capture 803 takes place, can be configured to capture image data 807i that have exactly one individual image 9 per (e.g., n) circular movement(s) of the chisel 5 around the rotation axis 201 (n can be, for example, 1 or more). For example, the image capture 803 can be synchronized with the circular movement of the chisel 5, e.g., such that an image capture frequency fß (also referred to as image capture frequency) is a function of the rotational frequency fo of the chisel 5.

[0135] For example, the relation can be satisfied: n-fo fß, where n is a natural number.

[0136] It may be advantageous if the condition analysis 807 is performed individually for each bit 5 on the cutting head 2, i.e., the monitoring group includes all bits 5 on the cutting head 2. Therefore, it can be understood that the processing of image data described herein can be performed analogously for each bit 5 on the cutting head 2, but this does not necessarily have to be the case. It may also be sufficient not to perform the condition analysis 807 for all bits 5 on the cutting head 2 in order to save resources. In that case, the monitoring group may include only a portion (e.g., less than 90% or less than 75%) of the bits 5 on the cutting head 2.

[0137] It may also be advantageous if the condition analysis 807 of each bit 5 in the monitoring group is based on at least one individual image of the bit 5 per time interval. The time interval may, for example, be the duration of a complete circular movement of the bit 5 (i.e., 1 / fo). In this case, the bit 5 can be optically recorded each time it passes the camera system. However, this may exceed the image recording frequency at which the camera system 502 delivers reliable individual images, for example depending on the number of bits 5 held by the cutting head 2. In this case, or for other reasons, it may also be sufficient to use n times the duration of a circular movement of the bit 5 as the time interval. It may also be advantageous to adapt the image recording frequency to the work sequence, for example after each full cut on the face, while the machine moves the boom idle to a new starting position.

[0138] As part of the image data 807i, a temperature-based individual image 9 (also referred to as infrared image 9) of the chisel 5 during the removal process 809 is shown here as an example. Due to the mechanical friction of the chisel 5 on the material being removed during the removal process 809, thermal power is introduced into the chisel 5 (mainly at its chisel tip), which leads to heating of the chisel 5. This is counteracted by the cooling of the chisel through the emission of infrared radiation and heat transfer to its surroundings (e.g., through heat conduction in the chisel and at contact points on the chisel holder). Cooling and heating reach an equilibrium when the chisel reaches the so-called operating temperature, around which the actual temperature of the chisel 5 fluctuates in the cycle of the circular movement and / or the removal sequence.The average operating temperature of the chisel can, for example, be greater than approximately 150°C or approximately 250°C in normal operation without increased wear events such as blockages, while at the tip, even in normal operation, temperatures of more than 750°C can be reached for short periods.

[0139] The transfer of heat from the chisel to the chisel holder, for example, is a function of the thermal conductivity of the latter, the contact area between them and the contact time between them.

[0140] Put simply, a heat flow occurs from the chisel tip 10 through the chisel head 11 to the chisel holder 8 or at least the chisel shank, resulting in a temperature gradient represented by the color information of the infrared image 9. For example, a higher brightness value of the infrared image 9 corresponds to a higher temperature and thus to the chisel head 11.

[0141] This temperature gradient arises shortly after the start of the removal process 809 (for example, after a short cutting phase) and can also be recorded during the entire circular movement of the bit, even if the bit is in contact with the material to be removed for only a fraction of the circular movement. This also applies to the time in which the removal process 809 is interrupted, for example, when no cutting is taking place, which can be the case when repositioning after cutting a face from top to bottom or vice versa with a roadheader or a continuous cutting machine. Depending on the specific implementation, the image can only be recorded when the removal process 809 is interrupted, ie, when no bit is in contact with the material to be removed and / or the removal machine 202 is at a distance from the material to be removed.

[0142] In one embodiment (e.g., the case explained above, preferably when recordings are made during cutting, where the risk is particularly high), the ablation system may include a camera protection device that protects (e.g., covers) the camera system (e.g., one or more camera lenses thereof) from solid particles (e.g., flying cutting material) from the ablation process 809. However, it should be understood that the camera protection device may alternatively or additionally be used in other cases, as will be described in more detail later.

[0143] In another implementation, the image capture may occur when the removal process 809 is performed by means of the cutting head 2 (e.g., a cutting roller 2), e.g., when the chisel is in the idle phase of its chisel path, or even in idle operation (e.g., in an idle rotation) after the removal process 809. Optionally, the chisel 5 and the chisel holder 8 may be captured from multiple perspectives.

[0144] When the infrared camera 6 begins capturing images (also referred to as recording) after or even during a removal process 809, the chisel 5 is clearly visible in the infrared image 9 due to the temperature gradient relative to the chisel holder 8, the cutting roller 2, and / or the surroundings, for example, by means of the image processing algorithm or another image processing process. In the infrared image 9 from the infrared camera 6, the highest temperature can be seen at the chisel tip 10 (e.g., based on the brightness), followed by the chisel head 11 and the chisel holder 8.

[0145] If the temperature is encoded using brightness values, the image area with the highest temperature in the infrared image 9 is the brightest, while the background 12 (this can be either the cutting roller 2 or the surrounding area) is somewhat darker. In this case, the geometry determination can include determining the chisel contour 13 of the chisel head 11 as a geometry representation 13 based on the bright image area of ​​the infrared image 9.

[0146] If the chisel 5 and the chisel holder 8 differ in their thermal conductivity and / or in the material they are made of, the temperature differences between them are even greater and thus easier to determine. However, the radiation emitted by the bodies captured in the infrared image can also depend on the emissivity of the bodies' surfaces, so that bodies with the same temperature can be displayed differently in the captured infrared image, e.g. a new chisel (or chisel holder), a worn chisel (or chisel holder), and a corroded chisel (or chisel holder). Chisels with scratches, adhering dirt, and corrosion emit infrared radiation better than new chisels with a comparatively smooth surface, so that their contours are more clearly visible in the infrared image the longer they have been in use.

[0147] Fig. 10 illustrates the method 100 according to various embodiments in a schematic flowchart 1000 similar to the flowchart 900, with the difference that the camera system 502 captures (e.g., per circular movement) several individual images of the bit 5 that differ from one another in perspective (also referred to as image perspective). For example, the several individual images (infrared images) are captured by the same infrared camera 6 from different viewing angles.

[0148] Fig. 11 illustrates the method 100 according to various embodiments in a schematic flowchart 1100 similar to the flowcharts 900, 1000, with the difference that the infrared camera 6 is arranged next to a plane 1002 (also referred to as the orbital plane) in which the chisel path is arranged (also referred to as a lateral perspective). Image capture 803 is shown on the left with a view along the head axis 201 and on the right with a view perpendicular to the head axis 201.

[0149] This lateral perspective can arise, for example, when several chisel paths arranged side by side pass through the field of view of the same infrared camera 6. However, a lateral perspective can also arise when the chisel axis of a chisel 5a (see Fig. 5B) is oblique to the rotation plane 1002 of the chisel 5a, which occurs, for example, at the edge sections of a cutting head 2 (e.g., a cutting roller 2) when a laterally directed removal process 809 is to be favored.

[0150] In the case of the lateral perspective, it is possible to use the same infrared camera 6 to determine multiple geometric representations 13 that correspond to different perspectives of the cutting head 2. This offers the same possibilities as the evaluation of stereoscopic image data acquired by multiple infrared cameras (corresponding to the same image acquisition time).

[0151] Fig. 12 illustrates a configuration of the camera system during image capture 803 according to various embodiments in a schematic perspective view 1200, for example, analogous to image capture 803 of flowcharts 900, 1000, and / or 1100. The camera system can have two or more infrared cameras 6, which capture the chisel 5 (e.g., at the same time) from different perspectives (also referred to as stereo view). This makes it easier to provide stereoscopic image data. This stereo view makes it easier to determine a fluctuation in the chisel geometry and / or a dependence of the chisel geometry on the perspective. This makes it easier to distinguish between symmetrical and asymmetrical chisel wear as a type of wear. Fig.13 illustrates a chisel 5 according to various embodiments 1300 in a schematic side view 1300a with a viewing angle transverse to the chisel axis 203 and a schematic top view 1300b with a viewing angle along the chisel axis 203, in which the chisel 5 has a marking 14 (also referred to as a thermal marking 14, wear marker, or simply a marker) on the chisel head 11. According to various embodiments, it has been clearly recognized that such a thermal marking 14 is identifiable based on the image data and stands out from the rest of the chisel 5. For example, it has been observed that even fresh scratches on an otherwise brand-new chisel appear darker in the infrared image.

[0152] The thermal marking 14 can have one or more segments (also referred to as a marking segment). The thermal marking 14 of the chisel 5 (e.g., each marking segment thereof) can differ from the chisel head 11 (e.g., the thickened portion 11k and / or the chisel tip 10) in at least one thermal property, for example, in a thermal emissivity and / or a thermal conductivity. This ensures that the thermal marking 14 becomes visible as an inhomogeneity in the infrared image, for example, even with small temperature differences and / or when the heat flow through the chisel 5 is time-invariant.

[0153] The thermal marking 14 can, for example, comprise or consist of a ceramic (e.g., tungsten carbide), aluminum brass, aluminum, bronze, stainless steel, enamel, or brass. Furthermore, grooves can be machined on the bit head so that the cut rock clogs the grooves, thereby continuously creating the corresponding thermal marking(s) during operation.

[0154] Exemplary implementations of the thermal marking 14 (e.g., each marking segment thereof) are formed using a coating and / or a material with a different thermal conductivity and / or emissivity than the bit head 11. Exemplary implementations of the thermal marking 14 (e.g., one or more marking segments thereof) are embedded in, cut out of, or applied to the bit head 11 as a coating. Exemplary implementations of the thermal marking 14 (e.g., one or more marking segments thereof) are arranged between the thickened portion 11k and the bit tip 10.

[0155] The geometry information can be based, for example, on the thermal marking 14, which makes the geometry determination 101 more reliable. More clearly, an incomplete and / or deformed thermal marking 14 can indicate where and / or how the chisel 5 (e.g., on its outer surface) is worn, whereas a profile image always only depicts the wear along the contour line.

[0156] If the chisel 5 has the thermal marking 14, the geometry representation 13 (e.g., per marking segment) can have or consist of a data-based representation (also referred to as a marking representation) of a geometry of the thermal marking 14 of the chisel 5. Examples of the geometry property derived from the marking representation (in this case also referred to as a marking property) in this case include: a circumference 13u of a marking representation; a (e.g., geometric) center of gravity 13m (preferably of the planar projection enclosed by a contour of the thermal marking or at least one marking segment) of the marking representation, e.g., its position; an area of ​​the surface of the marking representation; an angle enclosed by two edges of the marking representation; an extent of the marking representation; a number of marking segments.

[0157] As shown, the thermal marking 14 may comprise several strip-shaped (then also referred to as stripes) and / or ring-shaped marking segments that encircle the bit axis 203. With increasing wear, these stripes 14 disappear, resulting in a different infrared image 9.

[0158] The thermal marking 14 clearly provides a means which can be taken into account alternatively or in addition to the planar geometry of the chisel 5 in the infrared image in order to determine the wear condition (e.g. degree of wear) of the chisel.

[0159] In one exemplary implementation, the strips 14 are embedded in the chisel head 11. In another exemplary implementation, the chisel head 11 is coated with the strips 14, which have a different thermal conductivity and / or emissivity than the underlying chisel head 11. The removal of such a coating 15 (see also Fig. 16) can be gradually recognized in the infrared image as a difference from the good image pattern. In another exemplary implementation, the strips 14 are cut out of the surface of the chisel head and fill with cut material during operation.

[0160] The condition analysis 807 can, for example, be based on several stripes 14 or a coating 15 of the chisel 5 in order to determine the wear on the chisel head 11 in the infrared image 9. By means of the condition analysis 807, which has to determine one or more geometric properties of the stripes 14 or the coatings 15, the wear state can be determined, for example, the degree of wear can be quantitatively estimated.

[0161] Fig. 14 illustrates a chisel 5 in a schematic side view 1400a with a viewing angle transverse to the chisel axis 203 and a schematic top view 1400b with a viewing angle along the chisel axis 203 according to various embodiments 1400 analogous to the embodiments 1300, in which the thermal marking 14 has a plurality of rectilinear stripes and / or stripes extending away from the chisel tip. Fig. 15 illustrates a chisel 5 in a schematic side view 1500a with a viewing angle transverse to the chisel axis 203 and a schematic top view 1500b with a viewing angle along the chisel axis 203 according to various embodiments 1500 analogous to the embodiments 1300, 1400, in which the thermal marking 14 has a plurality of stripes extending along a helical line.

[0162] Fig.16 illustrates a chisel 5 in a schematic side view 1600a with a viewing angle transverse to the chisel axis 203 and a schematic top view 1600b with a viewing angle along the chisel axis 203 according to various embodiments 1600 analogous to the embodiments 1400, 1500, in which the thermal marking 14 comprises a coating 15 of the chisel head 11, which is arranged between the chisel tip 10 and the thickening 11k.

[0163] Fig. 17A illustrates chisels 5 of various wear states in a schematic perspective view 17 and resulting geometry representations in a schematic view 19 according to various embodiments, which are based on image data from a first perspective 1700a (for example, perspective A in Fig. 12). Fig. 17B illustrates the same chisels 5 in a schematic perspective view 18 and resulting geometry representations in a schematic view 20 according to various embodiments, which are based on image data from a second perspective 1700b (for example, perspective B in Fig. 12).

[0164] The chisel state 1701 represents an unused chisel 5 (for example, as the target state) whose degree of wear is, for example, 0. Chisel state 1703 represents a used chisel 5 whose degree of wear is, for example, greater than 0 and whose wear type (also referred to as wear type) is symmetrical wear. Chisel state 1705 represents a used chisel 5 whose degree of wear is, for example, greater than 0 and whose wear type is asymmetrical wear. For geometry representation, view 19 specifies the surface area as the first geometry property and its ratio to the target chisel state 1701 (in percent) as the second geometry property.

[0165] Asymmetrical wear may involve the breakage of parts of the chisel tip 10 or one-sided grinding due to a chisel blockage. As can be seen, symmetrical wear may be difficult to distinguish from asymmetrical wear if image data is available from only one perspective. Asymmetrical wear, e.g., due to a chisel blockage, may then be difficult to detect if the infrared camera 6 is positioned unfavorably.

[0166] According to various embodiments, the bit condition may be based on a result of the geometry comparison 811, which includes a comparison of geometry data from different perspectives. This may make it easier to distinguish symmetrical wear from asymmetrical wear.

[0167] For example, asymmetric wear can be determined as a chisel condition if a fluctuation of the geometric property (e.g., the area and / or the contour) between the first perspective and the second perspective exceeds a threshold value.

[0168] In an exemplary implementation, view 19 shows geometric representations of contours 13 of the chisel 5 of various wear states, which are determined based on one or more than one infrared image 9 per chisel 5. As can be seen from the chisels 5 shown above in perspective view 17, different wear states lead to similar indications of the surface area or the ratio to the target chisel state 1701. Nevertheless, an estimated remaining service life can be determined as the chisel state based on the geometric representation, for example its surface area or its ratio to the target chisel state 1701. The same chisel states are shown in views 18 and 20 from a different perspective.

[0169] Alternatively or additionally, the chisel height of the chisel head 11, the wedge angle of the chisel 5, and / or the position of the center of gravity of the determined chisel contour 13 can be determined in order to determine the degree of wear, the remaining service life and / or the type of wear.

[0170] In an exemplary implementation, the actual state of one or more than one (e.g., each) chisel 5 of the cutting head is updated after each rotation of the cutting head. For example, the actual chisel state can be expressed as a value (also referred to as a state value) that is continuously updated. The state value can, for example, indicate the difference between the actual chisel state (e.g., the actual surface area of ​​the geometry representation) and the desired state of the respective chisel 5.

[0171] If the variation in the geometry output between multiple perspectives exceeds a threshold, the condition determination may include determining the asymmetric wear type, and otherwise determining the symmetric wear type as a component of the bit condition. Alternatively or additionally, the condition determination may include converting the variation in the geometry output into a degree of asymmetry of wear as a component of the bit condition.

[0172] Fig. 18 illustrates a graphical user interface 21 of the removal machine 202 in a schematic plan view 1800, in which the method 100 comprises graphically outputting the (e.g., updated) actual chisel state of the or each chisel (as a result of the state determination 103), at least in the form of a graphic representation and / or as a state value. The updated actual chisel state is thus made more visible to the operator of the removal machine 202. The graphical user interface can be implemented by means of the data processing device 106 and / or a display device (e.g., having a display and / or a touchscreen). The graphical user interface can comprise both physical components and code-based components (e.g., software).

[0173] The graphic representation can, for example, indicate each chisel 5 in its position on the cutting head 2 as a symbol 22 (e.g., pictogram), supplemented by the condition value, the wear type, and / or a chisel numbering. The chisel numbering can, for example, include a code representing the position of the chisel, e.g., L1-1 for the first chisel 5 of the first spiral on the left cutting drum 2.

[0174] In an exemplary implementation, the graphical user interface is configured to display a symbol 22 (also referred to as a chisel symbol) for each chisel 5, in addition to the chisel numbering, including the condition value and the wear type 23. In the illustration, the designation "S" corresponds to the symmetrical wear type and "A" to the asymmetrical wear type. If the surface area of ​​surface 13a falls below a threshold value, e.g., below 70% of the target surface area of ​​surface 13a, the color of the chisel symbol is changed, for example, to red, to indicate a high degree of wear as a component of the actual chisel condition.

[0175] Alternatively or additionally, the graphical user interface may be configured to output the infrared images 9, e.g., in response to a user input, which provides the user with an alternative basis for controlling the ablation machine 202.

[0176] Fig. 19 illustrates a configuration of the camera system during image capture 803 according to various embodiments in a schematic perspective view 1900, for example, analogous to image capture 803 of flowcharts 1600, 1700, and / or 1800, similar to perspective view 1200 with the difference that the bit 5 is a roller bit of the disc bit type. What is described herein for the disc bit can apply analogously to a roller bit of the wart bit type. A roller bit 5 is rotatably mounted about its bit axis during operation, for example by means of a pivot bearing. The pivot bearing can be integrated, for example, into the roller bit 5 or the bit holder 8.

[0177] The camera system can have at least one infrared camera 6, e.g., two or more infrared image cameras 6. A plurality of infrared cameras 6 can be configured to capture the roller bit 5 (e.g., at the same time) from different perspectives (also referred to as stereo view) (e.g., perspective A and perspective B). In this regard, what is described herein (see Figs. 17A and 17B) applies analogously. Fig. 20A illustrates roller bit 5 in a schematic side view 2017 and a resulting geometry representation in a schematic view 19 according to various embodiments, which are based on image data from a first perspective 2000a (e.g., perspective A in Fig. 19). Fig.20B illustrates the same roller bits 5 in a schematic side view 2018 and resulting geometry representations in a schematic view 20 according to various embodiments, which are based on image data from a second perspective 2000b (e.g., perspective B in Fig. 19). In this regard, the description herein (see, for example, Figs. 17A and 17B) applies analogously.

[0178] Various implementations of the camera system 502 are explained below, which can be used individually or to implement one or more than one of the aspects described herein, for example, the ablation system 200 and / or the method 100. The camera system 502 has one or more than one camera protection device and, per camera protection device, at least one (ie, one or more than one) infrared imaging camera. The camera protection device is configured to protect the at least one infrared camera, e.g., at least its camera lens, from liquid (e.g., water) and / or solid particles (e.g., dust, splinters, and debris).

[0179] In a first exemplary implementation of camera system 502, the or each camera protection device comprises a compressed gas source for periodically cleaning the at least one infrared camera, e.g., its lens, using a gas stream (also referred to as blowing off) and / or continuously displacing the solid particles. In a second exemplary implementation of camera system 502, the or each camera protection device comprises a shutter in front of the lens, which is opened (e.g., only) for the duration of image capture (e.g., for the aperture time or longer).

[0180] In the second or a third exemplary implementation of the camera system 502, the or each camera protection device comprises a housing in which the at least one infrared camera is arranged, and which has an opening (also referred to as a housing opening) towards which the infrared camera is directed. The housing opening can be covered by the shutter, which moves relative to the housing. Alternatively or additionally, the housing can be arranged in a recess and moved out of the recess (e.g., unfolded) for the duration of the image capture (e.g., for the shutter time or longer) and then moved back in (e.g., folded in).

[0181] In the fourth exemplary implementation of the camera system 502, the or each camera protection device has a carrier (also referred to as a shield) that is transparent to infrared radiation (e.g., wall-shaped) and toward which the infrared camera is directed. The carrier can, for example, be arranged stationary relative to the infrared camera or can be mounted (and, for example, driven) so as to be movable relative to the infrared camera. Alternatively or additionally, the carrier can be in the form of a hollow cylinder in which the infrared camera is arranged and / or which is rotated. Alternatively or additionally, the carrier can be in the form of a plate and / or plate-shaped, which is, for example, rotated. The carrier can, for example, be formed from a ceramic, e.g., chalcogenide glass, or plastic. Alternatively or additionally to the moving carrier, the gas flow can be directed toward the carrier.

[0182] In the following, various examples are described which relate to what has been described above and shown in the figures.

[0183] Example 1 is a removal system, comprising: a removal machine (preferably configured as a crusher or cutting machine), which has a machine chisel (also referred to simply as a chisel) or at least one chisel holder for holding the machine chisel (which is, for example, movably mounted), and is configured to remove a material by means of the machine chisel; at least one (ie one or more than one) infrared camera for detecting (e.g.infrared-based or at least temperature-based) image data representing the machine tool and / or the tool holder; a data processing device configured to: determine an indication representing at least one geometric property of the machine tool based on the image data; determine a state of the machine tool based on the indication; preferably output instructions indicating the state of the machine tool and / or based thereon.

[0184] Example 2 is a camera system with at least one infrared camera or the ablation system according to claim 1, which further comprises: a camera protection device configured to protect the at least one infrared camera from solid particles. This improves the service life of the infrared camera.

[0185] Example 3 is configured as in Example 2, wherein the camera protection device comprises a compressed gas source configured to direct a gas stream toward the camera or to flow around it with the gas stream. This is relatively simple and cost-effective to implement.

[0186] Example 4 is configured as in example 2 or 3, wherein the camera protection device comprises a closure with a closure flap, wherein a camera lens of the at least one infrared camera is arranged between the closure flap and an infrared image sensor of the at least one infrared camera, and wherein the closure is configured to open the closure flap upon detection and subsequently (e.g., otherwise) to close it. This better protects the infrared camera against splinters.

[0187] Example 5 is configured like one of Examples 2 to 4, wherein the camera protection device comprises a housing in which the at least one infrared camera is arranged, and which is configured to fold out the at least one infrared camera during detection and to fold it in afterwards or otherwise. This better protects the infrared camera against fine dust. Example 6 is configured like one of Examples 2 to 5, wherein the camera protection device comprises a (e.g. at least for infrared radiation) transparent and / or wall-shaped carrier through which detection takes place, wherein preferably a camera lens of the at least one infrared camera is arranged between the carrier and an infrared image sensor of the at least one infrared camera. This better protects the infrared camera against fine dust and splinters and is mechanically more reliable.

[0188] Example 7 is configured as Example 6, further comprising: a drive device configured to set the carrier in motion, e.g., in a rotational motion and / or relative to the infrared camera. This extends the service life of the carrier (e.g., until cleaning).

[0189] Example 8 is configured as in example 6 or 7, wherein the carrier: is plate-shaped and / or dish-shaped; (e.g., formed as a glass cylinder) surrounds a cavity in which the at least one infrared camera is arranged; is formed as a film; and / or comprises or consists of plastic or glass. This is cost-effective.

[0190] Example 9 is a machine bit (e.g., the machine bit in any of Examples 1 to 8), comprising: a cutting component (e.g., a bit head) having a cutting edge, preferably configured as a bit tip (e.g., provided by an embedded bit pin); a mounting component (illustratively for mounting the machine bit), preferably configured as a shank (also referred to as a bit shank) or shaft, extending, for example, away from the cutting edge (e.g., along or across an axis, e.g.,longitudinal axis or rotational axis of the machine tool); and a marking which is embedded in the cutting component, cut into it or with which the cutting component is coated, wherein the cutting component and the marking differ from one another in at least one thermal property, preferably in a thermal emissivity and / or a thermal conductivity; wherein preferably the mounting component and the cutting component are rigidly connected to one another and / or wherein the marking is strip-shaped and / or annular or has at least a plurality of strip-shaped and / or annular marking segments; wherein preferably the mounting component is shaft-shaped, has a shaft or has at least one through-opening for receiving a shaft. This improves condition detection.

[0191] Example 10 is a method (e.g., for operating a removal system, camera system, or machine bit from any of Examples 1 to 9), comprising: determining an indication representing a geometric property of a machine bit based on image data representing a machine bit and preferably a bit holder holding it; determining a state of the machine bit based on the indication; preferably controlling a removal process performed by means of the machine bit based on a result of determining the state of the machine bit.

[0192] Example 11 is a computer program configured to perform the method according to claim 10. This facilitates the automation of the method.

[0193] Example 12 is a computer-readable medium storing (e.g., by means of code segments) instructions configured, when executed by a processor, to cause the processor to perform the method of claim 10. This facilitates automation of the method.

[0194] Example 13 is a data processing device (e.g., for a camera system or a removal machine according to any one of claims 1 to 12) comprising one or more processors configured to perform the method according to claim 11. This facilitates the automation of the method.

[0195] Example 14 is a removal system comprising: a removal machine having a machine bit or at least one bit holder for holding the machine bit, and configured to remove a material by means of the machine bit; at least one infrared camera for capturing image data representing the machine bit and / or the bit holder; and the data processing device according to claim 13.

[0196] Example 15 is configured as any of Examples 1 to 14, wherein the at least one infrared camera is attached to the ablation machine. This facilitates implementation.

[0197] Example 16 is configured as any one of Examples 1 to 15, further comprising: a frame supporting the at least one infrared camera, wherein the frame: has a handle for being carried by a user during operation; and / or has one or more stands for being arranged standing on a surface during operation. This increases flexibility.

[0198] Example 17 is configured as one of Examples 1 to 16, wherein the removal machine has a (e.g., rotatably mounted) cutting head to which the machine chisel is attached (e.g., in a form-fitting manner). This increases the removal rate.

[0199] Example 18 is configured as one of Examples 1 to 17, wherein the at least one infrared camera is configured to capture one or more (e.g., infrared-based) individual images of the cutting head as image data per revolution of the cutting head. This improves the data basis. Example 19 is configured as one of Examples 1 to 18, wherein the cutting head is configured as a transverse cutting head or as a longitudinal cutting head, wherein the transverse cutting head is preferably drum-shaped (e.g., configured as a drum milling machine). This increases the removal rate.

[0200] Example 20 is configured as one of Examples 1 to 19, wherein the removal machine has a pivot bearing by means of which the machine tool, e.g., its cutting head, is movably mounted (e.g., rotating). This increases the removal rate.

[0201] Example 21 is configured as any one of Examples 1 to 20, wherein the material removal machine comprises a drive train (e.g., comprising the cutting head) configured to set the machine tool in a rotating motion. This increases the material removal rate.

[0202] Example 22 is configured as one of Examples 1 to 21, wherein an image capture frequency during operation of the at least one infrared camera is greater than a rotational speed of the rotating movement. This improves the data basis.

[0203] Example 23 is configured as any of Examples 1 to 22, wherein the at least one infrared camera comprises one or more camera lenses (e.g., forming a lens) and an infrared image sensor. This improves the data basis. The camera lens can, for example, comprise or consist of infrared-transmissive glass, e.g., one or more lenses thereof.

[0204] Example 24 is configured as any one of Examples 1 to 23, wherein the data processing device and / or the instructions are configured to control the removal machine based on a result of determining the condition of the machine bit. This facilitates automation.

[0205] Example 25 is configured as any one of Examples 1 to 24, wherein determining the indication comprises: determining a data-based representation (e.g., contour) of a geometry of the machine tool, preferably from the viewing angle of the at least one infrared camera, based on the image data; wherein the indication comprises or is at least based on one or more properties of the data-based representation of the geometry. This facilitates the state determination.

[0206] Example 26 is configured as in Example 25, wherein the data-based representation of the geometry of the machine bit comprises one or more of: a data-based contour of the geometry of the machine bit; a data-based surface enclosed by the contour of the geometry of the machine bit; and / or a planar projection (from the viewpoint of the camera) of the machine bit. This further facilitates state determination.

[0207] Example 27 is configured as in example 25 or 26, wherein the indication comprises or is at least based on one or more of the following (e.g., geometric) properties of the data-based representation: a perimeter; a (e.g., geometric) center of gravity (preferably of the planar projection enclosed by a contour of the machine tool); an area; a shape; an angle enclosed by two edges of the data-based representation. This further facilitates state determination.

[0208] Example 28 is configured as in examples 25 to 27, wherein determining the data-based representation comprises: determining a plurality of image components (e.g., pixels or voxels) of the image data that satisfy a criterion; wherein the data-based representation is based on the plurality of image components; wherein the criterion preferably comprises a criterion of a filter (e.g., edge detection) and / or a homogeneity criterion and / or a gradient criterion. This further facilitates state determination.

[0209] Example 29 is configured as in Example 28, wherein determining the data-based representation comprises: converting the plurality of image components into a self-contained path (e.g., a polyhedron), wherein the data-based representation comprises, consists of, or is at least based on the path; wherein the conversion is preferably performed by smoothing. This further facilitates state determination.

[0210] Example 30 is configured as any of Examples 1 to 29, wherein the at least one geometric property represents (e.g., comprises) one or more of the following properties: a shape of the machine bit and / or a symmetry of the shape; an extent (e.g., length) of the machine bit; and / or a wedge angle of the machine bit. This further facilitates state determination.

[0211] Example 31 is configured as any one of Examples 1 to 30, wherein the specification comprises multiple components, each component associated with a geometric property, wherein determining the state comprises weighting the multiple components. This facilitates adapting the state determination to variable circumstances.

[0212] Example 32 is configured as any one of Examples 1 to 31, wherein the condition of the machine tool bit represents wear of the machine tool bit, preferably one or more than one property (e.g., symmetry and / or progression) of the wear of the machine tool bit. This facilitates preventive action and thus reduces operating costs.

[0213] Example 33 is configured as any one of Examples 1 to 32, wherein the image data comprises a plurality of individual images, each individual image representing the machine tool, wherein determining the indication is based on the plurality of individual images. This improves the data basis. Example 34 is configured as Example 33, wherein the indication comprises a plurality of components, a first component being based on a first individual image of the plurality of individual images, and a second component being based on a second individual image of the plurality of individual images, wherein determining the state is preferably based on a comparison of the first component and the second component with each other. This reduces data processing resources.

[0214] Example 35 is configured like examples 33 or 34, with the image data being combined into a panoramic image, which is used to determine the information. This reduces the data processing resources.

[0215] Example 36 is configured as any one of Examples 1 to 35, wherein determining the state comprises selecting one of several predefined (e.g., stored) states. This reduces data processing resources.

[0216] Example 37 is configured as in Example 36, wherein the plurality of predefined states comprises one or more of the following states: machine bit missing; machine bit requires maintenance (e.g., when the remaining service life of the machine bit is greater than zero); machine bit requires replacement (e.g., the remaining service life of the machine bit is zero); and / or the remaining service life of the machine bit is greater than zero. This reduces the data processing resources.

[0217] Example 38 is configured as any one of examples 1 to 37, further comprising: issuing instructions that indicate or are based on the condition of the machine tool bit. This facilitates preventive action and thus reduces operating costs.

[0218] Example 39 is configured as in Example 38, wherein the instructions comprise at least instructions for operating the chisel and / or are configured to control a removal process performed by the machine chisel. This facilitates preventive action and thus further reduces operating costs.

[0219] Example 40 is configured as any one of Examples 1 to 39, wherein the machine bit has a marking (e.g., providing a pattern), which is preferably embedded in the bit head, cut into it, or with which the bit head is coated (e.g., the bit head and the marking differ from each other in at least one thermal property, preferably in a thermal emissivity and / or a thermal conductivity), which preferably forms a scale, wherein the determination of the indication is based on the marking (e.g., the indication comprises an indication of a geometric property of the marking). This facilitates the condition determination. Example 41 is configured as in Example 40, wherein the machine bit has a coating and / or materials of different thermal conductivity or grooves by means of which the marking is formed. This further facilitates the condition determination.

[0220] Example 42 is configured as one of Examples 1 to 41, further comprising: controlling the at least one infrared camera based on data from a sensor (e.g., a rotation angle sensor) configured to detect a movement of the machine tool. This facilitates preventive action and thus further reduces operating costs.

[0221] Example 43 is configured as any of Examples 1 to 42, wherein the at least one infrared camera comprises multiple infrared cameras. This improves the data basis.

[0222] Example 44 is configured as any of Examples 1 to 43, wherein the image data comprises a stereoscopic image pair (e.g., representing the machine tool) and / or stereoscopic image data formed therefrom, wherein the condition (e.g., a condition value thereof) of the tool is preferably based on a difference between individual images of the image pair. This improves the data basis.

[0223] Example 45 is configured as any of Examples 1 to 44, wherein the image data comprises or consists of stereoscopic image data. This improves the data basis.

[0224] Example 46 is configured as any one of Examples 1 to 45, wherein the image data representing a machine tool includes thermographic information of the machine tool. This improves the data basis in the presence of dust and water mist.

[0225] Example 47 is configured as any one of Examples 1 to 46, wherein the condition of the machine tool is a wear condition of the machine tool, e.g., representing a degree of wear and / or wear symmetry of the machine tool. This facilitates preventive action and thus further reduces operating costs.

[0226] Example 48 is configured like one of Examples 1 to 47, but the image data is infrared-based. This improves the data basis for dust and water mist.

[0227] Example 49 is configured as any of Examples 1 to 48, wherein the infrared camera is configured to capture the image data based on infrared radiation (e.g., at least emanating from the machine tool). This improves the data basis in the presence of dust and water mist.

[0228] Example 50 is configured as any of Examples 1 to 49, wherein the image data includes a (e.g., data-based and / or pixel-based) representation of a spatial temperature distribution (e.g., at least emanating from the machine tool). This improves the data basis for dust and water mist.

[0229] Example 51 is configured as any one of Examples 1 to 50, wherein the condition of the machine tool is determined as the actual condition of the machine tool.

[0230] Example 52 is configured as any one of examples 1 to 51, wherein the machine tool is movably mounted along a movement path, wherein the infrared camera is directed toward the movement path.

[0231] Example 53 is configured as any one of Examples 1 to 52, wherein the at least one infrared camera comprises a plurality of infrared cameras whose fields of view (e.g., at the movement path of the tool holder and / or the machine tool) overlap one another or are spaced apart from one another.

[0232] Example 54 is configured as any one of examples 1 to 53, wherein the at least one infrared camera is directed toward a movement path of the bit holder and / or the machine bit.

[0233] Example 55 is configured as any of Examples 1 to 54, wherein the geometric property is invariant with respect to, or at least independent of, a (e.g., average) emissivity of the machine tool. This allows the temperature not to be determined in order to determine the geometric property.

[0234] Example 56 is configured as any of Examples 1 to 55, wherein the geometric property is invariant with respect to, or at least independent of, a calibration of the infrared camera. This allows the temperature to be omitted in order to determine the geometric property.

[0235] Example 57 is configured as any one of examples 1 to 56, wherein the image data is based on infrared radiation (also referred to as infrared radiation-based), which, for example, emanates at least from the machine tool (optionally from the tool holder and / or the surroundings of the machine tool) and / or is captured by means of the at least one infrared camera.

[0236] Example 58 is configured as any one of Examples 1 to 57, wherein the thermal property is a property that affects the emission of infrared radiation.

[0237] Example 59 is configured as any one of Examples 1 to 58, wherein the emissivity is an emissivity for infrared radiation (also referred to as thermal emissivity).

[0238] Example 60 is configured as any one of Examples 1 to 59, wherein the image data comprises or consists of at least infrared image data (also referred to as thermographic image data). Example 61 is configured as any one of Examples 1 to 60, wherein the image data is acquired using a thermographic process.

[0239] In the following, various exemplary implementations are explained which concern the aspects described herein, for example the data processing chain from the image data to the classification.

[0240] An exemplary implementation of determining the geometry information, which represents at least one geometric property of the chisel, is carried out by means of one or more than one first algorithm, examples of which include: an image processing algorithm, a contrast enhancement algorithm, a feature detection algorithm, a segmentation algorithm, e.g., a thresholding algorithm. One or more than one of these exemplary algorithms can be provided, for example, by means of a library, examples of which include: OpenCV, Scikit-Image, SciPy, NumPy, and other libraries. For example, the temperature-based image data can be converted into a black and white image using a thresholding transformation as an exemplary image processing algorithm. Optionally, the temperature-based image data can be transformed using a Gaussian blur filter in order to (e.g.,To remove small-scale image noise, and / or to sharpen it using an erosion algorithm, e.g., to sharpen a blurry image. Optionally, the black-and-white image can be converted into a contour image, for example, using the Sobel edge detection algorithm.

[0241] An exemplary implementation of determining the geometry representation is carried out by means of an image processing algorithm, examples of which include: edge detection, a Fourier high-pass filter, a threshold filter, a Fourier low-pass filter, a color value difference analysis, object detection, geometry detection, a trained algorithm.

[0242] Examples of edge detection algorithms include Sobel edge detection and Canny edge detection. An exemplary library that provides color value difference analysis is the colormath library. Examples of object detection algorithms include YOLO ("You Only Look Once," a class of end-to-end deep learning models for fast object detection), RCNN (a region-based convolutional neural network), and Faster-RCNN, provided, for example, by libraries such as OpenCV or TensorFlow. Examples of geometry detection algorithms include the Hough transform (in OpenCV).

[0243] An exemplary implementation of object detection using the YOLO algorithm comprises, in a first step, identifying a section of a temperature-based image that shows a chisel head with a certain, high degree of certainty. A second step identifies edges or prominent points in this area. An exemplary implementation of determining the geometry information that represents at least one geometric property of the chisel can be implemented as follows:

[0244] - Converting the image data into a blurred image using a transformation (also called transforming);

[0245] - Converting the blurred image into a black and white image using a filter (also called filtering);

[0246] - Converting the black and white image into a contour image using an edge detection algorithm (also called edge detection);

[0247] - Determining one or more boundary points of smooth contour lines and, based thereon, determining a contour model (e.g. a vector image as an exemplary contour model, which is also called a vector model);

[0248] - Determining the area of ​​closed contours in the contour image (e.g. based on the vector model), e.g. using a dedicated algorithm;

[0249] - Determination of characteristic geometric parameters as geometry information (examples include: the chisel head height, the opening angle of the chisel head tip, etc.) of closed contours in the contour image (e.g. from the vector model), e.g. based on the coordinates of the outermost points of the contours;

[0250] - optional determination of further contour features as geometric information (e.g. contour moment, center of gravity and circumference of one or more of the contours), e.g. by means of an algorithm set up for this purpose, e.g. by means of known mathematical operations.

[0251] An exemplary implementation of determining the bit condition based on the geometry information is carried out using one or more second algorithms, examples of which include: a reference comparison algorithm, a statistical algorithm, for example, provided by a library, examples of which include: numPy, Pandas. For example, the geometry information can be converted into a bit wear condition using a shape comparison algorithm (e.g., matchShapes from the OpenCV library) as a comparison algorithm. Optionally, the geometry information can be transformed using a projection correction to compensate for the influence of the viewing angle, which can be used alternatively or additionally to select a suitable reference model.

[0252] An exemplary implementation of the shape comparison algorithm comprises comparing the surface area of ​​the detected chisel head with the surface area of ​​a detected chisel head of the same chisel in new condition (as reference).

[0253] An exemplary implementation of determining the bit condition based on the geometry information can be implemented as follows: - Comparing the geometry information with a reference, for example using matchShape as an exemplary shape comparison algorithm;

[0254] - Determining one or more than one difference between the geometric specification (e.g. a bit head height or other geometric property of the bit) and the reference based on comparing the geometric specification with the reference (e.g. one or more than one geometric specification thereof);

[0255] - comparing the one or more differences with a criterion which may, for example, be a threshold value for a deviation of the bit head height (or other geometric property of the bit);

[0256] - Classifying the geometry specification based on comparing the one or more differences with the criterion;

[0257] Examples of the reference include: a geometric specification of a reference bit determined in a similar manner as explained above; a model of a reference bit; a statistical model of a reference bit.

[0258] An exemplary implementation of outputting instructions that indicate and / or are based on the condition of the machine bit is carried out by generating a message according to a communication protocol. The message can, for example, contain an indication of the condition of the machine bit, for example a result of the classification. The message can, for example, contain a warning and / or instruction to change the machine bit. The message can, for example, comprise a symbol that is output on the display device (e.g., a display) that visually shows the bit wear condition using colors. The message can, for example, be addressed to a graphics driver that controls the display device, and / or to the machine operator, and / or to the machine control system (e.g., containing instructions, e.g., "STOP propulsion").Examples of the communication protocol include: TCP / IP, UDP, eBus, USB, ProfiBus, CANopen (communication protocol based on a Controller Area Network (CAN) bus).

[0259] As explained above, it can be understood that the embodiments explained herein are applicable to removal machines of various types, such as cutting machines (e.g. rock cutting machines), in particular those in which rotating cutting drums with round shank bits are mounted. Examples of such removal machines include so-called roadheaders, continuous miners, shearer loaders, horizontal milling machines, surface miners, tunneling machines and milling attachments, which are generally used to remove material connected to the Earth's mantle (e.g. a natural or otherwise massive and extensive rock body) therefrom (e.g. to detach it from layers of the Earth's mantle, e.g. rock layers), in order to work their way into the Earth's mantle (also referred to as tunneling). Other examples of such removal machines also include so-called crushers (e.g.Drum or roller crusher, cone crusher, or in the form of another crushing machine) which are used to crush lumpy (or other loose) material (e.g. chunks or other material detached from the Earth's mantle). In other words, the term "excavation" can generally be understood as a division (e.g. crushing) of solid material (e.g. chunks or layers of the Earth's mantle, e.g. rock layers), e.g. a crushing (e.g. into a plurality of smaller bodies) of the material so that bulk material is formed or at least the grain size is reduced. Such a crusher (e.g. rock crusher) can, by analogy, be a drum with one or more than onein a respective holder) mounted chisel, for example one or more than one round shank chisel mounted in a respective chisel holder, which is used for example in connection with the exemplary infrared camera and the data processing system.

Claims

Patent claims 1. Removal system (200) comprising: a removal machine (202), preferably configured as a crusher or cutting machine, which has a machine chisel (5) or at least a chisel holder (8) for holding the machine chisel (5), and is configured for removing material by means of the machine chisel (5); at least one infrared camera (6) for capturing image data representing the machine chisel (5) and preferably the chisel holder (8); a data processing device (106) which is configured for: • Determine (101) a specification that represents at least one geometric property of the machine chisel (5) based on the image data; • Determining (103) a state of the machine chisel (5) based on the specification; • preferably issuing instructions which indicate the state of the machine chisel (5) specify and / or base on it.

2. Removal system (200) according to claim 1, wherein the at least one infrared camera (6) is directed towards a movement path of the chisel holder (8) and / or the machine chisel (5).

3. Removal system (200) according to claim 1 or 2, wherein the removal machine (202) has a cutting head to which the machine chisel is attached.

4. Ablation system (200) according to claim 3, wherein the at least one infrared camera (6) is configured to capture several individual images of the cutting head as image data per revolution of the cutting head.

5. Removal system (200) according to one of claims 1 to 4, wherein the condition of the machine chisel represents wear of the machine chisel, preferably a symmetry and / or a progression of wear.

6. Ablation system (200) according to any one of claims 1 to 5, wherein the image data are stereoscopic image data.

7. Removal system (200) according to one of claims 1 to 6, further comprising: • a camera protection device which is set up to include at least one infrared camera (6) to protect against solid particles.

8. Removal system (200) according to any one of claims 1 to 7, wherein the determination of the specification comprises: • Determining a data-based representation of a geometry of the machine chisel (5), preferably from the viewpoint of the at least one infrared camera (6), based on the image data; • wherein the specification includes or is at least based on one or more properties of the data-based representation. Abrasion system (200) according to any one of claims 1 to 8, wherein the specification includes or is at least based on one or more of the following geometric properties of the data-based representation: • a scope; • a focus; • an area; • a form; and / or • an angle enclosed by two edges of the data-based representation. Ablation system (200) according to any one of claims 1 to 9, • wherein the machine chisel (5) has a marking (14) which is embedded, cut into or coated in a chisel head (11) of the machine chisel (5), • wherein the chisel head (11) and the marking (14) differ from each other in at least one thermal property; • where the determination of the information is based on the marking, • wherein the at least one thermal property preferably comprises an emissivity and / or a thermal conductivity. Method (100), comprising: • Determining (101) a specification representing a geometric property of a machine chisel (5) based on temperature-based image data representing the machine chisel (5); • Determining (103) a state of the machine chisel (5) based on the specification; • preferably outputting instructions that specify or are based on the state of the machine tool (5). Computer program configured to perform the method according to claim 11. Computer-readable medium storing instructions configured, when executed by a processor, to cause the processor to perform the method according to claim 11. Data processing device (106) comprising one or more processors configured to perform the method according to claim 11. Machine chisel (5) comprising: • a cutting component (11) which has a cutting edge (10); • a mounting component for mounting the machine chisel, which is rigidly connected to the cutting component (11); and • a marking (14) which is embedded, cut into or coated in the cutting component (11), • wherein the cutting component (11) and the marking (14) differ from each other in at least one thermal property, • wherein the marking (14) preferably has several strip-shaped and / or ring-shaped marking segments.

Images