BR-112022024095-B1 - PROCESS AND MECHANISM FOR THE MECHANICAL DETERMINATION OF THE FUNCTIONAL CONDITION OF SUPPORT ROLLERS OF A CONVEYOR BELT SYSTEM

BR112022024095B1BR 112022024095 B1BR112022024095 B1BR 112022024095B1BR-112022024095-B1

Abstract

PROCESS AND MECHANISM FOR THE MECHANICAL DETERMINATION OF THE FUNCTIONAL CONDITION OF SUPPORT ROLLERS OF A CONVEYOR BELT SYSTEM. The present invention relates to a process for the mechanical determination of the functional condition of support rollers (13) of a conveyor belt system (1) during the operation of the conveyor belt system, wherein at least one unmanned vehicle (2) is provided with at least one image sensor system, by means of which the conveyor belt system can be captured, at least in sections, in a sensory manner in the form of image data, wherein image data of at least one sub-area of the conveyor belt system are captured as thermal image data. In the image data captured from the conveyor belt system, at least one position of the detection image area is automatically determined, in which at least one sub-area of a support roller (13) is reproduced. For each position in the detection image area determined from the image data, an analysis image area position is automatically defined in the thermal image data. In each defined position of the analysis image area, (...) is automatically analyzed.

Inventors

Philipp Eßer
Sophie Ruoshan Wei
Martin Krex
David Handl

Assignees

FLSMIDTH A/S

Dates

Publication Date: 20260310
Application Date: 20210521
Priority Date: 20200525

Claims (15)

1. A process for the mechanical determination of the functional condition of support rollers (13) of a conveyor belt system (1) during the operation of the conveyor belt system (1), wherein at least one unmanned vehicle (2) is provided with at least one image sensor system, by means of which the conveyor belt system (1) can be captured, at least in sections, in a sensory manner in the form of image data, wherein image data of at least one sub-area of the conveyor belt system (1) are captured as thermal image data, in the image data captured from the conveyor belt system (1) at least one position of the detection image area is automatically determined, in which at least one sub-area of a support roller (13) is reproduced, for each position of the detection image area determined from the image data a position of the analysis image area is automatically defined in the thermal image data, and in each position of the analysis image area defined thermal image data are automatically analyzed to automatically determine the functional condition of support rollers (13), characterized in that that image data that can be detected by the image sensor system in addition to thermal image data also includes photographic image data, image data of at least one sub-area of the conveyor belt system (1) are also captured as photographic image data, image data captured from the conveyor belt system (1), in which at least one identification image region position is automatically determined, are photographic image data in which photographic image data regions are automatically detected as image data regions, and the position of each detected photographic image data region is automatically provided as the identification image region position.
2. A process according to claim 1, characterized in that image data from at least one sub-area of the conveyor belt system (1) are captured as thermal image data, wherein at least one unmanned vehicle (2) is moved with at least one image sensor system comprising a thermal image sensor device (21) to detect thermal image data and a photographic image sensor device (22) to detect photographic image data, along at least one sub-area of the conveyor belt system (1), with the image sensor system capturing image data from at least one sub-area of the conveyor belt system (1) and the image data comprising at least thermal image data and photographic image data, in the photographic image data captured from the conveyor belt system (1), at least one position of the detection image area is automatically determined, wherein, in the captured photographic image data, photographic image data areas from at least one sub-area of the conveyor belt system (1) are automatically detected, in which at least one sub-area is reproduced. from a support roll (13), and the position of the respective detected data area of the photographic image data is automatically made available as the position of the detection image area of the respective support roll (13), for each position of the detection image area determined by the photographic image data, a position of the analysis image area is automatically defined in the thermal image data, wherein, for each position of the detection image area of a support roll (13) determined from the photographic image data, a position of the analysis image area of the support roll (13) is automatically defined in the thermal image data, which spatially corresponds to the respective position of the detection image area of the photographic image data, in each position of the analysis image area defined the thermal image data are automatically analyzed, wherein, in the position of the analysis image area of the support roll (13), temperature data of the respective support roll (13) are automatically determined from the thermal image data and the temperature data determined from the position of the analysis image area are automatically assigned to a functional condition of the respective roll. support (13).
3. Process, according to claim 1 or 2, characterized in that, in the photographic image data captured from the conveyor belt system (1), at least one position of the detection image area is automatically determined, wherein, in the photographic image data, areas of photographic image data are automatically detected, in which at least one object that can be detected is reproduced, in the photographic image data areas thus detected, under the objects that can be detected, support rollers (13) or subareas of support rollers (13) are automatically detected and for each detected support roller (13), as well as for each detected subarea of a support roller (13), the position of the photographic image data area, in which the support roller (13) or the subarea of the support roller (13) is reproduced, is made available as the position of the detection image area.
4. Process, according to any one of claims 1 to 3, characterized in that the detection quality in the automatic determination of the position of the detection image area in the captured photographic image data, particularly, the detection quality of the automatic detection of photographic image data areas in which at least one detected object can be reproduced, particularly, at least one subarea of a support roll (13), and/or the detection quality of the automatic detection of support rolls (13) or subareas of support rolls (13) in the detected photographic image data areas, can be improved based on a learning process performed by means of an artificial neural network, particularly by means of a one-level or multi-level Convolutional Neural Network.
5. Process, according to any one of claims 1 to 4, characterized in that, at each defined position of the analysis image area, thermal image data are automatically analyzed, wherein, at the defined position of the analysis image area, thermal image data that are thermal image data from the support rolls (13) are automatically selected and, at the defined position of the analysis image area, the selected thermal data are automatically analyzed.
6. Process, according to claim 5, characterized in that thermal image data are automatically selected which, in such sub-areas, are located within the defined positions of the analysis image area, in which thermal image data are arranged in circular or similar-to-circular contours and/or in which thermal image data correspond to the temperatures of the same temperature level.
7. Process, according to claim 5 or 6, characterized in that the quality of detection in the automatic selection of thermal image data, which are thermal image data from the support rolls (13), is improved based on a learning process performed by means of an artificial neural network, particularly, the quality of detection in the automatic selection of thermal image data, which, in such subareas, are within the defined positions of the analysis image area, in which thermal image data are arranged in circular or similar-to-circular contours and/or in which thermal image data correspond to the temperatures of the same temperature level.
8. Process, according to any one of claims 1 to 7, characterized in that the image data of the conveyor belt system (1) are assigned, respectively, to a position in the conveyor belt system (1) and/or, for the defined position of the analysis image area, the thermal image data or evaluation information are assigned, respectively, to an individual support roller (13) of the conveyor belt system (1), wherein the assignment is performed, in particular, by a radio-based position determination, by a comparison of captured image data with comparison image data, by a remote capture of the unmanned vehicle (2) and/or by a capture by alignment of the image sensor system.
9. Process, according to claim 2 or any of claims 3 to 8 when dependent on claim 2, characterized in that the temperature data determined from the position of the area of the analysis image are automatically assigned to a functional condition of a support roll (13), wherein, the temperature data determined from the respective support roll (13) are either automatically classified into, respectively, a functional condition from a plurality of previously defined functional conditions or are automatically assigned, respectively, to a functional condition in the context of a cluster analysis, particularly in the context of a multivariate cluster analysis.
10. Process, according to any one of claims 1 to 9, characterized in that the detection quality in the mechanical determination of the functional condition of support rollers (13), particularly the classification of thermal image data, is improved based on a learning process performed by means of an artificial neural network.
11. Process, according to any one of claims 1 to 10, characterized in that, for the respective support roll (13), the functional condition, image data and/or possibly the temperature data determined are included in a functional condition data collection.
12. Process for identifying functionally impaired support rollers (13) of a conveyor belt system (1) during the operation of the conveyor belt system (1), the process being characterized in that it comprises the process for the mechanical determination of the functional condition of support rollers (13) of a conveyor belt system (1), as defined in any one of claims 1 to 11, wherein functionally impaired support rollers (13) are detected, based on a comparison with historical data from a functional condition database, a time for a replacement of the respective support roller (13) is determined and, for that support roller (13), the determined time is sent to a communication interface.
13. Mechanism for the mechanical determination of the functional condition of support rollers (13) of a conveyor belt system (1) during the operation of the conveyor belt system (1), mechanism comprising at least one unmanned vehicle (2) mobile along at least one sub-area of the conveyor belt system (1), with at least one image sensor system, by means of which the conveyor belt system (1) can be captured, at least in sections, in a sensory manner, in the form of image data and comprising at least one thermal image sensor device (21) for capturing data in the form of thermal image data, a data processing device (3) for evaluating the captured image data, to determine the functional condition of support rollers (13) of a conveyor belt system (1) during the operation of the conveyor belt system (1), wherein the data processing device (3) is an image area detection module (31), which is configured to automatically determine, in the captured image data, at least one position of the image area of detection, in which at least one subarea of a support roller (13) is reproduced, an image area definition module (34), which is configured to automatically define, for a position in the detection image area determined from the image data, respectively, a position in the analysis image area in the thermal image data, and which has a condition determination module (35), which is configured to, at a defined position in the analysis image area, automatically analyze thermal image data, to automatically determine the functional condition of support rollers (13), characterized in that the image sensor system is configured so that the captureable image data in addition to the thermal image data also comprises image data, wherein the at least one image sensor system in addition to the thermal image data also comprises at least one photographic image sensor mechanism (22) to capture image data from at least one subarea of the conveyor belt system (1) in the form of photographic image data, wherein the image region identification module (31) is configured to use photographic image data, wherein photographic image data regions are automatically detected as image data regions, such as conveyor belt system image data (1) wherein at least one identification image region position is automatically determined, and the position of each detected photographic image data region is automatically provided as the identification image region position.
14. Mechanism according to claim 13, characterized in that the image area detection module (31) has an image area detection module (32) and an interface module (33), wherein the image area detection module (32) is configured to automatically detect, in the captured photographic image data, areas of photographic image data in which at least one subarea of a support roll (13) is reproduced, and wherein the interface module (33) is configured to automatically provide a position of the detected photographic image data area as the position of the detection image area of the respective support roll (13), and wherein the image area definition module (34) is configured to automatically define, for each position of the detection image area of a support roll (13) determined from the photographic image data, respectively, a position of the analysis image area of the support roll (13) in the thermal image data, which spatially corresponds to the respective position of the detection image area of the data. photographic image, and wherein, the condition determination module (35) has an analysis module (36) and an assignment module (37), wherein the analysis module (36) is configured to automatically determine, at the position of the analysis image area of the support roll (13) defined from the thermal image data, temperature data of the respective support roll (13), and wherein the assignment module (37) is configured to automatically assign the temperature data determined from the position of the analysis image area to a functional condition of the respective support rolls (13).
15. Mechanism, according to claim 14, characterized in that the data processing device (3) has at least one adaptive artificial neural network, through which at least one of the following detections occurs: detection of support rolls (13) or subareas of support rolls (13) for the automatic determination of photographic image data areas in the captured photographic image data, in which at least one subarea of a support roll (13) is reproduced, detection of thermal image data of a support roll (13) for the automatic determination of temperature data of the support roll (13) at a defined position of the analysis image area of the support roll (13), detection of functional conditions of a support roll (13) from temperature data of the support roll (13) determined for the automatic assignment of the functional condition of the support rolls (13).

Description

[0001] The invention relates to a process for the mechanical determination of the functional condition of support rollers of a conveyor belt system during the operation of the conveyor belt system, wherein therein is provided at least one unmanned vehicle with at least one image sensor system, by means of which the conveyor belt system can be captured, at least in sections, in a sensory manner in the form of image data, wherein image data of at least one sub-area of the conveyor belt system are captured as thermal image data. Furthermore, the invention relates to a process for identifying functionally impaired support rollers of a conveyor belt system based on the above process, as well as a mechanism for the mechanical determination of the functional condition of the support rollers of a conveyor belt system during the operation of the conveyor belt system, the mechanism comprising at least one unmanned vehicle mobile in at least one sub-area of the conveyor belt system with at least one image sensor system, by means of which the conveyor belt system can be captured, at least in sections, in a sensory manner, in the form of image data, and comprising at least one thermal image sensor device for capturing thermal image data. [0002] For the transport of bulk products such as, for example, debris, ores, fuels, construction materials and the like by a specific conveyor line (transport line), conveyor belt systems (conveyor belts, conveyor belt systems, belt conveyor systems, belt conveyor systems) are frequently used as stationary or semi-stationary conveyors. In a conveyor belt system, a continuous belt (support belt, conveyor belt) is moved by at least one drive station (drive drum) in a rotary motion. In this case, the belt is driven as a free upper compartment between two diverting stations, where the belt is diverted by a diverting cylinder, from one diverting station (starting side) to another diverting station (ending side). Starting from the diverting station on the ending side, the diverted belt is returned as a free lower compartment to the diverting station on the starting side, where it is again diverted and driven again as a free upper compartment. Typically, in this case, the upper free compartment forms the load compartment (working compartment, tension compartment) and the lower free compartment, the empty compartment. Along the entire length of the conveyor belt, the belt is supported in the upper free compartment and lower free compartment by support rollers (casters), which function as both support and transport elements. [0003] For bulk products, due to the greater collection capacity and better material management, in addition to flat belts (in a flat belt system), belts with a recessed free upper compartment are used (such as a recessed belt in a recessed conveyor system, for example, with a V-shaped recess every two support rollers or with a U-shaped recess, for example, every three, four, five or more support rollers) or a coiled free upper compartment (such as a hose belt/tubular belt, respectively in a hose conveyor system). Depending on the transport task, a belt driven in a recessed or coiled free upper compartment is returned in the flat, recessed, or even isolated or coiled free lower compartment. Frequently, a U-shaped recess can be found in heavily loaded free upper compartments and, in the reverse free lower compartment, a flat shape or a V-shaped recess. [0004] A continuously running conveyor belt needs to be supported and guided on the conveyor belt in the loaded upper free compartment, as well as in the return free lower compartment (in this location, in an unloaded or loaded state), with support being particularly important for the loaded part of the conveyor belt. Support rollers are used as both support and guidance elements in a shoring structure, specifically a support roller station (roller station). The support rollers allow rolling contact between the shoring structure and the conveyor belt. The support rollers have a rolling surface area that is limited on the front side by two cover areas, the bases of the support rollers. Generally, the rolling surface area is formed by a section of cylindrical steel tubing, although other materials and geometries are also possible. The cover areas typically form cast caps or sheet metal caps, which are pressed or welded into openings on the front side of the rolling surface area. In each coverage area, a bearing support is provided for the admission of a shaft that passes through the support roller or a shaft journal that projects into the inner area of the support roller. The bearing supports are ball and roller bearings (which most often form integral components of the coverage area), so that the support rollers are rotatably mounted by internal bearing. Typical embodiments of support rollers are subject to industrial standardization and the formulation of guidelines (such as, for example, in DIN 15207, DIN 22112 or VDI 2341 st