A smart identification-based automatic prying of hair platform and a construction method thereof

Abstract

This invention relates to an automatic rock-scraping trolley based on intelligent recognition and its construction method. The rock-scraping trolley includes an execution device, a sensing device, and a control device. The execution device includes a hydraulic robotic arm and a tracked chassis. A breaker hammer, driven to rotate by a swing cylinder, is mounted on one side of the front end of the hydraulic robotic arm, and a bucket is mounted on the other side. A rotary motor is connected to the rear end of the hydraulic robotic arm, and a bulldozer blade is mounted on the front end of the tracked chassis. The sensing device includes a lidar, a thermal imager, millimeter-wave or ultrasonic radar, and a high-definition camera. The control device includes a processing unit used to determine the area to be scraped based on the detection results of the lidar, thermal imager, and millimeter-wave or ultrasonic radar, and to control the hydraulic robotic arm to perform the scraping operation on the area. This invention enables automatic identification, precise positioning, and efficient removal of loose rocks in complex and narrow mining areas and tunnels, thereby improving the safety and efficiency of rock-scraping operations.

Description

Technical Field

[0001] This invention belongs to the field of mining machinery technology, and in particular relates to an automatic prying trolley based on intelligent recognition and its construction method. Background Technology

[0002] Currently, in the field of underground non-ferrous metal mining, shallow-hole ore-stopping is commonly used for extremely thin veins, and this method accounts for a significant proportion of non-ferrous metal mining. Because shallow-hole ore-stopping typically involves a small cutting width and a large vein dip angle, the stope space is narrow and the working environment is complex, making manual labor still the primary method of operation. After blasting, a certain amount of loose rock or pumice often remains in the stope roof and surrounding rock of the roadways. This loose rock is prone to falling under gravity or vibration, and if not cleared in time, it can easily cause accidents such as injuring or burying workers, posing a serious threat to the lives of underground personnel and potentially leading to stoppages, equipment damage, and significant economic losses for mining companies. Therefore, in underground mines, after blasting, it is usually necessary to roughen the roof and surrounding rock areas to remove loose rock and ensure the safety of subsequent operations.

[0003] Currently, in narrow mining areas and roadways, rock breaking operations mainly rely on manual hand-held crowbars or small rock breaking trolleys operated remotely. Manual hand-held crowbar operations are labor-intensive, inefficient, and require workers to be exposed to potential fall hazards for extended periods, posing significant safety risks. While remote-controlled rock breaking trolleys reduce the risk of personnel directly entering dangerous areas to some extent, this method remains semi-automatic, relying on manual judgment for selecting and locating the breaking area, demanding a high level of experience and skill from the operators. Furthermore, both manual and remote-controlled rock breaking primarily depend on visual identification of loose rock areas; inaccurate assessments of rock looseness can lead to overlooking high-risk areas and causing accidents. Therefore, existing rock breaking methods still have shortcomings in terms of operational safety, automation, and accuracy in identifying loose rock, requiring further improvement. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides an automatic rock-scraping trolley based on intelligent recognition and its construction method. It can automatically identify, accurately locate, and efficiently remove loose rocks in complex and narrow mining and tunnel environments, thereby improving the safety and efficiency of rock-scraping operations.

[0005] To achieve the above objectives, the technical solution of the present invention is as follows: An automatic fur-removing trolley based on intelligent recognition includes an actuator, a sensing device, and a control device. The actuator includes a six-degree-of-freedom hydraulic manipulator and a tracked chassis. The hydraulic manipulator has a breaker hammer driven to rotate by a swing cylinder on one side of its front end, and a bucket on the other side. A rotary motor is connected to the rear end of the hydraulic manipulator for adjusting its lateral posture when entering a mining area or roadway with a large inclination angle. The tracked chassis has a bulldozer blade at its front end and a water tank at its rear end for cleaning the sensor dust covers. The sensing device includes a lidar, a thermal imager, a millimeter-wave or ultrasonic radar, and a high-definition camera. The lidar is used to construct a three-dimensional model of the tunnel with centimeter-level accuracy and mark potential loose rock areas. The thermal imager is used to detect whether there are gaps inside the rock. The millimeter-wave or ultrasonic radar is used to detect whether there are cavities inside the rock. The high-definition camera is used by on-site personnel to observe the working status of the prying trolley inside the tunnel. The control device includes a processing unit for determining the area to be pried based on the detection results of lidar, thermal imager, and millimeter-wave or ultrasonic radar, and controlling the hydraulic robotic arm to perform prying operations on the area to be pried.

[0006] Preferably, the lidar, thermal imager, millimeter-wave or ultrasonic radar are positioned at the same location and spaced apart from the hydraulic breaker to reduce interference of the hydraulic breaker operation with the laser scanning; wherein, the thermal imager and the millimeter-wave or ultrasonic radar are used to perform secondary scanning of potentially loose rock areas to assist the hydraulic breaker in accurately aligning with the target area.

[0007] Preferably, the high-definition camera is mounted on the hydraulic robotic arm.

[0008] On the other hand, the present invention also discloses a construction method based on the above-mentioned intelligent recognition-based automatic shaving trolley, comprising the following steps: S1, the starting point for the remote-controlled scraping trolley to enter the tunnel for scraping. S2, set the total distance L that the roadway needs to be pried, and start automatic prying; S3, deploy the hydraulic robotic arm to the predetermined state T1 so that the lidar can perform scanning; S4, the prying trolley slowly moves forward a predetermined distance while the lidar scans; S5, analyze the three-dimensional model of the tunnel and mark it as a potential loose rock area; S6, the backward movement distance of the prying trolley is L1; S7, select the furthest potential loose rock area within L1 distance in front of the trolley; S8, the hydraulic robotic arm moves closer to the area selected by S7; S9, deploy the hydraulic robotic arm to the predetermined state T2, so that the millimeter-wave or ultrasonic radar and thermal imager can perform a secondary scan of the loose rock area. S10, combining the imaging results of the second scan with the three-dimensional modeling, to determine the area to be pried open; S11, remove the hair from the area to be removed; Steps S7-S11 are repeated to remove all loose rocks within the current segmented prying distance.

[0009] Preferably, in step S4, the predetermined distance is the total distance L; and after completing the current segment prying, the prying trolley retreats segment by segment according to the predetermined segment distance L1, repeating steps S6 to S11 from the inside to the outside, until the prying operation in the entire tunnel area is completed.

[0010] Preferably, in step S4, the predetermined distance is the segment distance L1; and after completing the prying of the current segment, the next segment is advanced, and steps S4 to S11 are repeated from the outside to the inside until the prying operation is completed in the entire tunnel area.

[0011] Preferably, the segment distance L1 is determined based on both the tunnel height and the length of the hydraulic robotic arm.

[0012] Preferably, in step S3, the hydraulic robotic arm extends forward and unfolds, while the breaker remains in a retracted state, and the unfolded height of the hydraulic robotic arm does not exceed 70% of the tunnel height.

[0013] Preferably, in step S9, the local feature map obtained by millimeter-wave or ultrasonic radar or thermal imager is compared with the feature map of the potential loose rock area marked by lidar to determine whether the breaker is aligned with the target area, and the position is finely adjusted according to the offset of the feature map.

[0014] Preferably, in step S10, if any of the following conditions are met, the corresponding area is determined as the area to be pried: the surface curvature is greater than 1.5, or the protrusion of the area exceeds 10cm, or the temperature gradient of the area is greater than 1.5℃ / cm, or the internal cavity size of the area is greater than 10cm³.

[0015] This invention provides a systematic design from two aspects: the mechanical structure layout of the skid trolley and the skid construction method. Compared with the prior art, the advantages of this invention are: (1) In terms of mechanical structure, by rationally arranging lidar, high-definition camera, millimeter-wave radar and thermal imaging sensor, lidar can avoid interference from breaker operation when scanning the roadway, ensuring the stability and accuracy of the roadway three-dimensional modeling; when the robotic arm approaches the prying area and performs precise positioning, millimeter-wave or ultrasonic radar and thermal imaging sensor perform secondary scanning of the target area and compare features with the potential loose rock area marked by lidar, thereby assisting in judging whether the breaker is aligned with the target area, effectively improving the positioning accuracy of robotic arm motion control and prying operation.

[0016] (2) Regarding the construction method, this invention uses multi-source information fusion of lidar, millimeter-wave or ultrasonic radar and thermal imaging sensors to classify and confirm loose rock areas in the roadway, avoiding excessive reliance on human observation and work experience in traditional prying operations. By first constructing a three-dimensional model of the roadway, potential loose rock areas are initially screened, and then the screened areas are subjected to secondary detection by millimeter-wave radar and thermal imaging. Compared with detection methods that rely solely on visual information, this improves the accuracy and reliability of loose rock identification. At the same time, since only potential loose rock areas are scanned and pryed, unnecessary full-area detection processes are reduced, effectively shortening the prying operation time and improving overall work efficiency.

[0017] (3) In the prying construction method of this invention, a segmented scanning and segmented prying operation method is adopted. The entire roadway prying process is divided into multiple continuous construction segments. After the identification, confirmation and prying treatment of loose rocks are completed in each segment, the next segment is started. Through this segmented construction method, it is possible to avoid a one-time comprehensive scanning and prying treatment of the entire roadway, reduce the risk of accumulated misjudgments in the long-distance operation process, and facilitate the fine control of the prying operation progress and operation range. This segmented construction method makes the prying operation process more orderly and controllable, which helps to improve the overall construction stability and operation safety, and is especially suitable for underground mine mining sites and roadway scenarios with limited space and complex operating environments. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of the automatic bark-removing trolley structure based on intelligent recognition according to the present invention; Figure 2 This is a schematic diagram of the automatic bark-removing trolley based on intelligent recognition from another angle. Figure 3 This is a schematic diagram of the automatic scraping trolley based on intelligent recognition entering the mining area and roadway according to the present invention. Figure 4 This is a comparative schematic diagram of the feature maps of the loose rock area in this invention (some features are misaligned). Figure 5 This is a comparative schematic diagram of the loose rock region feature maps of the present invention (local feature alignment); Figure 6 A flowchart illustrating a construction method for an automated barbed wire trolley based on intelligent recognition, according to an embodiment of the present invention. Figure 7 A flowchart illustrating a construction method for an automated barbed wire trolley based on intelligent recognition, according to another embodiment of the present invention. Reference numerals: 1-Hydraulic robotic arm; 2-Crawler chassis; 3-Swing cylinder; 4-Breaker; 5-Bucket; 6-Slewing motor; 7-Bulldozer blade; 8-Water tank; 9-LiDAR; 10-Thermal imager; 11-Millimeter-wave or ultrasonic radar; 12-High-definition camera; 13-Hydraulic station. Detailed Implementation

[0019] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention belong to the present invention.

[0020] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0021] like Figure 1-5 As shown in the figure, this embodiment discloses an automatic rock-scraping trolley based on intelligent recognition, including an execution device, a sensing device, and a control device; wherein, the execution device, the sensing device, and the control device work together to complete the identification, positioning, and rock-scraping operation of loose rocks in underground mines or roadways, thereby realizing the automation and intelligence of the rock-scraping operation.

[0022] The actuator includes a six-degree-of-freedom hydraulic robotic arm 1 and a tracked chassis 2. The hydraulic robotic arm 1, as the main actuator for the prying operation, has multi-degree-of-freedom motion capability and can flexibly adjust its posture in narrow tunnels and complex spaces. The tracked chassis 2 is used to support the entire vehicle structure and provide stable walking capability to adapt to the uneven working environment of underground mines.

[0023] The hydraulic robotic arm 1 has a breaker hammer 4 driven to rotate by a swing cylinder 3 on one side of its front end, and a bucket 5 on the other side. A rotary motor 6 is connected to the rear end of the hydraulic robotic arm 1 to adjust its lateral posture when entering a mining area or roadway with a large inclination angle. The breaker hammer 4 is used for prying and breaking up confirmed loose rock areas. The swing cylinder 3 drives the breaker hammer 4 to rotate and adjust its angle to meet different prying angle requirements. The bucket 5 is used to break up the ground during the movement of the prying trolley. The stone is cleared or the uneven ground is leveled. When there is a pile of rubble or obstruction in the roadway, the bucket 5 can be used to assist in clearing the obstacles. The rotary motor 6 is used to drive the hydraulic robotic arm 1 to rotate as a whole, so that the hydraulic robotic arm 1 can extend into the working space at an oblique posture when entering a mining area or roadway with a large inclination angle, thereby expanding the applicable range of the prying operation. In practical applications, a hydraulic station 13 can also be set on the prying trolley to provide power support for the hydraulic robotic arm 1, the swing cylinder 3, the rotary motor 6 and other hydraulic actuators.

[0024] The tracked chassis 2 is equipped with a bulldozer blade 7 at the front end and a water tank 8 at the rear end for cleaning the dust covers of the sensors. The bulldozer blade 7 is used to level the ground during the movement of the trolley, improving the walking conditions of the tracked chassis 2. The water tank 8 is used to supply water to the dust covers of the sensors at the front end, and to clean the dust covers of sensors such as the lidar 9 and the thermal imager 10 in the dusty mining environment, so as to ensure the detection accuracy of the sensors.

[0025] The sensing device includes a lidar 9, a thermal imager 10, a millimeter-wave or ultrasonic radar 11, and a high-definition camera 12. The lidar 9 is used to construct a three-dimensional model of the tunnel with centimeter-level accuracy and mark potentially loose rock areas. During the movement of the prying trolley, the lidar 9 scans the tunnel ahead at a high scanning rate (e.g., 500,000 points / second) to predict the travel path and avoid obstacles, and to identify protruding rocks and mark them as potentially loose rock areas by analyzing the tunnel surface morphology. The thermal imager 10 is used to detect whether there are cracks inside the rock. The air gap detection system utilizes the difference in thermal conductivity between loose rock and stable rock mass to determine the presence of air gaps. When air gaps exist inside the rock, the surface temperature gradient is more obvious (typical difference of 0.5-2℃), while the temperature distribution of stable rock mass is relatively continuous. Millimeter-wave or ultrasonic radar 11 is used to detect whether there are cavities inside the rock. When cavities exist inside the rock, the radar signal will generate obvious secondary reflection echoes, thereby assisting in judging the internal structural state of the rock. High-definition camera 12 is used by on-site personnel to observe the working status of the prying trolley inside the tunnel in real time, so as to make manual intervention or safety confirmation when necessary.

[0026] The control device includes a processing unit for determining the area to be pried based on the detection results of lidar 9, thermal imager 10, and millimeter-wave or ultrasonic radar 11, and controlling the hydraulic robotic arm 1 to perform prying operations on the area to be pried. The processing unit performs fusion analysis on the data collected by multiple sensors. First, it marks potential loose rock areas based on lidar 9, and then performs secondary confirmation by combining the detection results of thermal imager 10 and millimeter-wave or ultrasonic radar 11, thereby improving the accuracy of the determination of the area to be pried. Based on this, it generates motion control commands for the hydraulic robotic arm 1 to achieve precise positioning and prying operations on the breaker hammer 4.

[0027] Furthermore, the lidar 9, thermal imager 10, and millimeter-wave or ultrasonic radar 11 are positioned in the same location, maintaining a distance from the hydraulic breaker 4 to reduce interference from the hydraulic breaker's operation on the laser scanning. Specifically, they can be positioned above the hydraulic station 13, near the side of the hydraulic robotic arm 1. The thermal imager 10 and the millimeter-wave or ultrasonic radar 11 are both used to perform secondary scanning of potentially loose rock areas, assisting the hydraulic breaker 4 in accurately aligning the target area. The lidar 9, positioned in this location, can maintain a relatively stable scanning posture before and during the hydraulic breaker's prying operation, and is used to construct a three-dimensional model of the tunnel and continuously mark potentially loose rock areas. The high-definition camera 12 is mounted on the hydraulic robotic arm 1 to expand the monitoring coverage of the operation.

[0028] like Figure 4-5 As shown, the local feature map is used to determine the alignment of the hydraulic breaker 4 with the target rock area. When the local feature map is not centered, it is considered that the hydraulic breaker 4 is not fully aligned and fine-tuning is required by the hydraulic robotic arm 1 to achieve precise alignment. When the local feature map is centered on the target rock area, it is considered that the hydraulic breaker 4 is aligned with the target area and the roughening operation can be performed.

[0029] In this embodiment, by adjusting the posture of the hydraulic robotic arm 1, the millimeter-wave or ultrasonic radar 11 and the thermal imager 10 are aligned with the target area to detect the internal structure and thermal characteristics of the potential loose rock area. By comparing the local feature map obtained by the millimeter-wave or ultrasonic radar 11 or the thermal imager 10 with the feature map of the potential loose rock area marked by the lidar 9, it is determined whether the breaker 4 is aligned with the target area, and the position is finely adjusted according to the offset of the feature map.

[0030] like Figure 6-7 As shown, embodiments of the present invention also disclose a construction method for an automatic shaving trolley based on intelligent recognition, comprising the following steps: S1, the starting point for the remote-controlled prying trolley to enter the roadway; wherein, the prying trolley is remotely controlled to enter the roadway to be constructed, avoiding the direct entry of workers into areas with the risk of loose rocks, and providing a safe initial working position for subsequent automatic prying operations.

[0031] S2, set the total distance L of the roadway to be pried, and start automatic prying; where the total distance L is set according to the actual length of the roadway or the length of the section that needs to be pried, and is used to limit the overall scope of this automatic prying operation.

[0032] S3, the hydraulic robotic arm 1 is deployed to a predetermined state T1 so that the lidar 9 can perform scanning; wherein, the hydraulic robotic arm 1 extends forward and is deployed, the breaker 4 remains in a retracted state, and the deployed height of the hydraulic robotic arm 1 is controlled to not exceed 70% of the tunnel height, so as to ensure that the lidar 9 is not blocked by the breaker 4 during the scanning process, thereby obtaining stable three-dimensional scanning data of the tunnel.

[0033] S4, the prying trolley slowly moves forward a predetermined distance while the lidar 9 scans; during the movement, the prying trolley maintains a low and constant speed, and the lidar 9 continuously scans the space of the roadway ahead, on the one hand to build a three-dimensional model of the roadway, and on the other hand to predict the travel path and avoid obstacles.

[0034] S5. Analyze the three-dimensional model of the tunnel and mark it as a potential loose rock area. Specifically, by analyzing the surface morphology of the rock in the three-dimensional model of the tunnel, when the surface curvature of the rock is found to be greater than a preset threshold or there is obvious protrusion in a local area, such as when the surface curvature is greater than 1.2 or the protrusion in the area is greater than 5cm, the corresponding area is marked as a potential loose rock area for subsequent key processing.

[0035] S6, the retraction distance L1 of the prying trolley; where L1 is the segmented prying distance, which is determined according to the tunnel height and the working range of the hydraulic robotic arm 1, so that the prying trolley returns to a relatively safe position that is convenient for prying operations. L1 can be half the tunnel height, about 2m.

[0036] S7, select the furthest potential loose rock area within a distance L1 in front of the trolley; among them, the potential loose rock areas are processed in order from farthest to nearest to avoid interfering with the untreated areas during the prying process and improve the safety of the operation.

[0037] S8, the hydraulic robotic arm 1 approaches the area selected in S7; wherein, the hydraulic robotic arm 1 drives the breaker 4 to approach the target area, so that the breaker 4 maintains a predetermined approach distance of about 10cm with the target rock area after being deployed.

[0038] S9, the hydraulic robotic arm 1 is deployed to the predetermined state T2, so that the millimeter-wave or ultrasonic radar 11 and the thermal imager 10 perform a secondary scan of the loose rock area; wherein, by adjusting the posture of the hydraulic robotic arm 1, the millimeter-wave or ultrasonic radar 11 and the thermal imager 10 are aligned with the target area, and the internal structure and thermal characteristics of the potential loose rock area are detected. By comparing the local feature map obtained by the millimeter-wave or ultrasonic radar 11 or the thermal imager 10 with the feature map of the potential loose rock area marked by the lidar 9, it is determined whether the breaker 4 is aligned with the target area, and the position is finely adjusted according to the offset of the feature map.

[0039] S10. Combining the imaging results of the secondary scan with the 3D model, determine the area to be pried. Specifically, when the target area meets the preset loosening criteria, the corresponding area is designated as the area to be pried to avoid unnecessary fracturing of stable rock mass. For example, if any of the following conditions are met, the corresponding area is designated as the area to be pried: surface curvature greater than 1.5, or the protrusion in the area exceeds 10cm, or the temperature gradient in the area is greater than 1.5℃ / cm, or the internal cavity size of the area is greater than 10cm³.

[0040] S11, the area to be pried is pried; wherein, the hydraulic robotic arm 1 further drives the breaker 4 to touch the target rock and perform the breaking and prying operation. During the prying process, PID closed-loop control can also be used to adjust the impact force of the breaker 4 in real time. The millimeter wave or ultrasonic radar 11 detects that when the target area is flat, the prying of the area is completed.

[0041] Steps S7-S11 are repeated to remove all loose rocks within the current segmented prying distance.

[0042] like Figure 6 As shown, in one embodiment, in step S4, the predetermined distance is the total distance L; and after completing the prying of the current segment, the prying trolley retreats segment by segment at the predetermined segment distance L1, repeating steps S6 to S11 from the inside out until the prying operation is completed within the entire tunnel area. In this embodiment, after entering the tunnel, the prying trolley first advances along the tunnel direction to cover the entire total distance L to be pryed, and performs an overall scan of the tunnel space using the lidar 9 to complete a three-dimensional model. After completing the overall marking of the potential loose rock area, it retreats segment by segment at the segment distance L1. After completing each segment, the potential loose rock area within that segment is scanned and pryed a second time, so that the prying operation proceeds segment by segment from the inside of the tunnel to the outside, thereby avoiding interference with untreated areas during the prying process, improving operational safety, and is suitable for construction scenarios with long tunnel lengths and relatively stable overall spatial conditions.

[0043] like Figure 7As shown, in another embodiment, in step S4, the predetermined distance is the segment distance L1; and after completing the prying of the current segment, the trolley continues to advance to the next segment, repeating steps S4 to S11 from the outside to the inside until the prying operation is completed within the entire tunnel. In this embodiment, after entering the tunnel, the prying trolley advances segment by segment in units of segment distance L1. After completing each segment, the potential loose rock area within the current segment is scanned, confirmed, and pryed before entering the next segment to continue the operation. This allows the prying process to proceed segment by segment from the outside of the tunnel to the inside, thus keeping the trolley in the treated area or a relatively safe area throughout the prying process. This is suitable for operation scenarios where tunnel space is limited or the construction environment changes significantly.

[0044] In addition, in other embodiments, step S7 is not limited to processing according to the spatial distance of potential loose rock areas. Alternatively, after completing step S6, each potential loose rock area within the segmented distance range in front of the trolley can be scanned twice in sequence. Based on the detection results obtained by the millimeter-wave or ultrasonic radar 11 and the thermal imager 10, the risk level of each potential loose rock area can be assessed, and the processing order of the areas to be pried can be determined according to the risk weight, so that the prying operation is carried out on the areas with higher risk levels first.

[0045] In summary, this invention discloses an automatic rock-breaking trolley based on intelligent recognition and its construction method. By integrating a hydraulic robotic arm 1, a tracked chassis 2, a hydraulic breaker 4, a lidar 9, a thermal imager 10, a millimeter-wave or ultrasonic radar 11, and a high-definition camera 12 onto the rock-breaking trolley, and using a control device to fuse and analyze multi-source sensor data, it achieves automatic identification, precise positioning, and segmented rock-breaking operations in underground mine working areas and roadways. This technical solution uses the lidar 9 to construct a three-dimensional model of the roadway and screen potential loose rock areas, and then combines the thermal imager 10 and the millimeter-wave or ultrasonic radar 11 for secondary detection and alignment control, improving the accuracy of loose rock identification and the positioning precision of the hydraulic breaker 4's rock-breaking operation. Simultaneously, the construction method combining segmented scanning and segmented rock-breaking makes the rock-breaking process more orderly and controllable, effectively reducing the safety hazards of workers directly exposed to loose rock risk areas and improving overall work efficiency. This invention can adapt to complex operating environments such as extremely thin ore veins, high-angle mining areas, and space-constrained roadways, and provides a highly automated and intelligent technical solution for underground mine skidding operations. It has positive significance for improving the safety level of mine production and promoting the intelligent development of mining machinery and equipment.

[0046] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Under the concept of the present invention, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the present invention as described above. For the sake of brevity, they are not provided in detail. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An automatic fur-removing trolley based on intelligent recognition, characterized in that, Includes actuators, sensing devices, and control devices; The actuator includes a six-degree-of-freedom hydraulic manipulator (1) and a tracked chassis (2); the hydraulic manipulator (1) has a breaker hammer (4) driven to rotate by a swing cylinder (3) on one side of its front end, and a bucket (5) on the other side of its front end; the hydraulic manipulator (1) is connected to a rotary motor (6) at its rear end, which is used to drive the hydraulic manipulator to adjust its lateral posture when entering a mining area or roadway with a large inclination angle; the tracked chassis (2) has a bulldozer blade (7) at its front end and a water tank (8) at its rear end for cleaning the dust cover of the sensor. The sensing device includes a lidar (9), a thermal imager (10), a millimeter-wave or ultrasonic radar (11), and a high-definition camera (12); the lidar (9) is used to construct a three-dimensional model of the tunnel with centimeter-level accuracy and mark potential loose rock areas; the thermal imager (10) is used to detect whether there are gaps inside the rock; the millimeter-wave or ultrasonic radar (11) is used to detect whether there are cavities inside the rock; and the high-definition camera (12) is used by on-site personnel to observe the working status of the prying trolley inside the tunnel. The control device includes a processing unit for determining the area to be pried based on the detection results of the lidar (9), thermal imager (10) and millimeter-wave or ultrasonic radar (11), and controlling the hydraulic robotic arm (1) to perform prying operations on the area to be pried.

2. The automatic bark-removing trolley based on intelligent recognition according to claim 1, characterized in that, The lidar (9), thermal imager (10), and millimeter-wave or ultrasonic radar (11) are positioned in the same location and are spaced apart from the hydraulic breaker (4) to reduce the interference of the hydraulic breaker operation on the laser scanning. The thermal imager (10) and the millimeter-wave or ultrasonic radar (11) are used to perform secondary scanning on potentially loose rock areas to assist the hydraulic breaker (4) in accurately aligning the target area.

3. The automatic bark-clearing trolley based on intelligent recognition according to claim 2, characterized in that, The high-definition camera (12) is mounted on the hydraulic robotic arm (1).

4. A construction method based on the intelligent recognition-based automatic plastering trolley as described in any one of claims 1-3, characterized in that, Includes the following steps: S1, the starting point for the remote-controlled scraping trolley to enter the tunnel for scraping. S2, set the total distance L that the roadway needs to be pried, and start automatic prying; S3, deploy the hydraulic robotic arm (1) to the predetermined state T1 so that the lidar (9) can perform scanning; S4, the prying trolley slowly moves forward a predetermined distance while the lidar (9) scans; S5, analyze the three-dimensional model of the tunnel and mark it as a potential loose rock area; S6, the backward movement distance of the prying trolley is L1; S7, select the furthest potential loose rock area within L1 distance in front of the trolley; S8, the hydraulic robotic arm (1) approaches the area selected by S7; S9, deploy the hydraulic robotic arm (1) to the predetermined state T2, so that the millimeter wave or ultrasonic radar (11) and the thermal imager (10) can perform a secondary scan of the loose rock area; S10, combining the imaging results of the second scan with the three-dimensional modeling, to determine the area to be pried open; S11, pry the area to be pried off; Steps S7-S11 are repeated to remove all loose rocks within the current segmented prying distance.

5. The construction method of the automatic barbed trolley based on intelligent recognition according to claim 4, characterized in that, In step S4, the predetermined distance is the total distance L; and after the current segment is pried open, the prying trolley retreats segment by segment according to the predetermined segment distance L1, repeating steps S6 to S11 from the inside to the outside, until the prying operation in the entire tunnel area is completed.

6. The construction method of the automatic shaving trolley based on intelligent recognition according to claim 4, characterized in that, In step S4, the predetermined distance is the segment distance L1; and after completing the prying of the current segment, the next segment is advanced, and steps S4 to S11 are repeated from the outside to the inside until the prying operation of the entire tunnel is completed.

7. The construction method of the automatic barbed wire prying trolley based on intelligent recognition according to claim 5 or 6, characterized in that, The segment distance L1 is determined by the tunnel height and the length of the hydraulic robotic arm (1).

8. The construction method of the automatic shaving trolley based on intelligent recognition according to claim 7, characterized in that, In step S3, the hydraulic manipulator (1) extends forward and unfolds, while the breaker (4) remains in a retracted state, and the unfolded height of the hydraulic manipulator (1) does not exceed 70% of the tunnel height.

9. The construction method of the automatic barbed wire trolley based on intelligent recognition according to claim 7, characterized in that, In step S9, the local feature map obtained by millimeter-wave or ultrasonic radar (11) or thermal imager (10) is compared with the feature map of potential loose rock area marked by lidar (9) to determine whether the hydraulic breaker (4) is aligned with the target area, and the position is finely adjusted according to the offset of the feature map.

10. The construction method of the automatic shoveling trolley based on intelligent recognition according to claim 7, characterized in that, In step S10, if any of the following conditions are met, the corresponding area is determined to be the area to be pried: the surface curvature is greater than 1.5, or the protrusion of the area exceeds 10cm, or the temperature gradient of the area is greater than 1.5℃ / cm, or the internal cavity size of the area is greater than 10cm³.

Images