A coal bunker dynamic blockage cleaning device and method based on bionics and digital twinning
Patent Information
- Application Number
- CN202510592021.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-09
- Publication Date
- 2026-11-03
- Estimated Expiration
- 2045-05-09
AI Technical Summary
Existing coal bunkers are prone to blockages when taking out coal due to large pieces of coal or excessive moisture. Traditional cleaning methods are time-consuming, labor-intensive, and inconvenient, and existing equipment is prone to failure and cannot monitor blockages in a timely manner.
The flexible conical coal bunker, which adopts a biomimetic design, combines digital twin technology and deep reinforcement learning algorithms. Through longitudinal extension, scaling, twisting and spiral peristalsis mechanisms, it monitors strain signals in real time to achieve automated blockage clearing.
It achieves automated, low-cost, and timely coal bunker unblocking, avoiding equipment damage and manual labor intensity, and improving cleaning efficiency.
Smart Images

Figure CN120171952B_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of coal bunker unblocking technology, specifically relating to a dynamic coal bunker unblocking device and method based on bionics and digital twins. Background Technology
[0002] Coal bunkers are used to store pulverized coal and coal lumps. A belt conveyor is often connected to the bottom of the bunker to transport the coal lumps and pulverized coal to the required equipment, such as the furnace of a thermal power plant, via a conical discharge bin. However, when retrieving coal from the bunker, large pieces of coal often cause blockages at the conical discharge bin, or excessive moisture due to humid weather can cause pulverized coal to adhere to the conical discharge bin walls, reducing the internal passageways and causing blockages.
[0003] Most coal bunkers still rely on manual cleaning, which, while not requiring specialized equipment, is time-consuming, labor-intensive, and exposes workers to harsh working conditions, contradicting the people-oriented production philosophy. Another solution involves installing vibration and mixing equipment inside the coal bunkers for cleaning. This method is somewhat effective, but if the equipment malfunctions, the coal in the bunker must be removed for repairs, which is extremely inconvenient. Summary of the Invention
[0004] In order to solve at least one of the above-mentioned technical problems in the prior art, the present invention provides a dynamic coal bunker unblocking device and method based on bionics and digital twins.
[0005] This invention employs the following technical solution: a dynamic coal bunker unblocking device based on bionics and digital twins, comprising a bionic conical coal feeding bunker, a longitudinal telescopic mechanism, a scaling and torsional mechanism, a spiral peristaltic mechanism, and a material monitoring and decision-making module; the bionic conical coal feeding bunker is a flexible structure made of wear-resistant rubber material, located between the upper and lower discs of the longitudinal telescopic mechanism, and can achieve axial expansion and contraction along the discs under the drive of the telescopic components of the longitudinal telescopic mechanism; the scaling and torsional mechanism is installed between the discharge end of the bionic conical coal feeding bunker and the lower disc of the longitudinal telescopic mechanism, and is used to control the bionic... The opening and closing degree and torsion angle of the discharge port of the conical coal feeding bunker; the spiral track of the spiral peristaltic mechanism surrounds the outer periphery of the biomimetic conical coal feeding bunker and is connected to the upper plate of the longitudinal telescopic mechanism. The peristaltic mechanism of the spiral peristaltic mechanism can move on the spiral track and generate a peristaltic crushing force on the biomimetic conical coal feeding bunker; the material monitoring and decision module is installed on the outer surface of the biomimetic conical coal feeding bunker to monitor the strain signal of the biomimetic conical coal feeding bunker, and control the longitudinal telescopic mechanism, the scaling and torsional mechanism and the spiral peristaltic mechanism based on the strain signal to realize the contraction, expansion, torsion, bending and peristalsis of the biomimetic conical coal feeding bunker.
[0006] Preferably, the biomimetic conical coal feeding bin has reinforcing ribs inside; the diameter of the feed inlet of the biomimetic conical coal feeding bin is larger than the diameter of the discharge outlet.
[0007] Preferably, the longitudinal telescopic mechanism includes a telescopic component, an upper plate, and a lower plate. The upper plate is fixed to the feed end of the biomimetic conical coal discharge bunker and has a channel at its center that matches the feed end. The telescopic component includes multiple telescopic cylinders spaced apart along the outer periphery of the plate. The lower plate is connected to the lower part of the upper plate via telescopic cylinders and has a channel at its center that matches the discharge end.
[0008] Preferably, multiple scaling and torsional mechanisms are arranged at intervals along the circumference of the lower plate. Each scaling and torsional mechanism includes a scaling and torsional hydraulic cylinder, a torsional motor, a torsional bracket, and a torsional sliding groove. The torsional sliding groove is located on the circumference of a virtual circle with one of the radii as the center of the lower plate. The torsional sliding groove is an arc-shaped groove. The two ends of the scaling and torsional hydraulic cylinder are respectively rotatably connected to the discharge end of the biomimetic conical coal discharge bunker and the torsional bracket. The torsional bracket is slidably arranged in the torsional sliding groove and driven by the torsional motor. The lower end of the torsional bracket is provided with a drive wheel connected to the output shaft of the torsional motor.
[0009] Preferably, the spiral peristaltic mechanism includes a spiral track, a track fixing frame, and a peristaltic mechanism; the spiral track is connected to the upper plate of the longitudinal telescopic mechanism through the track fixing frame; the peristaltic mechanism includes a peristaltic motor body, a peristaltic hydraulic cylinder, a swing arm, a peristaltic motor, a rotating tripod, and peristaltic wheels. The three peristaltic wheels are rotatably connected in a triangular shape to the inner layer of the rotating tripod. The swing arm is rotatably connected between the peristaltic motor body and the rotating tripod. The two ends of the peristaltic hydraulic cylinder are rotatably connected to the peristaltic motor body and the swing arm, respectively. The drive shaft of the peristaltic motor is keyed to the central shaft of the rotating tripod. The peristaltic motor is used to drive the rotating tripod to rotate around its center to provide rotational force for the peristaltic wheels. The peristaltic hydraulic cylinder is used to drive the swing arm to rotate at a small angle.
[0010] Preferably, the material monitoring and decision-making module includes strain gauges and a digital twin control module. Multiple strain gauges are evenly and layered along the circumference of the biomimetic conical coal feeding bunker. The digital twin control module controls the longitudinal telescopic mechanism, the scaling and torsional mechanism, and the spiral peristaltic mechanism based on the strain signals collected by the strain gauges at the biomimetic conical coal feeding bunker.
[0011] A second aspect of the present invention also provides a dynamic unblocking method for coal bunkers based on bionics and digital twins, comprising the following steps: Based on multibody system dynamics-discrete element software, a rigid-flexible-discrete coupled model of the dynamic unblocking device was established, and simulation of dynamic unblocking in coal bunkers was carried out. Using the motion state of coal particles during the simulation process as input, and the total strain value of the corresponding biomimetic conical coal feeding bin as the target, a convolutional neural network is used for fitting to obtain the correspondence between the strain value and the internal coal particles. Based on the strain value, it is determined whether there is a fault condition such as coal blockage or coal powder adhesion inside, as well as the motion state of coal particles inside under normal working conditions, thus completing the establishment of a digital twin system. In the digital twin system, a deep reinforcement learning algorithm is used to control the longitudinal stretching system, scaling and twisting system, and spiral peristalsis system to cooperate in completing the biomimetic movements of contraction, expansion, twisting, bending and peristalsis. The optimal movement is determined by training with the strain values corresponding to the smooth discharge of coal particles inside the system and the smooth discharge of coal particles after peristalsis after coal blockage. The real-time strain values of strain gauges at the biomimetic conical coal feeding bunker are obtained and input into the digital twin system. The digital twin system monitors the motion state of coal particles in the current biomimetic conical coal feeding bunker in real time and decides the optimal motion state to feed back to the longitudinal extension system, scaling and torsional system, and spiral peristalsis system in the real world for action.
[0012] Preferably, in the rigid-flexible-dispersive coupling model of the dynamic unblocking device, the biomimetic conical coal discharge bunker is constructed as a flexible body, while the longitudinal telescopic mechanism, scaling and torsional mechanism, spiral creep mechanism, and strain gauge are rigid bodies. The discrete element method is used to restore the true shape and material properties of the coal block, simulate the situations of coal blockage, smooth coal discharge, smooth coal discharge after creeping after coal blockage, and smooth coal discharge after creeping after coal blockage, and the inability to discharge coal smoothly after creeping. Simulation analysis is performed, and the strain value under each simulation is recorded.
[0013] Preferably, the original diameter D of the outlet of the flexible biomimetic conical coal bunker is used as a reference, and the diameter of the coal particles is set to be less than or equal to the original diameter D. The shape of the coal particles is randomly generated according to the actual situation. Simulations were conducted to obtain strain values under different working conditions: smooth coal discharge, coal blockage, smooth coal discharge after coal blockage and subsequent creep, and failure to discharge coal smoothly after coal blockage and subsequent creep. A convolutional neural network was used for fitting to obtain the nonlinear relationship between the strain value and the internal coal particles.
[0014] Preferably, the digital twin system reassesses the monitored state every 0.5 seconds to adjust the action strategy in real time, and the deep reinforcement learning algorithm is the Deep Deterministic Policy Gradient algorithm.
[0015] Compared with the prior art, the beneficial effects of the present invention are: This invention designs a flexible, biomimetic conical coal feeding bin based on the biomimetic principles of intestinal peristalsis and snake mouth contraction, thus avoiding the risk of coal blockage. The spiral extrusion method prevents damage such as tearing during the extrusion process.
[0016] The movement of coal blocks in the coal bunker was monitored in real time using digital twin technology, providing data support for control strategies. It can determine whether blockage has occurred inside the bunker without the need for drilling or using expensive instruments. Using strain gauges is a low-cost method.
[0017] This system, based on deep reinforcement learning algorithms to control motion, is a purely data-driven strategy that eliminates the need for complex mechanistic mathematical models, resulting in low development costs and high efficiency. Furthermore, the control strategy is adjusted every 0.5 seconds, making it a dynamic process that facilitates timely detection of congestion risks. Attached Figure Description
[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0019] Figure 1 This is an overall structural diagram of the present invention; Figure 2 This is a schematic diagram of the dynamic unblocking device of the present invention; Figure 3 This is a schematic diagram of the scaling and torsional system of the present invention; Figure 4 This is a schematic diagram of the spiral peristaltic system of the present invention; Figure 5 This is a schematic diagram of the peristaltic device of the present invention (first view). Figure 6 This is a schematic diagram of the peristaltic device of the present invention (second view).
[0020] In the diagram: 1-Bionic conical coal bunker; 2.1-Telescopic component; 2.2-Upper plate; 2.3-Lower plate; 3.1-Helical track; 3.2-Track fixing frame; 3.3-Peristaltic motor body; 3.4-Peristaltic hydraulic cylinder; 3.5-Swing arm; 3.6-Peristaltic motor; 3.7-Rotating tripod; 3.8-Peristaltic wheel; 4.1-Scaling and torsional hydraulic cylinder; 4.2-Torsional motor; 4.3-Torsional support; 4.4-Torsional sliding groove; 5-Strain gauge; 6-Coal bunker. Detailed Implementation
[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0022] It should be noted that the structures, proportions, sizes, etc., shown in the accompanying drawings of this specification are only for the purpose of assisting those skilled in the art in understanding and reading the content disclosed in the specification, and are not intended to limit the conditions under which the present invention can be implemented. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in the proportional relationships, or adjustments to the size, without affecting the effects and objectives that the present invention can produce, should fall within the scope of the technical content disclosed in the present invention. It should be noted that in this specification, relational terms such as "first" and "second" are only used to distinguish one entity from several other entities, and do not necessarily require or imply any actual relationship or order between these entities.
[0023] This invention provides an embodiment: like Figures 1 to 6 As shown, a dynamic coal bunker unblocking device based on bionics and digital twins includes a bionic conical coal bunker 1, a longitudinal telescopic mechanism, a scaling and torsional mechanism, a spiral peristaltic mechanism, and a material monitoring and decision-making module. The bionic conical coal bunker 1 is a flexible structure located between the upper and lower discs of the longitudinal telescopic mechanism, and can extend and retract along the axial direction of the discs under the action of the telescopic component 2.1 of the longitudinal telescopic mechanism. The scaling and torsional mechanism is installed between the discharge end of the bionic conical coal bunker 1 and the lower disc 2.3 of the longitudinal telescopic mechanism, and is used to control the opening and closing degree of the discharge port of the bionic conical coal bunker 1. The spiral track 3.1 of the spiral peristaltic mechanism surrounds the outer periphery of the biomimetic conical coal feeding bin 1 and is connected to the upper plate 2.2 of the longitudinal telescopic mechanism. The peristaltic mechanism of the spiral peristaltic mechanism can move on the spiral track 3.1 and generate a peristaltic crushing force on the biomimetic conical coal feeding bin 1. The material monitoring and decision module is installed on the outer surface of the biomimetic conical coal feeding bin 1 to monitor the strain signal of the biomimetic conical coal feeding bin 1, and control the longitudinal telescopic mechanism, the scaling and torsional mechanism and the spiral peristaltic mechanism based on the strain signal to realize the contraction, expansion, torsion, bending and peristalsis of the biomimetic conical coal feeding bin 1.
[0024] In this embodiment, the biomimetic conical coal discharge bin 1 is made of high-strength, wear-resistant rubber material and has internal reinforcing ribs. The diameter of the inlet of the biomimetic conical coal discharge bin 1 is larger than the diameter of the outlet, which can withstand the impact and wear of the coal flow. The biomimetic conical coal discharge bin can mimic the peristaltic principle of intestines under the drive of the spiral peristalsis system, so that the coal blocks can be discharged smoothly. Under the drive of the scaling and twisting system, it simulates the flexible expansion and contraction of a snake's mouth, realizing automatic adjustment of the opening size and reducing coal block accumulation. Under the coordinated cooperation of the longitudinal expansion and contraction system, the scaling and twisting system, and the spiral peristalsis system, it can perform multimodal motion, including contraction, relaxation, twisting, bending, and peristalsis, effectively clearing the coal flow and preventing blockage.
[0025] The longitudinal telescopic mechanism includes a telescopic component 2.1, an upper plate 2.2, and a lower plate 2.3. The upper plate 2.2 is fixed to the feed end of the biomimetic conical coal feeding bin 1 and has a channel at its center that matches the feed end. The telescopic component 2.1 includes multiple telescopic cylinders spaced along the outer periphery of the plate. The lower plate 2.3 is connected to the lower part of the upper plate 2.2 via telescopic cylinders and has a channel at its center that matches the discharge end.
[0026] Multiple scaling and torsional mechanisms are spaced along the circumference of the lower plate 2.3. Each mechanism includes a scaling and torsional hydraulic cylinder 4.1, a torsional motor 4.2, a torsional support 4.3, and a torsional sliding groove 4.4. The torsional sliding groove 4.4 is located on the circumference of a virtual circle with one radius centered on the center of the lower plate 2.3. The torsional sliding groove 4.4 is an arc-shaped groove. The two ends of the scaling and torsional hydraulic cylinder 4.1 are rotatably connected to the discharge end of the biomimetic conical coal feeding bin 1 and the torsional support 4.3, respectively. The torsional support 4.3 is slidably mounted in the torsional sliding groove 4.4 and driven by the torsional motor 4.2. A drive wheel connected to the output shaft of the torsional motor 4.2 is located at the lower end of the torsional support 4.3. The torsional support 4.3 and the torsional sliding groove 4.4 are connected by a tongue-and-groove sliding connection to restrict the vertical movement of the torsional support 4.3 and prevent it from flying out of the torsional sliding groove 4.4 during torsional movements.
[0027] By scaling and extending / retracting the hydraulic cylinder 4.1, the opening of the biomimetic conical coal feeding bin can be made to have different sizes, resembling a snake's mouth. When the torsion support slides to different positions in the torsion sliding groove, it can cause the biomimetic conical coal feeding bin to twist to different degrees, causing the coal powder adhering to the inside to fall off.
[0028] The spiral peristaltic mechanism includes a spiral track 3.1, a track fixing frame 3.2, and a peristaltic mechanism. The spiral track 3.1 is connected to the upper plate 2.2 of the longitudinal telescopic mechanism via the track fixing frame 3.2. The peristaltic mechanism includes a peristaltic motor body 3.3, a peristaltic hydraulic cylinder 3.4, a swing arm 3.5, a peristaltic motor 3.6, a rotating tripod 3.7, and peristaltic wheels 3.8. The three peristaltic wheels 3.8 are rotatably connected in a triangular shape to the inner layer of the rotating tripod 3.7. The swing arm 3.5 is rotatably connected between the peristaltic motor body 3.3 and the rotating tripod 3.7. The two ends of the peristaltic hydraulic cylinder 3.4 are rotatably connected to the peristaltic motor body 3.3 and the swing arm 3.5, respectively. The drive shaft of the peristaltic motor 3.6 is keyed to the central shaft of the rotating tripod 3.7. The peristaltic motor 3.6 is used to drive the rotating tripod 3.7 to rotate around its center to provide rotational force for the peristaltic wheels 3.8. The peristaltic hydraulic cylinder 3.4 is used to drive the swing arm to rotate at a small angle. By using a flexible, biomimetic conical coal outlet 1 to generate a creeping crushing force on the coal blocks inside, the coal blocks that are blocked inside can be smoothly discharged or broken into small coal particles.
[0029] The material monitoring and decision-making module includes strain gauges 5 and a digital twin control module. The multiple strain gauges 5 are evenly and layered along the circumference of the biomimetic conical coal feeding bunker 1, divided into 3 layers, with 6 strain gauges evenly distributed in each layer, and are installed in the strain gauge mounting slots. The digital twin control module controls the longitudinal telescopic mechanism, scaling and torsional mechanism, and spiral peristaltic mechanism based on the strain signals collected by the strain gauges 5 at the biomimetic conical coal feeding bunker 1.
[0030] In a second aspect, the present invention also provides a dynamic unblocking method for coal bunkers based on bionics and digital twins, comprising the following steps: S1: Based on multibody system dynamics-discrete element software, a rigid-flexible-dispersive coupling model of the dynamic unblocking device is established, and the dynamic unblocking of the coal bunker is simulated. In the rigid-flexible-dispersive coupling model of the dynamic unblocking device, the biomimetic conical coal discharge bunker 1 is constructed as a flexible body, while the longitudinal telescopic mechanism, scaling and torsional mechanism, spiral creep mechanism and strain gauge 5 are rigid bodies. The discrete element method is used to restore the real shape and material properties of the coal block, and the situations of coal blockage, smooth coal discharge, smooth coal discharge after creep after coal blockage, and smooth coal discharge after creep after coal blockage are simulated. The simulation analysis is carried out, and the strain value under each simulation is recorded.
[0031] S2: Taking the motion state of coal particles during the simulation process as input, and the total strain value of the corresponding biomimetic conical coal feeding bin as the target, a convolutional neural network is used for fitting to obtain the correspondence between the strain value and the internal coal particles. Based on the strain value, it is determined whether there is a fault condition such as coal blockage or coal powder adhesion inside, as well as the motion state of coal particles inside under normal working conditions, thus completing the establishment of the digital twin system. Specifically, in the simulation, the size of the coal particles is user-defined; any desired size or shape can be set, but it needs to be based on the actual coal particles in the coal bunker. With different coal particles, the rigid-flexible-dispersive coupling model automatically outputs strain values for different particle sizes. During the simulation, a single variable is controlled. Using the original diameter D of the outlet of the flexible biomimetic conical coal bunker as a benchmark, the coal particle diameters are set to 0.1D, 0.2D, 0.3D...D, and the shape of the coal particles is randomly generated based on real-world conditions. Simulations are performed to obtain strain values under different operating conditions: smooth coal discharge, coal blockage, smooth coal discharge after coal blockage and subsequent creep, and failure to discharge smoothly after coal blockage and subsequent creep. A convolutional neural network is used for fitting to obtain the nonlinear relationship between the strain values and the internal coal particles.
[0032] S3: In the digital twin system, a deep reinforcement learning algorithm is used to control the longitudinal stretching system, scaling and twisting system, and spiral peristalsis system to cooperate in completing biomimetic movements of contraction, expansion, twisting, bending, and peristalsis. The optimal movement is determined by training with the strain values corresponding to the smooth discharge of coal particles inside the system and the smooth discharge of coal after peristalsis following coal blockage. The deep reinforcement learning algorithm is the Deep Deterministic Policy Gradient algorithm.
[0033] S4: Acquire the real-time strain values of strain gauges at the biomimetic conical coal feeding bunker. Input these values into the digital twin system. The digital twin system monitors the motion state of coal particles within the bunker in real time and determines the optimal motion state, feeding it back to the real-world longitudinal extension system, scaling and torsional system, and spiral peristalsis system for action. The digital twin system reassesses the monitored state every 0.5 seconds to adjust the action strategy in real time, avoiding the risk of blockage.
[0034] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.
Claims
1. A dynamic unblocking device for coal bunkers based on bionics and digital twins, characterized in that: Includes a biomimetic conical coal feeding bin (1), a longitudinal telescopic mechanism, a scaling and twisting mechanism, a spiral peristaltic mechanism, and a material monitoring and decision-making module; The biomimetic conical coal feeding bin (1) is a flexible structure made of wear-resistant rubber material, located between the upper and lower discs of the longitudinal telescopic mechanism, and can extend and retract along the axial direction of the disc under the drive of the telescopic component (2.1) of the longitudinal telescopic mechanism; the scaling and torsional mechanism is installed between the discharge end of the biomimetic conical coal feeding bin (1) and the lower disc (2.3) of the longitudinal telescopic mechanism, and the scaling and torsional mechanism is used to control the opening and closing degree and torsional angle of the discharge port of the biomimetic conical coal feeding bin (1); the spiral track (3.1) of the spiral peristaltic mechanism surrounds the biomimetic conical coal feeding bin (1). 1) The outer periphery is connected to the upper plate (2.2) of the longitudinal telescopic mechanism. The peristaltic mechanism of the spiral peristaltic mechanism can move on the spiral track (3.1) and generate a peristaltic crushing force on the bionic conical coal feeding bin (1). The material monitoring and decision module is installed on the outer surface of the bionic conical coal feeding bin (1) to monitor the strain signal of the bionic conical coal feeding bin (1) and control the longitudinal telescopic mechanism, scaling and twisting mechanism and spiral peristaltic mechanism based on the strain signal to realize the contraction, expansion, twisting, bending and peristalsis of the bionic conical coal feeding bin (1).
2. The dynamic unblocking device for coal bunkers based on bionics and digital twins according to claim 1, characterized in that: The biomimetic conical coal feeding bin (1) has internal reinforcing ribs; the diameter of the feed inlet of the biomimetic conical coal feeding bin (1) is larger than the diameter of the discharge outlet.
3. The dynamic unblocking device for coal bunkers based on bionics and digital twins according to claim 1, characterized in that: The longitudinal telescopic mechanism includes a telescopic component (2.1), an upper plate (2.2), and a lower plate (2.3). The upper plate (2.2) is fixed to the feed end of the biomimetic conical coal feeding bin (1) and has a channel at its center that matches the feed end. The telescopic component (2.1) includes multiple telescopic cylinders spaced along the outer periphery of the plate. The lower plate (2.3) is connected to the lower part of the upper plate (2.2) via telescopic cylinders and has a channel at its center that matches the discharge end.
4. The dynamic unblocking device for coal bunkers based on bionics and digital twins according to claim 1, characterized in that: Multiple scaling and torsional mechanisms are arranged at intervals along the circumference of the lower plate (2.3). The scaling and torsional mechanisms include a scaling and torsional hydraulic cylinder (4.1), a torsional motor (4.2), a torsional bracket (4.3), and a torsional sliding groove (4.4). The torsional sliding groove (4.4) is located on the circumference of a virtual circle with the center of the lower plate (2.3) as the center and with one of the radii as the radius. The torsional sliding groove (4.4) is an arc-shaped groove. The two ends of the scaling and torsional hydraulic cylinder (4.1) are rotatably connected to the discharge end of the biomimetic conical coal feeding bin (1) and the torsional bracket (4.3), respectively. The torsional bracket (4.3) is slidably arranged in the torsional sliding groove (4.4) and driven by the torsional motor (4.2). The lower end of the torsional bracket (4.3) is provided with a drive wheel connected to the output shaft of the torsional motor (4.2).
5. The dynamic unblocking device for coal bunkers based on bionics and digital twins according to claim 1, characterized in that: The spiral peristaltic mechanism includes a spiral track (3.1), a track fixing frame (3.2), and a peristaltic mechanism; the spiral track (3.1) is connected to the upper plate (2.2) of the longitudinal telescopic mechanism via the track fixing frame (3.2); the peristaltic mechanism includes a peristaltic motor (3.3), a peristaltic hydraulic cylinder (3.4), a swing arm (3.5), a peristaltic motor (3.6), a rotating triangular frame (3.7), and peristaltic wheels (3.8). The three peristaltic wheels (3.8) are rotatably connected in a triangular shape to the inner layer of the rotating triangular frame (3.7), and the swing arm... The arm (3.5) is rotatably connected between the peristaltic motor body (3.3) and the rotating tripod (3.7). The two ends of the peristaltic hydraulic cylinder (3.4) are rotatably connected to the peristaltic motor body (3.3) and the swing arm (3.5) respectively. The drive shaft of the peristaltic motor (3.6) is keyed to the central shaft of the rotating tripod (3.7). The peristaltic motor (3.6) is used to drive the rotating tripod (3.7) to rotate around its center to provide rotational force for the peristaltic wheel (3.8). The peristaltic hydraulic cylinder (3.4) is used to drive the swing arm to rotate at a small angle.
6. The dynamic unblocking device for coal bunkers based on bionics and digital twins according to claim 1, characterized in that: The material monitoring and decision-making module includes strain gauges (5) and a digital twin control module. Multiple strain gauges (5) are evenly and layered along the circumference of the bionic conical coal feeding bin (1). The digital twin control module controls the longitudinal telescopic mechanism, scaling and torsional mechanism, and spiral peristaltic mechanism based on the strain signals collected by the strain gauges (5) at the bionic conical coal feeding bin (1).
7. A dynamic coal bunker unblocking method based on bionics and digital twins, implemented using the dynamic coal bunker unblocking device based on bionics and digital twins as described in any one of claims 1 to 6, characterized in that... Includes the following steps: Based on multibody system dynamics-discrete element software, a rigid-flexible-discrete coupling model of the dynamic unblocking device is established, and the dynamic unblocking of coal bunkers is simulated. Using the motion state of coal particles during the simulation process as input, and the total strain value of the corresponding biomimetic conical coal feeding bin as the target, a convolutional neural network is used for fitting to obtain the correspondence between the strain value and the internal coal particles. Based on the strain value, it is determined whether there is a fault condition such as coal blockage or coal powder adhesion inside, as well as the motion state of coal particles inside under normal working conditions, thus completing the establishment of a digital twin system. In the digital twin system, a deep reinforcement learning algorithm is used to control the longitudinal stretching system, scaling and twisting system, and spiral peristalsis system to cooperate in completing the biomimetic movements of contraction, expansion, twisting, bending and peristalsis. The optimal movement is determined by training with the strain values corresponding to the smooth discharge of coal particles inside the system and the smooth discharge of coal particles after peristalsis after coal blockage. The real-time strain values of strain gauges at the biomimetic conical coal feeding bunker are obtained and input into the digital twin system. The digital twin system monitors the motion state of coal particles in the current biomimetic conical coal feeding bunker in real time and decides the optimal motion state to feed back to the longitudinal extension system, scaling and torsional system, and spiral peristalsis system in the real world for action.
8. A dynamic unblocking method for coal bunkers based on bionics and digital twins according to claim 7, characterized in that: In the rigid-flexible-dispersive coupling model of the dynamic unblocking device, the biomimetic conical coal discharge bunker (1) is constructed as a flexible body, while the longitudinal telescopic mechanism, scaling and torsional mechanism, spiral creep mechanism and strain gauge (5) are rigid bodies. The discrete element method is used to restore the real shape and material properties of the coal block, simulate the situations of coal blockage, smooth coal discharge, smooth coal discharge after creep after coal blockage, and smooth coal discharge after creep after coal blockage, and the inability to discharge coal smoothly after creep. Simulation analysis is performed, and the strain value under each simulation is recorded.
9. A dynamic unblocking method for coal bunkers based on bionics and digital twins according to claim 8, characterized in that: Based on the original diameter D of the outlet of the flexible biomimetic conical coal bunker, the diameter of the coal particles is set to be less than or equal to the original diameter D, and the shape of the coal particles is randomly generated according to the actual situation. Simulations were conducted to obtain strain values under different working conditions: smooth coal discharge, coal blockage, smooth coal discharge after coal blockage and subsequent creep, and failure to discharge coal smoothly after coal blockage and subsequent creep. A convolutional neural network was used for fitting to obtain the nonlinear relationship between the strain value and the internal coal particles.
10. A dynamic unblocking method for coal bunkers based on bionics and digital twins according to claim 7, characterized in that: The digital twin system reassesses the monitored state every 0.5 seconds to adjust the action strategy in real time. The deep reinforcement learning algorithm is the Deep Deterministic Policy Gradient algorithm.
Citation Information
Patent Citations
Stifled device is prevented to visual former coal bunker
CN208683557U
Powder blanking device
CN210365238U
