Bridge type ship unloader control method and related equipment

Abstract

The invention provides a bridge type ship unloader control method and related equipment, which can effectively cover the sensing requirement of a load operation scene and improve the control precision of unloading at the same time. The method comprises the steps that when a starting instruction is received, a cart corresponding to the bridge type ship unloader is controlled to run to a preset scanning area, and parameters of all sensors corresponding to a bridge type ship unloader system are initialized; original data of each sensor in all the sensors are collected in real time, the original data are preprocessed through a pre-trained perception model to obtain a structured data packet, and the original data comprise color texture information, 3D point cloud distance information and obstacle information; the structured data packet comprises semantic information and confidence; determining a control instruction sequence of the grab bucket of the bridge type ship unloader in the current period according to the structured data packet; and controlling the grab bucket of the bridge type ship unloader to operate in the current period according to the control instruction sequence.

Description

Technical Field

[0001] This invention relates to the field of ship unloading technology, and in particular to a control method and related equipment for a bridge-type ship unloader. Background Technology

[0002] Bridge unloader control refers to the process of manually operating or using automated programs to manage the coordinated operation of the core mechanisms of the unloader, completing the operation of grabbing bulk cargo from the ship's hold and transferring it to the shore conveyor. When combined with artificial intelligence perception technology, it can give the machine the ability to autonomously perceive and make decisions, aiming to build an efficient and intelligent modern port operation system.

[0003] The current bridge unloader control system ensures that multiple bridge cranes exchange and share data with the central computing control unit while also enabling data exchange and sharing among the multiple bridge cranes. This ensures that multiple bridge cranes can obtain each other's working status in real time during the unloading process and independently complete their work under the coordination of the central computing control unit. Throughout the process, it ensures the stability of the center of gravity of the unloaded ship and ensures the safety of the unloaded ship. Based on the collaborative operation of multiple bridge cranes, the unloading efficiency is effectively improved. However, the decision-making logic of the bridge ship unloader control system is based on a fixed unloading configuration, lacks the ability to adapt to complex dynamic environments, and the execution module operates according to the unloading configuration, resulting in low control accuracy. Summary of the Invention

[0004] This invention provides a control method and related equipment for a bridge-type ship unloader, which can effectively cover the perception requirements of load operation scenarios and improve the control accuracy of unloading.

[0005] The first aspect of this invention provides a control method for a bridge-type ship unloader, comprising: When a start command is received, the trolley corresponding to the bridge ship unloader is controlled to move to the predetermined scanning area, and the parameters of all sensors corresponding to the bridge ship unloader system are initialized. The system collects raw data from each of the sensors in real time and preprocesses the raw data using a pre-trained perception model to obtain a structured data packet. The raw data includes color and texture information, 3D point cloud distance information, and obstacle information. The structured data packet includes semantic information and confidence level. The control command sequence for the grab bucket of the bridge unloader in the current cycle is determined based on the structured data packet. The grab bucket of the bridge unloader is controlled to operate within the current cycle according to the control command sequence.

[0006] A second aspect of the present invention provides a control device for a bridge-type ship unloader, applied to a bridge-type ship unloader system, comprising: The initialization module is used to control the trolley corresponding to the bridge ship unloader to run to the predetermined scanning area when a start command is received, and to initialize the parameters of all sensors corresponding to the bridge ship unloader system. The preprocessing module is used to collect raw data from each of the sensors in real time and preprocess the raw data through a pre-trained perception model to obtain a structured data packet. The raw data includes color texture information, 3D point cloud distance information and obstacle information. The structured data packet includes semantic information and confidence level. The determination module is used to determine the control command sequence of the grab bucket of the bridge unloader in the current cycle based on the structured data packet; The operation module is used to control the grab bucket of the bridge unloader to operate within the current cycle according to the control command sequence.

[0007] In one possible design, the determining module is specifically used for: Extract the target coordinates from the structured data packet and convert the target coordinates into the local coordinate system of the bridge unloader; The grasping strategy for the current period is determined based on the structured data packet, and the grasping data of the grab bucket is calculated, including the opening angle and the expected closing torque threshold. The grabbing point is determined based on the grabbing strategy and the target coordinates; Construct an aerial trajectory between the grab point and the current position of the grab bucket, the aerial trajectory avoiding the bulkheads and static obstacles of the target cargo ship; The aerial trajectory is subjected to anti-sway processing to generate an anti-sway trajectory, which is a curve with a specific acceleration; When the anti-shake trajectory is verified, the verified anti-shake trajectory is decomposed into the control command sequence.

[0008] In one possible design, the determining module is further configured to: As the grab moves according to the sequence of control commands, the actual position and swing state of the grab are acquired in real time. When an abnormal situation exists, the instruction sequence following the abnormal moment in the control instruction sequence is compensated; When the grab bucket completes the sequence of control commands, the grab bucket's digging data is recorded, including the actual full bucket rate, energy consumption, and duration. Based on the mining data, adjust the grasping strategy and anti-shake parameters for subsequent mining cycles after the current mining cycle.

[0009] In one possible design, the running module is specifically used for: The control command sequence is parsed to determine the target point coordinates; Calculate the distance difference between the current position of the grab and the coordinates of the target point; The distance difference is converted into a real-time changing speed setpoint and direction signal; The grab bucket is controlled to operate according to the speed setpoint and the direction signal; During the movement of the grab bucket, the real-time actual position of the grab bucket is calculated, and the real-time actual position is compared with the coordinates of the target point to obtain the target deviation; The speed setpoint and the direction signal are adjusted according to the target deviation, and the grab bucket is controlled to run based on the adjusted speed setpoint and the direction signal until the grab bucket reaches the target point coordinates.

[0010] In one possible design, the operating module is further configured to: When the structured data packet includes alarm information, the alarm information is synchronously responded to in each of the multiple interfaces, and the multiple interfaces are associated with the bridge unloader system. Based on the user's operation instructions for synchronizing the corresponding alarm information, and based on the operation instructions, decision information is generated; The alarm information, the operation instructions, and the decision information are stored together and the perception model is updated and trained using the alarm information, the operation instructions, and the decision information.

[0011] In one possible design, the operating module is further configured to: When a target event that triggers an early warning is detected, it is determined whether the target event meets the first preset condition and does not meet the second preset condition; When the target event meets the first preset condition but does not meet the second preset condition, an early warning message is issued; Determine whether the target event satisfies the second preset condition and does not satisfy the third preset condition; When the target event satisfies the second preset condition but does not satisfy the third preset condition, the target component corresponding to the target event is adaptively adjusted. Determine whether the target event satisfies the third preset condition; When the target event meets the third preset condition, the power supply to the target component is disconnected, a fault alarm is sent with the highest priority, and a log is recorded so that maintenance personnel can perform fault maintenance based on the recorded log.

[0012] In one possible design, the operating module is further configured to: A graphical human-machine interface is provided, which displays a dynamic picture of the overall structure of the bridge ship unloader and its working environment. Generate a real-time data dashboard, which displays the performance indicators of the bridge ship unloader in the form of charts, dashboards and numbers; A virtual unloader model corresponding to the bridge-type ship unloader is constructed, and the device parameter viewing and operation permissions of the bridge-type ship unloader are set for users with different permissions.

[0013] A third aspect of the present invention provides an electronic device, including a memory and a processor, wherein the processor is configured to execute a computer management program stored in the memory to implement the steps of the bridge unloader control method as described in any of the preceding aspects.

[0014] A fourth aspect of the present invention provides a computer-readable storage medium having a computer management program stored thereon, which, when executed by a processor, implements the steps of controlling a bridge unloader as described in any of the preceding aspects.

[0015] In summary, it can be seen that in the embodiments provided by the present invention, the raw data of each sensor in all sensors is collected in real time and the corresponding structured data package is generated. This can accurately identify ship hatches, material shapes and dynamic obstacles, thereby effectively covering the perception needs of complex operation scenarios. Then, based on the structured data package, the control command sequence of the grab bucket in the current cycle is determined, and the grab bucket is controlled to operate in the current cycle based on the control command sequence. This allows for periodic control of the grab bucket and improves control accuracy. Attached Figure Description

[0016] Figure 1 The system architecture diagram of the bridge-type ship unloader control system provided in the embodiments of the present invention; Figure 2 A schematic flowchart of the bridge unloader control method provided in an embodiment of the present invention; Figure 3 This is a virtual structural diagram of the bridge-type ship unloader control device provided in an embodiment of the present invention; Figure 4 A schematic diagram of the hardware structure of the bridge-type ship unloader control device provided in an embodiment of the present invention; Figure 5 A schematic diagram of an embodiment of the electronic device provided in this invention; Figure 6 A schematic diagram illustrating an embodiment of a computer-readable storage medium provided in this invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below 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 embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] In the following description, specific embodiments of the invention will be illustrated with reference to steps and symbols performed by one or more computers, unless otherwise stated. Therefore, these steps and operations will be referred to several times as being performed by a computer, and computer execution as referred to herein includes operations by a computer processing unit representing electronic signals of data in a structured format. This operation transforms the data or maintains it at a location in the computer's memory system, which can be reconfigured or otherwise alter the operation of the computer in a manner well known to those skilled in the art. The data structure maintained by the data is the physical location of the memory, which has specific characteristics defined by the data format. However, the principles of the invention described above are not intended to be limiting, and those skilled in the art will understand that many of the steps and operations described below can also be implemented in hardware.

[0019] The principles of this invention are applied using many other general-purpose or purpose-specific computing, communication environments, or configurations. Examples of well-known computing systems, environments, and configurations suitable for use with this invention include (but are not limited to) handheld phones, personal computers, servers, multiprocessor systems, microcomputer-based systems, mainframe computers, and distributed computing environments, including any of the aforementioned systems or devices.

[0020] The terms "first," "second," and "third," etc., used in this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0021] Please see Figure 1 , Figure 1 This is a system architecture diagram of a bridge-type ship unloader control system provided in an embodiment of the present invention. The bridge-type ship unloader control system includes basic equipment 10 consisting of a ship unloader unit and ship hatches, and hardware and software system facilities 20. The hardware and software system facilities 20 include a multimodal perception layer 20A, a decision analysis layer 20B, a drive execution layer 20C, a human-computer interaction and monitoring platform 20D, and a safety management layer 20E, wherein: The multimodal perception layer 20A is used to comprehensively perceive the working environment and identify and detect targets and obstacles, transforming raw sensor data into structured information to provide a data foundation for the decision analysis layer 20B. The decision analysis layer 20B is used to comprehensively analyze the received perception information, realize planning and decision-making, and generate motion command output; The driver execution layer 20C receives motion commands and converts them into physical action operations to achieve motion control and execution response; The 20D Human-Computer Interaction and Monitoring Platform provides a comprehensive display of system status and an operation interface, enabling supervision and control of decision-making commands. The 20E safety management layer operates in parallel with system control operations to ensure that safety actions are enforced under any abnormal circumstances.

[0022] For ease of understanding, the various components of the hardware and software system facility 200 are described in detail below: The multimodal perception layer 20A includes a hardware sensor cluster and an edge gateway deployed on the basic equipment. The hardware sensor cluster includes an optical vision unit, a radar perception unit, an attitude positioning unit, and a computing hardware platform. The optical vision unit includes an overhead camera installed at the highest point of the unloader gantry, used to collect a global view of the hatch and to perform preliminary positioning of the ship and the hatch. The optical vision unit includes a zoom camera mounted on the ship unloader trolley, which is equipped with a gimbal and a telephoto lens to identify material details, grab bucket status and obstacles; the optical vision unit also includes a pair of stereo binocular cameras mounted on the ship unloader trolley and grab bucket to calculate depth information based on parallax. The radar sensing unit includes a main lidar installed below the main beam of the ship unloader, which generates an overall point cloud map of the material surface based on the hatch scanning image; the radar sensing unit also includes auxiliary lidars installed on the bottom of the ship unloader trolley and on the grab bucket, which detect obstacles in a small area of ​​the grab bucket; the radar sensing unit also includes a millimeter-wave radar set close to the optical vision unit, which detects large obstacles. The attitude positioning unit includes a GNSS-RTK receiver and an inertial detection unit. The GNSS-RTK receiver provides absolute geographic coordinates for positioning, while the inertial detection unit is installed on the bottom of the unloader trolley and on the grab bucket to monitor the acceleration and angular velocity data of the grab bucket.

[0023] The computing hardware platform includes an edge computing industrial control computer installed inside the electrical room. The edge computing industrial control computer is equipped with a GPU server to realize sensor data processing, analysis and inference. The edge gateway is equipped with a sensor driver module and a sensor synchronization module. The sensor driver module controls the sensor cluster, and the sensor synchronization module provides a unified timestamp to achieve time and space alignment of the sensing data from different sensors. The edge gateway also preprocesses the raw data from the sensor cluster and has a communication protocol stack deployed to transmit the processed sensor data to the decision analysis layer. A model library is deployed on the edge gateway, which includes object detection models, semantic segmentation models, 3D reconstruction algorithms, and multi-sensor fusion algorithms. The object detection model identifies parameters such as ships, hatches, personnel, and vehicles. The semantic segmentation model accurately segments material areas and obstacle areas. The 3D reconstruction algorithm generates high-precision 3D maps from images and point clouds. The multi-sensor fusion algorithm achieves multi-source data fusion.

[0024] The decision analysis layer 20B includes a motion planner, an anti-sway and anti-sway controller, and a grabbing strategy optimizer. The motion planner calculates the optimal spatial trajectory of the grab bucket from its current position to the target position based on a fast exploration random tree algorithm. The anti-sway and anti-sway controller actively suppresses and eliminates the swaying amplitude generated by the grab bucket's operation based on a specific speed curve. The grabbing strategy optimizer optimizes and adjusts the optimal cutting angle, depth, and speed of the grab bucket based on the material type and the current stockpile shape to maximize the full bucket rate. The decision analysis layer 20B also includes a central decision unit, a task scheduler, and a digital twin engine. The central decision unit is an industrial server used to run the processing algorithms of the motion planner, anti-sway controller, and grasping strategy optimizer, and to generate decision information. The task scheduler generates control commands based on the decision information and distributes them to the motion planner, anti-sway controller, and grasping strategy optimizer for response and processing. A virtual model of the ship unloader is built in the digital twin engine to realize virtual space simulation testing.

[0025] The drive execution layer 20C includes a PLC logic controller, a frequency converter driver, a motor actuator and brake, a transmission mechanism, and a basic sensing module. The PLC logic controller receives control commands from the decision analysis layer 20B and performs logic processing. According to the commands, it outputs control signals to the frequency converter driver, including analog voltage and digital pulses. The frequency converter driver is installed at each motion axis of the unloading unit. According to the received PLC control signals, it adjusts the frequency and amplitude of the output current to control the motor speed and torque. The motor actuator and brake include a three-phase asynchronous motor and a disc brake. The disc brake is installed on the motor shaft of the three-phase asynchronous motor to realize circuit on / off control. The transmission mechanism includes wire ropes, drums and pulley blocks to realize lifting and opening / closing actions, as well as gears, couplings and travel wheels to realize vehicle body movement. The basic sensing module includes rotary encoders, absolute encoders, load cells, limit switches and proximity switches.

[0026] The 20D human-computer interaction and monitoring platform includes monitoring hardware facilities and interactive software facilities. The monitoring hardware facilities include a central monitoring station, which is equipped with an operation terminal module and a remote terminal module that is connected to the central monitoring station through a monitoring network. The central monitoring station includes an industrial computer and a multi-monitor array. The industrial computer runs monitoring software and graphics processing software, and displays monitoring data, including panoramic video, 3D models, data reports and alarm information, through the monitor screens in a split-screen manner. The operation terminal module includes a touch panel, joystick, and button station for local mode switching and emergency operation; the remote terminal module includes a management workstation and a mobile device connected to the management workstation, which remotely monitors the operation status of the dock unloader according to the software on the mobile device. The operation terminal module and the remote terminal module are equipped with a network camera and microphone assembly, as well as an alarm device. The interactive software infrastructure includes system monitoring software, a data and model visualization module, and a user management module. The system monitoring software provides a graphical human-machine interface for displaying dynamic images of the unloader as a whole and its working environment. The data and model visualization module includes a real-time data dashboard and a twin model platform. The real-time data dashboard displays performance indicators in the form of charts, dashboards, and numbers. The twin model platform displays a virtual unloader model built based on 3D development tools. The user management module sets the viewing and operation permissions for equipment parameter data according to different user permissions.

[0027] The safety management layer 20E includes a safety monitoring module and a safety control module. The safety monitoring module includes hard limit switches installed at the travel limit positions of the motion mechanism, emergency stop devices at key positions of the whole machine and along the track, real-time monitoring of ambient wind speed based on an anemometer, issuing an alarm and restricting operation when the wind speed exceeds the safety threshold, and over-height and over-weight limiters installed on the hoisting mechanism. The safety control module includes a safety contactor, a safety brake, and an audible and visual alarm. The safety contactor is controlled by a relay to cut off the power supply to the motor, and the safety brake is used for power failure braking control.

[0028] In summary, the AI-based bridge unloader control system provided by this invention constructs a hardware sensor cluster including optical vision units, radar sensing units, and attitude positioning units. Combined with an AI model library at the edge gateway and multi-sensor fusion algorithms, it accurately identifies ship hatches, material shapes, and dynamic obstacles, effectively covering the perception needs of complex operational scenarios. By dynamically generating and adjusting strategies based on machine learning and strategy optimization, it improves operational adaptability. Then, based on a motion planner and digital twin engine, it simulates and verifies the safety and efficiency of the operating trajectory. The task scheduler coordinates various modules to achieve refined decision-making and execution control, reducing on-site operational risks. Through multi-dimensional safety monitoring and graded response, it ensures equipment and operational safety. Combined with a human-machine interaction mechanism and high visualization, it allows for rapid recovery of operations through remote monitoring and local quick operation, improving operational efficiency.

[0029] The following description explains the bridge-type ship unloader control method provided by this invention from the perspective of the bridge-type ship unloader control device. Please refer to [link / reference]. Figure 2 , Figure 2 A flowchart illustrating the bridge unloader control method provided by the present invention includes: 201. When a start command is received, the trolley corresponding to the bridge ship unloader is controlled to move to the predetermined scanning area, and the parameters of all sensors corresponding to the bridge ship unloader system are initialized.

[0030] In this embodiment, when the bridge ship unloader system is started or a new ship docks at the pier, the operator can click "Start Scan" on the corresponding monitoring platform. The bridge ship unloader control device controls the trolley corresponding to the bridge ship unloader to move to the predetermined scanning area and initializes the parameters of all sensors corresponding to the bridge ship unloader system. Figure 1 The hardware sensor cluster in the middle has been described in detail, and will not be repeated here.

[0031] During unloading operations, the trolley and auxiliary trolley of a bridge-type ship unloader work in tandem. Typically, the trolley first moves to the approximate location of a hold and secures itself. Then, the auxiliary trolley performs high-frequency reciprocating motions at this location to empty the hold of material. After completion, the trolley moves to the next hold, and the auxiliary trolley continues its work.

[0032] 202. Collect raw data from each sensor in real time and preprocess the raw data using a pre-trained perception model to obtain structured data packets.

[0033] In this embodiment, all sensors are triggered according to a unified hardware clock. The bridge unloader control device can collect the raw data of each sensor in real time, that is, synchronously collect one frame of data from each sensor, and synchronously record the precise position and attitude of the body through GNSS and IMU. The raw data includes color and texture information of camera images, precise 3D point cloud distance information of lidar, and obstacle information of millimeter-wave radar. Then, the color and texture information of the camera image, the precise 3D point cloud distance information of the lidar, and the obstacle information of the millimeter-wave radar are aligned and fused to generate a high-confidence fusion perception result with semantic information. The fusion perception result is then used for data inference through a pre-trained perception model to obtain a structured data package. For example, the structured data package could be: "The ship is a Panamax bulk carrier with 5 hatches. The center coordinates of hatch 1 are (X, Y, Z), and the dimensions are length A meters x width B meters. The material in hatch 1 is iron ore. The current stockpile is peaked, and the highest point coordinates are (X1, Y1, Z1). The estimated remaining volume is 1500 cubic meters. A human-shaped obstacle has been detected to the left rear of the hatch, with a confidence level of 95%."

[0034] 203. Determine the control command sequence of the grab bucket of the bridge unloader in the current cycle based on the structured data packet.

[0035] In this embodiment, after determining the structured data packet, the bridge unloader control device can determine the control command sequence of the bridge unloader's grab bucket in the current cycle based on the structured data packet. The following is a detailed explanation of how to generate the control command sequence in the current cycle: Extract the target coordinates from the structured data packet and convert the target coordinates into the local coordinate system of the bridge ship unloader; The grabbing strategy for the current period is determined based on the structured data packet, and the grabbing data of the grab bucket is calculated, including the opening angle and the expected closing torque threshold. Determine the grab point based on the grabbing strategy and target coordinates; Construct an aerial trajectory between the grab point and the current position of the grab bucket, and the aerial trajectory avoids the bulkheads and static obstacles of the target cargo ship; Anti-sway processing is applied to the aerial trajectory to generate an anti-sway trajectory, which is a curve with a specific acceleration. When the anti-shake trajectory verification is successful, the verified anti-shake trajectory is decomposed into the control command sequence.

[0036] To facilitate understanding, the following example, using the grab bucket of a bridge unloader performing a single grab, will be used to explain in detail how to generate a sequence of control commands: The bridge unloader control unit receives the processed structured data packet, which can be, for example, "The remaining iron ore in hold 1 is in a sloping shape, with the highest point coordinates P1(X1, Y1, Z1) (i.e., the target coordinates), with no dynamic obstacles, and the grab bucket is currently in the Home position." The motion planner is invoked to transform P1 to the local coordinate system of the bridge unloader, and the grab strategy optimizer is invoked to analyze the sloping iron ore corresponding to the target cargo ship, determine that the grab strategy to be adopted is the sloping cut-in strategy from the top of the slope, and calculate the grab bucket's grab data, which includes the opening angle and the expected closing torque threshold. Call the task scheduler to confirm that the current target is still cabin 1. Select a specific grab point P near the highest point P1 through the grab strategy optimizer. Calculate the air trajectory T from the current position of the grab bucket to point P. This trajectory must avoid the cabin wall and any static obstacles. The anti-sway and anti-sway controller processes the aerial trajectory T to generate an anti-sway trajectory T' with a specific acceleration curve. This anti-sway trajectory T' allows the trolley and lifting mechanism of the bridge ship unloader to move in coordination, ensuring that the grab bucket moves smoothly and swings to the minimum when it reaches the grab point P. The execution trajectory T' is quickly simulated in the virtual model through the digital twin engine to ensure no collisions and optimal efficiency. The anti-sway trajectory T' is verified, and after successful verification, the anti-sway trajectory T' is decomposed into a series of continuous, timestamped control commands, which is the control command sequence, such as "at time t1, the speed of the trolley increases to x m / s²", and finally sent to the drive execution layer through the industrial network to control the grab bucket to run according to the control command sequence.

[0037] It should be noted that during the movement of the grab bucket, the bridge-type ship unloader control device continuously monitors the actual position and swing state of the grab bucket. If there are abnormal situations (such as unexpected strong winds or swinging), the bridge-type ship unloader control device can compensate for the command sequence after the abnormal moment in the control command sequence; and control the grab bucket based on the compensated commands; at the same time, after the grab bucket cuts into the material of the target cargo ship, it can also obtain the change of motor current (torque) in real time to determine whether the grab bucket is full and decide the lifting timing.

[0038] It should also be noted that after the grab bucket completes a grab, the actual full bucket rate, energy consumption, time and other data of this grab are recorded, and this data is analyzed to continuously optimize the grab strategy and anti-shake parameters.

[0039] It should also be noted that when the grab bucket encounters a hard, compacted layer while grabbing iron ore, it cuts in with normal force, but the data from the drive system shows that "the hoisting motor current is not over-limit, but the trolley translation motor current is abnormally high." This means that the grab bucket cannot "bite" the material in front of it. Based on the feedback data, the current situation is determined to be: excessive grabbing resistance, possibly due to encountering a compacted layer; and the corresponding handling solution is determined as follows: Option A: Increase the intensity, but this will greatly increase energy consumption and equipment wear and tear, and may even damage the hull.

[0040] Option B: Avoid and learn. Based on the priority principle of "protecting the device", the grab strategy optimizer immediately generates a new strategy, such as and issues a command to immediately release the grab and abandon this grab.

[0041] Next, the motion planner is invoked to plan a short path to the target, allowing the grab to move to an adjacent, seemingly looser area. The task scheduler marks this congested area as an "ungrabable zone" on the internal map. Then, a new control command sequence is generated based on the method described above, and the grab is moved to the new position for normal grabbing based on this new control command sequence. The coordinates of failed grabbing points and sensor data are recorded for later analysis. If the same situation is encountered multiple times, a new grabbing pattern will be learned and recorded.

[0042] 204. Control the grab bucket of the bridge unloader to operate within the current cycle according to the control command sequence.

[0043] In this embodiment, after determining the control command sequence, the bridge unloader control device can control the grab bucket of the bridge unloader to operate within the current cycle according to the control command sequence. The current cycle includes, but is not limited to, the grab bucket's movement cycle and the grab bucket's digging cycle, which will be described in detail below: The control command sequence is parsed to determine the coordinates of the target point; Calculate the distance difference between the current position of the grab and the coordinates of the target point; The distance difference is converted into a real-time changing speed setpoint and direction signal; The grab bucket is controlled to operate based on the speed setpoint and direction signal; During the movement of the grab bucket, the real-time actual position of the grab bucket is calculated, and the real-time actual position is compared with the coordinates of the target point to obtain the target deviation; Adjust the speed setpoint and the direction signal according to the target deviation, and control the operation of the grab bucket based on the adjusted speed setpoint and the direction signal until the grab bucket reaches the target point coordinates.

[0044] To make it easier to understand, the following explanation uses the current cycle as the movement cycle of the grab (that is, the grab moving from its current position to the target point) as an example: The decision-making system sends a command to the PLC via industrial Ethernet: "Move the center point of the grab bucket to the absolute coordinates P(X, Y, Z) at an S-shaped speed curve". After receiving this high-level instruction, the PLC parses it using its internal program (usually written in structured text ST or function block diagram FBD). Based on the current position of the grab bucket fed back by the encoder, the PLC calculates the distance difference to the target point coordinate P. Based on the S-shaped speed curve (including acceleration, constant speed, and deceleration), the PLC converts this distance difference into a real-time changing speed setpoint and direction signal. This speed setpoint is usually sent to the frequency converters of the three axes as an analog voltage or via fieldbus messages. The trolley, the hoisting frequency converter, and the crane receive instructions from the PLC. Each frequency converter adjusts the frequency and voltage of the current output to the motor to precisely control the speed and direction of the corresponding motor. The rotation of the motor is ultimately converted into the actual movement of the grab bucket in three-dimensional space through the transmission mechanism such as the gearbox, drum, and wire rope. The rotary encoder installed on the motor feeds back the actual speed and number of revolutions of the motor to the frequency converter and PLC in real time. The frequency converter uses feedback to form a closed loop to ensure that the motor speed can accurately follow the set value of the PLC. The PLC uses this feedback to calculate the real-time actual position of the grab bucket and continuously compares this real-time actual position with the target point coordinates P. Based on the deviation between the two, the PLC continuously adjusts the speed command sent to the frequency converter. Specifically, the speed increases when the deviation is large and decreases when the deviation is small, until the deviation is zero. When the PLC detects that the deviation between the actual position of the grab bucket and the target position P has entered a very small error range (such as ±2mm), the PLC determines that "positioning is complete". The PLC immediately reduces the speed command to zero and sends a "brake" signal to the frequency converter. The frequency converter stops outputting, the motor brakes and holds the brake, and the grab bucket stops stably at the target point P. Finally, the PLC sends a feedback message "positioning command completed".

[0045] The following example illustrates the scenario where a grab bucket moves from its current position (point A) to a target point (point B) above the material pile inside the hold, ready to grab material: The control command sequence is translated into "Move to target point B, using an S-shaped velocity curve, with the maximum speed not exceeding 80% of the rated speed", and then sent to the execution control layer. The PLC reads the encoder and decodes the control command sequence to determine the coordinates of the current position A of the grab bucket as (Xa, Ya, Za). After calculating the vector, it decomposes the S-shaped speed curve into synchronous speed commands on three axes (X-trolley, Y-carriage, Z-lifting). For example, for the trolley mechanism: "Accelerate to 80% of the rated speed within 3 seconds, run at a constant speed, and then start decelerating when there are 2 meters left to reach point B, and finally reach the target point at 0 speed." The PLC sends a voltage signal to the trolley inverter via the analog output module. The voltage signal gradually rises from 0V to the set voltage value and then falls back to 0V. The trolley inverter receives the changing voltage signal and converts it into AC power that varies from 0Hz to 40Hz. The trolley motor then starts to rotate smoothly and drives the wheels through the gearbox, causing the trolley to move towards the target point B.

[0046] The encoder installed on the motor provides real-time feedback that "the current speed is 35Hz and it has rotated 1500 times." The frequency converter detects that the speed setting is 40Hz, but the actual speed is 35Hz. It then fine-tunes the output voltage to make the speed catch up with the set value more quickly. The PLC calculates the actual position of the trolley, Ycurrent, based on the number of revolutions fed back by the encoder, and compares it with the target position, Yb. It finds that the trolley is moving slower than the expected trajectory, so it increases the analog voltage value sent to the frequency converter to compensate. When the PLC calculates that the trolley is 0.1 meters away from the target point, the voltage signal it sends to the frequency converter has dropped very low, and the motor runs at low speed. When the deviation is less than 2mm, the PLC sends a 0V signal and issues a brake command. The frequency converter stops outputting, the motor is locked by the brake pads, the trolley stops at point B, and the grab bucket is suspended in the air with almost no swing. Finally, the PLC sends a completion signal, and the bridge unloader control device can issue the next instruction to execute the grabbing.

[0047] In one embodiment, the bridge unloader control device also performs the following operations while controlling the movement of the grab bucket: When the structured data packet includes alarm information, the alarm information will be synchronously responded to on each of the multiple interfaces, and the multiple interfaces are associated with the bridge unloader system. Based on the user's operation instructions for synchronizing the corresponding alarm information, and based on the operation instructions, decision information is generated; Alarm information, operation instructions, and decision information are stored together and the perception model is updated and trained using these information.

[0048] This section uses the example of an operator handling an unidentified obstacle to illustrate the processing of alarm information during grab bucket operation: During the operation of the grab bucket by the bridge-type ship unloader control device, a protrusion covered by a tarpaulin inside the target cargo ship's hold (which was not previously identified as an obstacle) was moved by the wind and entered the LiDAR scanning area. It was identified as a dynamic obstacle by the perception system, and the corresponding perception data was collected by the sensors. The perception data was preprocessed to obtain a structured data packet, which contained alarm information. The alarm information could be "Warning! A moving unknown object was detected at coordinates (X, Y) in hold 1, with a confidence level of 75%. It is recommended to pause." The bridge unloader control device determines the control command based on the structured data packet, such as the command "pause the current action and keep all mechanisms in the current state", and issues the command; at the same time, it sends the alarm information to the monitoring platform, sends a highest level alarm message through protocols such as OPCUA and MQTT, and attaches the coordinates, type, screenshot and LiDAR point cloud data of the obstacle; After determining the alarm information, the bridge-type ship unloader control device can synchronously respond to the alarm information on each of multiple interfaces, including: Alarm list: A red highlighted alarm record appears, accompanied by a rapid alarm sound; Twin model platform: Automatically switches the view to cabin 1 and generates a bright, flashing red cube at the obstacle location for a direct warning; Video window: Automatically pops up a video feed from the camera mounted on the mast, pointing directly at Cabin 1; Real-time data dashboard: The current status has changed from "Auto Run" to "Auto Pause - Waiting for Processing"; Meanwhile, based on the alarm information, the operator observes the position of the obstacle from various angles in the 3D model to determine whether it is on the movement path of the grab bucket. Then, switching to the real-time video and zooming in, the operator discovers that it is a tarpaulin being blown by the wind, rather than a hard obstacle. At this point, the operator makes a decision: this object does not require stopping the entire machine's operation, but it must be avoided. Through touch screen operation, the operator draws an ignore zone in the obstacle area of ​​the digital twin model and selects to continue operation; and issues the corresponding operation command. The bridge-type ship unloader control device generates corresponding decision information based on the operator's operation instructions ("Set an ignore zone in the coordinate (X, Y) area and resume automatic operation"). This decision information may include updating the environmental map inside the target cargo ship, marking the area as passable, replanning a grab path around the area, and finally generating an alarm cancellation instruction ("Alarm cancelled, continue to execute the unfinished grab task according to the new path"). Finally, the event data and process (including object images, point cloud features, and operator decision instructions) corresponding to the alarm event are associated and stored in the database for continuous training of the perception model. When encountering the same or similar situations, the model can be directly identified and classified as low-risk and negligible objects, reducing unnecessary downtime.

[0049] In one embodiment, the bridge unloader control device also performs the following operations while controlling the operation of the grab bucket: When a target event that triggers an early warning is detected, it is determined whether the target event meets the first preset condition and does not meet the second preset condition; When the target event meets the first preset condition but does not meet the second preset condition, an early warning message is issued; Determine whether the target event satisfies the second preset condition and does not satisfy the third preset condition; When the target event satisfies the second preset condition but does not satisfy the third preset condition, the target component corresponding to the target event is adaptively adjusted. Determine whether the target event satisfies the third preset condition; When the target event meets the third preset condition, the power supply to the target component is disconnected, a fault alarm is sent with the highest priority, and a log is recorded so that maintenance personnel can perform fault maintenance based on the recorded log. In this embodiment, taking motor overheating as an example, the safety management during the operation of the grab bucket is described in detail: The bridge unloader control device collects temperature data in real time from the PT100 temperature sensor installed on the hoisting motor windings and transmits the signal to the safety PLC module through the safety analog module. The safety PLC module presets multiple safety thresholds and response strategies to determine whether the collected temperature data reaches the threshold for triggering an early warning (monitoring motor temperature > 65°C). If so, it determines that a target event that triggers an early warning has been detected and determines whether the target event meets the first preset condition (the first preset condition is a continuous rise in temperature). However, if it does not meet the second preset condition (for example, the current dimension of the second preset condition is 80 degrees), an early warning message is issued, indicating that the motor temperature is too high. The motor temperature is monitored in real time, and it is determined whether the detected motor temperature meets the second preset condition. However, if it does not meet the third preset condition (the third preset condition is the temperature at which the machine must be stopped immediately, such as 95°C), adaptive adjustments are made to the target component corresponding to the target event. For example, a "degradation" command is sent to the main control system through a safety protocol. Upon receiving the command, the main system will immediately limit the output power (torque) of the motor, reduce its workload, and slow it down so that the temperature will no longer rise.

[0050] The system continuously monitors the motor temperature and determines whether it meets the third preset condition (temperature reaches the dangerous limit >95°C, continued heating may burn out the motor). If so, it disconnects the safety contactor controlling the motor, forcibly cuts off the power, and simultaneously triggers the mechanical brake to lock the grab bucket in its current position. The status icon of the corresponding motor on the monitoring platform turns red and emits a rapid alarm sound. At the same time, it sends a fault alarm to the monitoring platform with the highest priority and records it in the event log. When the operator sees the alarm on the monitoring platform, they notify the maintenance personnel, who then conduct on-site troubleshooting, locate the fault, and repair it. After the fault is resolved, a manual reset operation must be performed on the on-site control box for the safety PLC module to re-engage the safety contactor.

[0051] In summary, it can be seen that the embodiments provided by this invention construct a hardware sensor cluster including optical vision units, radar sensing units, and attitude positioning units, and combine it with the AI ​​model library of the edge gateway and multi-sensor fusion algorithms to accurately identify ship hatches, material shapes, and dynamic obstacles, thereby effectively covering the perception needs of complex operation scenarios. By using machine learning and strategy optimization as the core, dynamic adjustment strategies are generated to improve operational adaptability. Then, based on the motion planner and digital twin engine, the safety and efficiency of the running trajectory are simulated and verified. According to the task scheduler, the various modules are coordinated to achieve refined processing of decision execution control and reduce on-site operation risks. By covering multi-dimensional safety monitoring and hierarchical response, the safety of equipment and operations is ensured. Combined with the human-computer interaction mechanism and visualization, operations can be quickly restored through remote monitoring and local rapid operation, improving operational efficiency.

[0052] The embodiments of the present invention have been described above from the perspective of the control method for the bridge-type ship unloader. The embodiments of the present invention will now be described below from the perspective of the control device for the bridge-type ship unloader.

[0053] Please see Figure 3 , Figure 3 A virtual structural schematic diagram of the bridge unloader control device in this embodiment of the invention. The bridge unloader control device 300 is applied to the bridge unloader system and includes: The initialization module 301 is used to control the trolley corresponding to the bridge ship unloader to run to the predetermined scanning area when a start command is received, and to initialize the parameters of all sensors corresponding to the bridge ship unloader system. The preprocessing module 302 is used to collect raw data from each of the sensors in real time and preprocess the raw data through a pre-trained perception model to obtain a structured data packet. The raw data includes color texture information, 3D point cloud distance information and obstacle information. The structured data packet includes semantic information and confidence level. The determination module 303 is used to determine the control command sequence of the grab bucket of the bridge unloader in the current cycle based on the structured data packet; The operation module 304 is used to control the grab bucket of the bridge unloader to operate in the current cycle according to the control command sequence.

[0054] In one possible design, the determining module 303 is specifically used for: Extract the target coordinates from the structured data packet and convert the target coordinates into the local coordinate system of the bridge unloader; The grasping strategy for the current period is determined based on the structured data packet, and the grasping data of the grab bucket is calculated, including the opening angle and the expected closing torque threshold. The grabbing point is determined based on the grabbing strategy and the target coordinates; Construct an aerial trajectory between the grab point and the current position of the grab bucket, the aerial trajectory avoiding the bulkheads and static obstacles of the target cargo ship; The aerial trajectory is subjected to anti-sway processing to generate an anti-sway trajectory, which is a curve with a specific acceleration; When the anti-shake trajectory is verified, the verified anti-shake trajectory is decomposed into the control command sequence.

[0055] In one possible design, the determining module 303 is further configured to: As the grab moves according to the sequence of control commands, the actual position and swing state of the grab are acquired in real time. When an abnormal situation exists, the instruction sequence following the abnormal moment in the control instruction sequence is compensated; When the grab bucket completes the sequence of control commands, the grab bucket's digging data is recorded, including the actual full bucket rate, energy consumption, and duration. Based on the mining data, adjust the grasping strategy and anti-shake parameters for subsequent mining cycles after the current mining cycle.

[0056] In one possible design, the operation module 304 is specifically used for: The control command sequence is parsed to determine the target point coordinates; Calculate the distance difference between the current position of the grab and the coordinates of the target point; The distance difference is converted into a real-time changing speed setpoint and direction signal; The grab bucket is controlled to operate according to the speed setpoint and the direction signal; During the movement of the grab bucket, the real-time actual position of the grab bucket is calculated, and the real-time actual position is compared with the coordinates of the target point to obtain the target deviation; The speed setpoint and the direction signal are adjusted according to the target deviation, and the grab bucket is controlled to run based on the adjusted speed setpoint and the direction signal until the grab bucket reaches the target point coordinates.

[0057] In one possible design, the operation module 304 is further configured to: When the structured data packet includes alarm information, the alarm information is synchronously responded to in each of the multiple interfaces, and the multiple interfaces are associated with the bridge unloader system. Based on the user's operation instructions for synchronizing the corresponding alarm information, and based on the operation instructions, decision information is generated; The alarm information, the operation instructions, and the decision information are stored together and the perception model is updated and trained using the alarm information, the operation instructions, and the decision information.

[0058] In one possible design, the operation module 304 is further configured to: When a target event that triggers an early warning is detected, it is determined whether the target event meets the first preset condition and does not meet the second preset condition; When the target event meets the first preset condition but does not meet the second preset condition, an early warning message is issued; Determine whether the target event satisfies the second preset condition and does not satisfy the third preset condition; When the target event satisfies the second preset condition but does not satisfy the third preset condition, the target component corresponding to the target event is adaptively adjusted. Determine whether the target event satisfies the third preset condition; When the target event meets the third preset condition, the power supply to the target component is disconnected, a fault alarm is sent with the highest priority, and a log is recorded so that maintenance personnel can perform fault maintenance based on the recorded log.

[0059] In one possible design, the operation module 304 is further configured to: A graphical human-machine interface is provided, which displays a dynamic picture of the overall structure of the bridge ship unloader and its working environment. Generate a real-time data dashboard, which displays the performance indicators of the bridge ship unloader in the form of charts, dashboards and numbers; A virtual unloader model corresponding to the bridge-type ship unloader is constructed, and the device parameter viewing and operation permissions of the bridge-type ship unloader are set for users with different permissions.

[0060] above Figure 3 The bridge-type ship unloader control device in this embodiment of the invention has been described from the perspective of modular functional entities. The following is a detailed description of the bridge-type ship unloader control device in this embodiment of the invention from the perspective of hardware processing. Please refer to [link / reference]. Figure 4 A schematic diagram of an embodiment of the bridge unloader control device 400 of the present invention is shown. The bridge unloader control device 400 includes: Input device 401, output device 402, processor 403, and memory 404 (where the number of processors 403 can be one or more). Figure 4 (Taking a processor 403 as an example). In some embodiments of the present invention, the input device 401, output device 402, processor 403, and memory 404 may be connected via a communication bus or other means, wherein... Figure 4 Take the China-Israel communication bus connection as an example.

[0061] Specifically, by calling the operation instructions stored in memory 404, processor 403 performs the following steps: When a start command is received, the trolley corresponding to the bridge ship unloader is controlled to move to the predetermined scanning area, and the parameters of all sensors corresponding to the bridge ship unloader system are initialized. The system collects raw data from each of the sensors in real time and preprocesses the raw data using a pre-trained perception model to obtain a structured data packet. The raw data includes color and texture information, 3D point cloud distance information, and obstacle information. The structured data packet includes semantic information and confidence level. The control command sequence for the grab bucket of the bridge unloader in the current cycle is determined based on the structured data packet. The grab bucket of the bridge unloader is controlled to operate within the current cycle according to the control command sequence.

[0062] By calling the operation instructions stored in memory 404, processor 403 is also used to execute... Figure 2 Any of the methods in the corresponding embodiments.

[0063] Please see Figure 5 , Figure 5 A schematic diagram of an embodiment of the electronic device provided in this invention.

[0064] like Figure 5As shown, this embodiment of the invention provides an electronic device, including a memory 510, a processor 520, and a computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the computer program 511, it performs the following steps: When a start command is received, the trolley corresponding to the bridge ship unloader is controlled to move to the predetermined scanning area, and the parameters of all sensors corresponding to the bridge ship unloader system are initialized. The system collects raw data from each of the sensors in real time and preprocesses the raw data using a pre-trained perception model to obtain a structured data packet. The raw data includes color and texture information, 3D point cloud distance information, and obstacle information. The structured data packet includes semantic information and confidence level. The control command sequence for the grab bucket of the bridge unloader in the current cycle is determined based on the structured data packet. The grab bucket of the bridge unloader is controlled to operate within the current cycle according to the control command sequence.

[0065] In practical implementation, when the processor 520 executes the computer program 511, it can achieve... Figure 2 Any of the corresponding implementation methods in the embodiments.

[0066] Since the electronic device described in this embodiment is the device used by the computing device for implementing the mid-frequency unit excitation of an array antenna in this embodiment of the present invention, those skilled in the art can understand the specific implementation method and various variations of the electronic device in this embodiment based on the method described in this embodiment of the present invention. Therefore, how the electronic device implements the method in this embodiment of the present invention will not be described in detail here. Any device used by those skilled in the art to implement the method in this embodiment of the present invention is within the scope of protection of this invention.

[0067] Please see Figure 6 , Figure 6 This is a schematic diagram of an embodiment of a computer-readable storage medium provided in this invention.

[0068] like Figure 6 As shown, this embodiment of the invention also provides a computer-readable storage medium 600, on which a computer program 611 is stored. When the computer program 611 is executed by a processor, it performs the following steps: When a start command is received, the trolley corresponding to the bridge ship unloader is controlled to move to the predetermined scanning area, and the parameters of all sensors corresponding to the bridge ship unloader system are initialized. The system collects raw data from each of the sensors in real time and preprocesses the raw data using a pre-trained perception model to obtain a structured data packet. The raw data includes color and texture information, 3D point cloud distance information, and obstacle information. The structured data packet includes semantic information and confidence level. The control command sequence for the grab bucket of the bridge unloader in the current cycle is determined based on the structured data packet. The grab bucket of the bridge unloader is controlled to operate within the current cycle according to the control command sequence.

[0069] In the specific implementation process, the computer program 611 is executed by the processor to achieve... Figure 2 Any of the corresponding implementation methods in the embodiments.

[0070] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0071] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0072] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0073] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1The function specified in one or more boxes.

[0074] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0075] This invention also provides a computer program product comprising computer software instructions that, when executed on a processing device, cause the processing device to perform actions such as... Figure 2 The process in the corresponding embodiment.

[0076] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0077] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0078] In the embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or units through some interfaces, and may be electrical, mechanical, or other forms.

[0079] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0080] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0081] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0082] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. 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 spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A control method for a bridge-type ship unloader, characterized in that, Applications in bridge-type ship unloader systems include: When a start command is received, the trolley corresponding to the bridge ship unloader is controlled to move to the predetermined scanning area, and the parameters of all sensors corresponding to the bridge ship unloader system are initialized. The system collects raw data from each of the sensors in real time and preprocesses the raw data using a pre-trained perception model to obtain a structured data packet. The raw data includes color and texture information, 3D point cloud distance information, and obstacle information. The structured data packet includes semantic information and confidence level. The control command sequence for the grab bucket of the bridge unloader in the current cycle is determined based on the structured data packet. The grab bucket of the bridge unloader is controlled to operate within the current cycle according to the control command sequence.

2. The method according to claim 1, characterized in that, The step of determining the control command sequence for the grab bucket of the bridge unloader in the current cycle based on the structured data packet includes: Extract the target coordinates from the structured data packet and convert the target coordinates into the local coordinate system of the bridge unloader; The grasping strategy for the current period is determined based on the structured data packet, and the grasping data of the grab bucket is calculated, including the opening angle and the expected closing torque threshold. The grabbing point is determined based on the grabbing strategy and the target coordinates; Construct an aerial trajectory between the grab point and the current position of the grab bucket, the aerial trajectory avoiding the bulkheads and static obstacles of the target cargo ship; The aerial trajectory is subjected to anti-sway processing to generate an anti-sway trajectory, which is a curve with a specific acceleration; When the anti-shake trajectory is verified, the verified anti-shake trajectory is decomposed into the control command sequence.

3. The method according to claim 2, characterized in that, The method further includes: As the grab moves according to the sequence of control commands, the actual position and swing state of the grab are acquired in real time. When an abnormal situation exists, the instruction sequence following the abnormal moment in the control instruction sequence is compensated; When the grab bucket completes the sequence of control commands, the grab bucket's digging data is recorded, including the actual full bucket rate, energy consumption, and duration. Based on the mining data, adjust the grasping strategy and anti-shake parameters for subsequent mining cycles after the current mining cycle.

4. The method according to claim 1, characterized in that, The step of controlling the grab bucket of the bridge unloader to operate within the current cycle according to the control command sequence includes: The control command sequence is parsed to determine the target point coordinates; Calculate the distance difference between the current position of the grab and the coordinates of the target point; The distance difference is converted into a real-time changing speed setpoint and direction signal; The grab bucket is controlled to operate according to the speed setpoint and the direction signal; During the movement of the grab bucket, the real-time actual position of the grab bucket is calculated, and the real-time actual position is compared with the coordinates of the target point to obtain the target deviation; The speed setpoint and the direction signal are adjusted according to the target deviation, and the grab bucket is controlled to run based on the adjusted speed setpoint and the direction signal until the grab bucket reaches the target point coordinates.

5. The method according to any one of claims 1 to 4, characterized in that, The method further includes: When the structured data packet includes alarm information, the alarm information is synchronously responded to in each of the multiple interfaces, and the multiple interfaces are associated with the bridge unloader system. Based on the user's operation instructions for synchronizing the corresponding alarm information, and based on the operation instructions, decision information is generated; The alarm information, the operation instructions, and the decision information are stored together and the perception model is updated and trained using the alarm information, the operation instructions, and the decision information.

6. The method according to any one of claims 1 to 4, characterized in that, The method further includes: When a target event that triggers an early warning is detected, it is determined whether the target event meets the first preset condition and does not meet the second preset condition; When the target event meets the first preset condition but does not meet the second preset condition, an early warning message is issued; Determine whether the target event satisfies the second preset condition and does not satisfy the third preset condition; When the target event satisfies the second preset condition but does not satisfy the third preset condition, the target component corresponding to the target event is adaptively adjusted. Determine whether the target event satisfies the third preset condition; When the target event meets the third preset condition, the power supply to the target component is disconnected, a fault alarm is sent with the highest priority, and a log is recorded so that maintenance personnel can perform fault maintenance based on the recorded log.

7. The method according to any one of claims 1 to 4, characterized in that, The method further includes: A graphical human-machine interface is provided, which displays a dynamic picture of the overall structure of the bridge ship unloader and its working environment. Generate a real-time data dashboard, which displays the performance indicators of the bridge ship unloader in the form of charts, dashboards and numbers; A virtual unloader model corresponding to the bridge-type ship unloader is constructed, and the device parameter viewing and operation permissions of the bridge-type ship unloader are set for users with different permissions.

8. A control device for a bridge-type ship unloader, characterized in that, Applications in bridge-type ship unloader systems include: The initialization module is used to control the trolley corresponding to the bridge ship unloader to run to the predetermined scanning area when a start command is received, and to initialize the parameters of all sensors corresponding to the bridge ship unloader system. The preprocessing module is used to collect raw data from each of the sensors in real time and preprocess the raw data through a pre-trained perception model to obtain a structured data packet. The raw data includes color texture information, 3D point cloud distance information and obstacle information. The structured data packet includes semantic information and confidence level. The determination module is used to determine the control command sequence of the grab bucket of the bridge unloader in the current cycle based on the structured data packet; The operation module is used to control the grab bucket of the bridge unloader to operate within the current cycle according to the control command sequence.

9. An electronic device, characterized in that, include: A memory and a processor, wherein the processor is used to execute computer management programs stored in the memory to implement the steps of the bridge unloader control method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer management program, which, when executed by a processor, implements the steps of the bridge unloader control method as described in any one of claims 1 to 7.

Images