Remote full-automatic multi-machine cooperative intelligent control system based on ship unloader

Abstract

The invention discloses a remote full-automatic multi-machine cooperative intelligent control system based on ship unloaders, and relates to the technical field of port machinery automation and intelligent control, and the system comprises an initial alignment module which is used for matching a hatch position based on three-dimensional model data, analyzing an optimal operation area of each ship unloader through a path planning algorithm in combination with the three-dimensional model data, and setting an optimal operation area of each ship unloader; the ship unloader is adjusted to move to a designated position; the grabbing module is used for combining the three-dimensional model data with the real-time scanning data, generating a next grabbing point location of the grab bucket by using a multi-target genetic algorithm, sending a next optimal grabbing point to the ship unloader through a communication protocol, and grabbing; the optimal operation area of each ship unloader is determined through the three-dimensional model data generated by the 3D laser scanning technology in combination with the path planning algorithm, it is ensured that equipment is accurately positioned to the working position, and the operation precision and safety are improved.

Description

Technical Field

[0001] The invention relates to the technical field of port machinery automation and intelligent control, in particular to a remote fully automatic multi-machine collaborative intelligent control system based on a ship unloader. Background Art

[0002] In recent years, with the acceleration of global economic integration and the continuous growth of international trade volume, the efficiency of port cargo loading and unloading has become one of the key factors restricting the efficiency of the logistics chain. As an indispensable core equipment of large bulk cargo terminals, ship unloaders play an irreplaceable role in improving port operation efficiency. However, the operation of traditional ship unloaders still relies too much on manual driving, and there are problems such as low operating efficiency, poor safety, and susceptibility to environmental influences. To this end, automation and intelligent technologies are gradually applied to the operation and control of ship unloaders, hoping to solve the above problems. For example, the application of three-dimensional scanning technology enables ship unloaders to identify target locations more accurately; and task scheduling based on artificial intelligence algorithms has improved the work efficiency of ship unloaders to a certain extent. Despite this, the existing technology still faces many challenges, especially in the generation and optimization of multi-machine collaborative operation plans.

[0003] At present, although the existing remote control system of ship unloaders can realize the automated operation of a single device to a certain extent, its performance is not satisfactory when facing the collaborative operation of multiple machines under complex working conditions. First of all, for the generation of multi-machine collaborative operation plans, most of them adopt preset rules or simple mathematical models, which makes it difficult to dynamically adjust the operation strategy according to the actual working conditions, limiting flexibility and adaptability. Secondly, there is currently a lack of effective real-time data interaction mechanism, and there is no way to update key information such as the operation status and the amount of remaining materials in a timely manner, which will lead to unreasonable task allocation and affect the overall operation efficiency. In view of these shortcomings, the present invention proposes a remote fully automatic multi-machine collaborative intelligent control system based on a ship unloader. By introducing the Q-learning algorithm to generate a multi-machine collaborative operation plan, and using a genetic algorithm for optimization, the problems of adaptability and efficiency of the multi-machine collaborative operation plan are effectively solved. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a ship unloader-based remote fully automatic multi-machine collaborative intelligent control system to solve the problems of multi-machine collaborative operation scheme optimization and imperfect real-time data interaction mechanism.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: The present invention provides a remote fully automatic multi-machine collaborative intelligent control system based on a ship unloader, which comprises: The task generation module generates a multi-machine collaborative operation plan based on the ship berthing information through the Q-learning algorithm, and optimizes it through the genetic algorithm to obtain the optimal multi-machine collaborative operation plan; The 3D modeling module uses 3D laser scanning to collect hull data and cabin material data based on the optimal multi-machine collaborative operation solution, and then splices and fuses them to generate 3D model data; The initial alignment module matches the hatch position based on the 3D model data, analyzes the best operating area for each ship unloader through the path planning algorithm combined with the 3D model data, and uses the communication protocol to send movement instructions to adjust the ship unloader to the specified position; The grabbing module combines the 3D model data with the real-time scanning data, uses a multi-objective genetic algorithm to generate the next grabbing point of the grab bucket, sends the next best grabbing point to the ship unloader through the communication protocol, and performs grabbing; The safety protection module monitors the tilt of the hull and the safety distance through the camera, and dynamically adjusts the operating position of the ship unloader; Dynamic resource scheduling module adjusts task priorities and resource allocation based on the dynamically adjusted ship unloader operation position As a preferred solution of the remote fully automatic multi-machine collaborative intelligent control system based on the ship unloader of the present invention, wherein: the multi-machine collaborative operation plan is generated by the Q-learning algorithm according to the ship berthing information, and the specific steps are as follows: Obtain ship berthing information, remove noise data through the standard deviation method, and use the median filling method to fill in missing values; The processed ship berthing information is calculated through the Q-learning algorithm to obtain a multi-machine collaborative operation plan.

[0007] As a preferred solution of the remote fully automatic multi-machine cooperative intelligent control system based on the ship unloader of the present invention, wherein: the optimization is performed by genetic algorithm to obtain the optimal multi-machine cooperative operation plan, and the specific steps are as follows: Genetic algorithm is used to optimize the generated multi-machine collaborative operation scheme, and the multi-objective weighted scoring method is used to define the fitness function to measure the optimization effect of multi-machine collaborative operation. The optimal multi-machine collaborative operation solution is obtained through iterative selection, crossover and mutation processes.

[0008] As a preferred solution of the remote fully automatic multi-machine collaborative intelligent control system based on the ship unloader of the present invention, the optimal multi-machine collaborative operation solution is based on the use of 3D laser scanning to collect hull data and cabin material data, and splice and fuse them to generate three-dimensional model data. The specific steps are as follows: Through 3D laser scanning, a grid scanning strategy is used to scan the hull and interior of the same cabin area multiple times from multiple angles to obtain 3D laser scanning raw data; The original 3D laser scanning data is input into Geomagic Wrap, and the ICP algorithm is used for point cloud registration. The point cloud data after registration is obtained by minimizing the distance error between the two sets of points. The improved Poisson surface reconstruction algorithm is then input to merge into a complete 3D model data. As a preferred solution of the remote fully automatic multi-machine collaborative intelligent control system based on the ship unloader of the present invention, wherein: the hatch position is matched based on the three-dimensional model data, and the optimal operating area of ​​each ship unloader is analyzed by combining the three-dimensional model data with the path planning algorithm. The specific steps are as follows: Use Geomagic Wrap to analyze the complete 3D model data, locate each hatch, and record the coordinate information; The optimal path is obtained by using the path planning algorithm based on the hatch coordinate information and the moving range and arm span of the ship unloader; The optimal path is analyzed through the area division method to obtain the optimal operating area of ​​each ship unloader.

[0009] As a preferred solution of the remote fully automatic multi-machine collaborative intelligent control system based on the ship unloader of the present invention, wherein: the use of the communication protocol to send a moving instruction to adjust the ship unloader to move to a specified position, the specific steps are as follows: Based on the optimal path and optimal operating area, instructions for the target position coordinates and operating parameters are sent to each ship unloader. After receiving the instructions, each ship unloader performs self-diagnosis, moves accurately to the designated position and starts operation.

[0010] As a preferred solution of the remote fully automatic multi-machine collaborative intelligent control system based on the ship unloader of the present invention, wherein: the three-dimensional model data and the real-time scanning data are combined, and the next grabbing point of the grab bucket is generated using a multi-objective genetic algorithm. The specific steps are as follows: The static 3D model data is synchronized and integrated with the real-time 3D laser scanning data, and the ICP algorithm is used for data alignment to obtain the integrated 3D model data; Based on the integrated 3D model data, the objective function of the next grabbing point is defined through a multi-objective optimization method of material volume and obstacle distance; The multi-objective genetic algorithm is used to optimize the objective function and obtain the next best grasping point.

[0011] As a preferred solution of the remote fully automatic multi-machine collaborative intelligent control system based on the ship unloader of the present invention, wherein: the next best grabbing point is sent to the ship unloader through the communication protocol and the grabbing is performed, and the specific steps are as follows: Based on the calculated optimal grabbing point, a grabbing instruction containing the three-dimensional coordinates of the target position and operation parameters is first generated, and the grabbing instruction is sent to the ship unloader. The ship unloader moves to the designated position and grabs according to the grabbing instruction.

[0012] As a preferred solution of the remote fully automatic multi-machine collaborative intelligent control system based on the ship unloader of the present invention, wherein: the camera is used to monitor the tilt of the hull and the safety distance, and the operating position of the ship unloader is dynamically adjusted. The specific steps are as follows: The camera collects the data of the tilt angle of the hull and the distance between the hull and the ship unloader in real time, and uses the Kalman filter to perform denoising and smoothing. Based on the processed data of the ship hull tilt angle and the distance between the hull and the ship unloader, the safety assessment method is used to calculate the safety assessment index, and the multi-objective genetic algorithm is used to recalculate the optimal operating area of ​​each ship unloader. According to the new optimal operating area allocation plan, instructions are sent to each ship unloader to adjust to the designated position to continue working, and the environment and ship unloader status changes are continuously monitored.

[0013] As a preferred solution of the remote fully automatic multi-machine collaborative intelligent control system based on the ship unloader of the present invention, wherein: the task priority and resource allocation are adjusted based on the dynamically adjusted operation position of the ship unloader, and the specific steps are as follows: Perform statistical analysis on historical operation data to obtain comprehensive performance thresholds; After the ship unloader is adjusted to the new operating area, the performance status is analyzed in combination with the ship unloader status and safety assessment indicators. The ship unloaders below the comprehensive performance threshold are prioritized and re-ordered to generate a new task priority list.

[0014] Re-allocate resources to each ship unloader based on the new task priority list and total available resources; According to the resource allocation results and task priority list, the task is assigned to the ship unloader, and the operation instruction is sent to start the operation.

[0015] The beneficial effects of the present invention are as follows: a multi-machine collaborative operation plan is generated using a Q-learning algorithm, and a genetic algorithm is used for optimization to achieve a customized ship unloading operation plan. This not only improves operating efficiency and resource utilization, but also reduces manual intervention and reduces operating costs. At the same time, based on the three-dimensional model data generated by 3D laser scanning technology, the path planning algorithm is combined to determine the optimal operating area for each ship unloader to ensure that the equipment is accurately positioned at the working position, thereby improving operating accuracy and safety. This method effectively avoids the risk of equipment collision, reduces energy consumption and maintenance costs, and brings significant economic and environmental benefits. In summary, the combined effect of intelligent scheduling and precise operation has greatly improved the overall performance of the machine, achieved efficient, safe and economical ship unloading operations, and provided a solid foundation for remote fully automatic multi-machine collaborative control. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0017] Figure 1 This is a schematic diagram of the remote fully automatic multi-machine collaborative intelligent control system based on the ship unloader in Example 1.

[0018] Figure 2 This is a schematic diagram of the task generation and optimization process in Example 1.

[0019] Figure 3 This is a schematic diagram of three-dimensional modeling and data processing in Example 1.

[0020] Figure 4 This is a schematic diagram of the safety monitoring and dynamic adjustment process in Example 1. DETAILED DESCRIPTION

[0021] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0022] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0023] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0024] Example 1, reference Figure 1~Figure 4 This embodiment provides a remote fully automatic multi-machine collaborative intelligent control system based on a ship unloader, comprising the following steps: The task generation module generates a multi-machine collaborative operation plan based on the ship berthing information through the Q-learning algorithm.

[0025] Obtain ship berthing information, remove noise data through the standard deviation method, and use the median filling method to fill in missing values; It should be noted that AIS provides real-time data such as ship size, shape and berthing position to ensure that the specific parameters and current position of each ship are known. At the same time, the port sends information about the expected types and quantities of cargo to the unloader. The real-time data such as ship size, shape and berthing position have been entered before the ship arrives and updated according to the scheduling plan. The information on the expected types and quantities of cargo to be loaded and unloaded is integrated to obtain the ship berthing information. After obtaining the ship berthing information, the information on the expected types and quantities of cargo to be loaded and unloaded is first preprocessed to ensure accuracy and completeness. The standard deviation method is used to remove noise data. The specific steps are to calculate the standard deviation of each item of information on the expected types and quantities of cargo to be loaded and unloaded, and identify outliers that exceed the set standard deviation multiple, which are regarded as noise and eliminated. Then, for missing values ​​generated due to noise removal or the original collection process, the median filling method is used to supplement them. The standard deviation method is used to fill the missing values ​​by calculating the median of the existing information on the expected types and quantities of cargo to be loaded and unloaded, ensuring the continuity and consistency of the information set of the expected types and quantities of cargo to be loaded and unloaded. For example, when dealing with key parameters such as ship size and berthing location, this method can effectively avoid overall deviations caused by individual erroneous ship berthing data, thereby improving the accuracy and reliability of subsequent path planning and work allocation, and ultimately achieving the purpose of efficiently and accurately obtaining ship berthing information.

[0026] The processed ship berthing information is calculated through the Q-learning algorithm to obtain a multi-machine collaborative operation plan.

[0027] It should be noted that the processed ship berthing information is calculated by the Q-learning algorithm to obtain a multi-machine collaborative operation solution. First, the state space is defined, including the port and ship automatic identification method, providing the real-time position information of the ship, and combining the processing and analysis of the ship berthing information to obtain the position coordinates of the ship unloader, the amount of material at the current grabbing point, and the distance of the surrounding obstacles to fully describe the working environment. Next, the action space is defined, and each action includes the displacement change along each axis and the grabbing / releasing operation, which is used to control the operation of the ship unloader. Then, the reward function is designed to evaluate the effect of each step of the operation, and the Q-learning algorithm is used to update the Q value table to learn which action can achieve the best effect in a specific state. Finally, the optimal strategy is generated based on the trained Q value table to guide multiple ship unloaders to collaborate efficiently, ensure the overall operation efficiency and safety are optimized, and realize an automated and intelligent multi-machine collaborative operation solution.

[0028] The task generation module is optimized through genetic algorithm to obtain the optimal multi-machine collaborative operation plan.

[0029] The generated multi-machine collaborative operation scheme is optimized by genetic algorithm, and the multi-objective weighted scoring method is used to define the fitness function to measure the optimization effect of multi-machine collaborative operation.

[0030] It should be noted that the generated multi-machine collaborative operation scheme is optimized by using a genetic algorithm. First, a fitness function is defined to measure the effect of multi-machine collaborative operation. The fitness function comprehensively considers multiple key performance indicators such as grasping efficiency, operational safety and energy consumption, and balances the importance of each goal through a weighted scoring method. When the population is initialized, a set of potential multi-machine collaborative operation schemes is randomly generated; then the fitness value of each scheme is calculated, and based on these fitness values, the roulette wheel selection method is used to select excellent individuals to enter the next generation. Next, a new offspring individual is created through a crossover operation. The specific method is to exchange some genes of two parent individuals to produce a new combination; and a mutation operation is applied to introduce random changes, such as randomly changing the action sequence or position coordinates of some individuals, to increase population diversity and explore a better solution space.

[0031] The optimal multi-machine collaborative operation solution is obtained through iterative selection, crossover and mutation processes.

[0032] It should be noted that the entire process is continuously optimized through iterative selection, crossover and mutation steps until a predetermined stop condition is reached, such as the maximum number of iterations or the fitness no longer significantly improves. This method uses the powerful search capabilities of genetic algorithms and combines specific evaluation criteria to ensure efficient, safe and flexible multi-machine collaborative operations in complex environments, and ultimately obtains the optimal multi-machine collaborative operation solution; It should also be noted that the fitness function is expressed as: ; in, is the fitness function, is the weight of the crawling efficiency goal, is the weight of the operational safety objective, is the weight of the energy consumption target, Indicates the reciprocal of the minimum safety distance. is a small positive value to prevent the denominator from being zero, Indicates the amount of material grabbed per unit time, Indicates energy consumption.

[0033] The 3D modeling module, based on the optimal multi-machine collaborative operation solution, uses 3D laser scanning to collect hull data and cabin material data, and splices and fuses them to generate 3D model data.

[0034] Through 3D laser scanning, a grid scanning strategy is adopted to scan the hull and the interior of the same cabin area multiple times from multiple angles to obtain the 3D laser scanning raw data.

[0035] It should be noted that through 3D laser scanning technology and a grid scanning strategy, detailed 3D model data collection of the hull and its internal structure is carried out. First, the hull surface or internal space is divided into multiple small, regular grid areas to ensure that each grid is covered. Then, the same grid area is scanned multiple times from different angles to obtain comprehensive and high-resolution data. This multi-angle repeated scanning method can effectively reduce the shadow effect and the missing 3D model data, and improve the accuracy of the final 3D model. The 3D laser scanning device emits a laser beam and measures the time it takes to reflect back, thereby calculating the distance of each point on the surface of the object and generating point cloud data. During the scanning process, the results of each scan are recorded to ensure that all point cloud data are accurately captured. After preliminary processing, these raw point cloud data can provide detailed information about the hull and internal structure, providing a solid foundation for subsequent analysis and operations. In this way, the 3D laser scanning raw data is finally obtained.

[0036] The original 3D laser scanning data is input into Geomagic Wrap, and the ICP algorithm is used for point cloud registration. The point cloud data after registration is obtained by minimizing the distance error between the two sets of points. The improved Poisson surface reconstruction algorithm is then input to merge them into a complete 3D model data.

[0037] It should be noted that the original point cloud data obtained by 3D laser scanning is input into Geomagic Wrap, and the ICP algorithm is used for point cloud registration. The matching is achieved by minimizing the distance error between the two sets of points to generate registered point cloud data. Then, the point cloud data is processed using an improved version of the Poisson surface reconstruction algorithm. The improved version of the Poisson surface reconstruction algorithm enhances noise filtering, adaptive resolution control, and optimized boundary processing to ensure high-quality data for surface reconstruction. During the reconstruction process, the point cloud data is first finely filtered for noise, and then the grid resolution is automatically adjusted according to the point cloud density. The improved Poisson surface reconstruction algorithm is used to construct a preliminary three-dimensional surface model, and the open boundaries are specially processed to ensure that the model surface is smooth and continuous. Finally, all processed point cloud data are merged into a complete, high-quality three-dimensional model data to obtain a complete three-dimensional model data.

[0038] The initial alignment module matches the hatch position based on the 3D model data and analyzes the optimal operating area of ​​each ship unloader through the path planning algorithm combined with the 3D model data.

[0039] Geomagic Wrap was used to analyze the complete 3D model data, locate each hatch, and record the coordinate information.

[0040] It should be noted that when using Geomagic Wrap to analyze the complete 3D model data, the high-quality 3D model data generated previously is first imported. In the software, feature extraction methods are used to identify and locate the position of each hatch. The specific operation includes using the automatic surface detection function in the software to preliminarily identify possible hatch areas, and then using the boundary definition tool to carefully analyze these areas to ensure that the edges of each hatch are accurately captured. Next, the coordinate measurement tool is used to record the 3D coordinates of the center point of each hatch. In addition, these coordinate data can be exported to standard format files such as CSV or TXT for subsequent processing and reference. In this way, not only can each hatch be located, but the coordinate information can also be recorded in detail, and finally a complete data set containing all hatch coordinates is generated, which provides an important reference for the operation of the ship unloader, thereby obtaining a complete data set containing all hatch coordinate information.

[0041] The optimal path is obtained using the path planning algorithm based on the hatch coordinate information and the moving range and arm span of the ship unloader.

[0042] It should be noted that the optimal path is calculated using the path planning algorithm by importing the coordinate information of the hatches and combining the moving range and arm span of the ship unloader. First, the three-dimensional coordinate data of each hatch is input into the path planning. Based on these input data, the A algorithm evaluates the cost of different paths and selects the best path that meets the operational requirements while minimizing energy consumption and time. In this process, the motion trajectory of the ship unloader is simulated in real time to ensure the safety and feasibility of the path. Finally, a detailed path plan is generated to guide the ship unloader to efficiently and safely reach each hatch to perform the task, thus obtaining an optimized optimal path.

[0043] The optimal path is analyzed through the area division method to obtain the optimal operating area of ​​each ship unloader.

[0044] It should be noted that in the future, the optimal path will be analyzed by the regional division method. First, the optimal path data of each ship unloader and the three-dimensional model data of the ship need to be imported. Next, the regional division algorithm such as Voronoi diagram and K-means clustering is used to subdivide the operating area. The specific steps are to first use the Voronoi diagram to generate preliminary partitions according to the optimal path of the ship unloader to ensure that each ship unloader has an independent working area, and then use K-means clustering to further optimize these areas so that the task volume in each area is balanced and cross interference is avoided. In this process, the optimal operating area of ​​each ship unloader is ensured to be both efficient and safe based on factors such as the material distribution density and obstacle location extracted from the three-dimensional model data and the operating efficiency of the ship unloader. Finally, a specific operating area allocation plan for each ship unloader is generated, which provides detailed guidance for the collaborative operation of multiple machines, thereby obtaining the optimal operating area of ​​each ship unloader.

[0045] The initial alignment module uses the communication protocol to send movement instructions to adjust the ship unloader to move to the specified position.

[0046] Based on the optimal path and optimal operating area, instructions for the target position coordinates and operating parameters are sent to each ship unloader. After receiving the instructions, each ship unloader performs self-diagnosis, moves accurately to the designated position and starts operation.

[0047] It should be noted that in the process of realizing automated ship unloading based on the optimal path and the optimal operating area, it is first necessary to collect data including the optimal path coordinates, operating parameters and self-diagnosis status of each ship unloader. Next, the target position coordinates and necessary operating parameter instructions are sent to each ship unloader. This process uses a communication protocol to ensure the accurate transmission of instructions. After receiving the instructions, each ship unloader will use its own self-diagnosis algorithm to check the equipment status. After confirming that it is correct, it will accurately move to the specified position according to the received coordinate data and start the operation.

[0048] The grabbing module combines the 3D model data with the real-time scanning data and uses a multi-objective genetic algorithm to generate the next grabbing point of the grab bucket.

[0049] The static 3D model data is synchronized and integrated with the real-time 3D laser scanning data, and the ICP algorithm is used for data alignment to obtain the integrated 3D model data.

[0050] It should be noted that in order to synchronize and integrate static 3D model data with real-time 3D laser scanning data, two sets of data need to be imported first: one set is high-quality static 3D model data generated by Geomagic Wrap, and the other set is fresh point cloud data acquired by real-time 3D laser scanning equipment, which contains detailed geometric information and spatial coordinates. Next, the ICP algorithm is used for data alignment to achieve matching by minimizing the distance error between the two sets of point clouds. In the specific operation, the static model data is used as a reference benchmark, and the real-time scanning data is gradually adjusted to achieve the best alignment effect. Finally, the integrated 3D model data is obtained.

[0051] Based on the integrated 3D model data, the objective function of the next grasping point is defined through a multi-objective optimization method of material volume and obstacle distance.

[0052] It should be noted that, based on the integrated 3D model data, key information, including material volume distribution and obstacle distance, is first extracted, which comes from the integration results of static 3D model data and real-time 3D laser scanning data. Next, a multi-objective optimization method is used to define an objective function for determining the next grab point of the grab.

[0053] The multi-objective genetic algorithm is used to optimize the objective function and obtain the next best grasping point.

[0054] It should be noted that the multi-objective genetic algorithm (MOGA) is used to optimize and solve the objective function to determine the next best grabbing point. It provides the basic input for multi-objective optimization. Next, the multi-objective genetic algorithm is used for processing. The multi-objective genetic algorithm can find a balance between multiple conflicting objectives, such as maximizing the volume of grasped materials and minimizing the distance to obstacles. During the optimization process, the multi-objective genetic algorithm iteratively improves the solutions in the population through selection, crossover, and mutation operations, gradually approaching the optimal solution. Each generation of the population contains a set of potential grabbing point locations. After multiple iterations, one or more Pareto optimal solutions are finally obtained, representing the best compromise between different objectives. Based on these Pareto optimal solutions, a most suitable grabbing point is selected as the next operating point. The entire process not only takes into account the maximum collection of materials, but also ensures the safety of the operation and avoids collisions with obstacles. When the next best grabbing point is reached, The grabbing module sends the next best grabbing point to the ship unloader through the communication protocol and performs grabbing.

[0055] Based on the calculated optimal grabbing point, a grabbing instruction containing the three-dimensional coordinates of the target position and operation parameters is first generated, and the grabbing instruction is sent to the ship unloader. The ship unloader moves to the designated position and grabs according to the grabbing instruction.

[0056] It should be noted that based on the calculated optimal grabbing point, a grabbing instruction containing the three-dimensional coordinates of the target position and operating parameters is first generated. This includes the coordinates of the optimal grabbing point obtained from the multi-objective genetic algorithm and the required operating parameters such as the grabbing bucket posture adjustment angle and the grabbing force setting value. These grabbing instructions are sent to the ship unloader using a communication protocol. After receiving the instructions, the ship unloader first performs a self-diagnosis to ensure that all mechanical components are in normal working condition, which is achieved through a built-in self-diagnosis algorithm. Once confirmed to be correct, the ship unloader moves accurately to the specified position according to the three-dimensional coordinate data in the instruction, and adjusts the grabbing bucket posture and strength according to the operating parameters to start the grabbing operation. During this process, the status of the ship unloader is continuously monitored to ensure the safety and accuracy of the operation.

[0057] The safety protection module monitors the hull inclination and safety distance through cameras and dynamically adjusts the operating position of the ship unloader.

[0058] The camera collects the data of the hull tilt angle and the distance between the hull and the ship unloader in real time, and uses the Kalman filter to perform denoising and smoothing.

[0059] It should be noted that the camera collects the data of the inclination angle of the hull and the distance between the hull and the ship unloader in real time. Specifically, the camera is used to capture the visual information of the hull, from which the inclination angle and the inclination angle of the hull, and the distance between the hull and the ship unloader are extracted. The data usually contain noise and fluctuations, so denoising and smoothing are required. The Kalman filter is used as the main processing method here. The Kalman filter can estimate the current state based on the current measurement value and the state prediction value of the previous moment, effectively reducing noise and smoothing the data of the inclination angle of the hull and the distance between the hull and the ship unloader.

[0060] Based on the processed data of hull inclination angle and distance between hull and ship unloader, the safety assessment index is calculated by using safety assessment method, and the optimal operating area of ​​each ship unloader is recalculated by multi-objective genetic algorithm.

[0061] It should be noted that, based on the processed data of the inclination angle of the hull and the distance between the hull and the ship unloader, the safety assessment method is first used to calculate the safety assessment index, which usually includes a quantitative analysis of potential risk factors, such as whether the inclination angle is within the safety range and whether the distance is sufficient to avoid collision. Next, the optimal operating area of ​​each ship unloader is recalculated using a multi-objective genetic algorithm. The multi-objective genetic algorithm can find a balance between multiple conflicting objectives, such as maximizing operating efficiency and minimizing safety risks. During the optimization process, the genetic algorithm iteratively improves the solutions in the population through selection, crossover and mutation operations, gradually approaching the optimal solution. Each generation of the population contains a set of potential operating area allocation schemes. After multiple iterations, one or more Pareto optimal solutions are finally obtained, representing the best compromise between different objectives. Based on these Pareto optimal solutions, a most suitable operating area is allocated to each ship unloader, and the optimal operating area of ​​each ship unloader is recalculated, and the optimized operating area allocation scheme is obtained.

[0062] According to the new optimal operating area allocation plan, instructions are sent to each ship unloader to adjust to the designated position to continue working, and the environment and ship unloader status changes are continuously monitored.

[0063] It should be noted that according to the new optimal operation area allocation scheme, instructions are sent to each ship unloader to adjust to the designated position to continue working, and the environment and the state changes of the ship unloader are continuously monitored. First, a grab instruction containing the three-dimensional coordinates of the target position and the operating parameters is generated, including the specific coordinates and operating requirements in the optimal operation area allocation scheme obtained from the multi-objective genetic algorithm optimization. These instructions are sent to each ship unloader using a communication protocol. After receiving the instructions, the ship unloader performs a status check through the built-in self-diagnosis algorithm to ensure that all mechanical components are working properly. Once confirmed to be correct, the ship unloader moves to the new designated position according to the instructions and starts working according to the operating parameters. In this process, cameras and sensors are used to collect environmental data such as the tilt angle of the hull and the distance between the hull and the ship unloader in real time, and denoise and smooth the data through the Kalman filter to ensure accuracy and reliability. Cameras and sensors continuously monitor these environmental and ship unloader state changes so that the operation plan can be dynamically adjusted when necessary to ensure the safety and efficiency of the operation.

[0064] Adjust task priority and resource allocation based on the dynamically adjusted ship unloader operating position.

[0065] Statistical analysis of historical job data is performed to obtain comprehensive performance thresholds.

[0066] It should be noted that data including operation efficiency, equipment operating status and safety index data are collected from multiple dimensions of the ship unloader historical operation database. The representative characteristic efficiency, equipment operation and safety characteristics and comprehensive characteristics are extracted after cleaning and preprocessing by the mean filling method. Descriptive statistical analysis, distribution fitting test, machine learning algorithm-assisted analysis and other methods are used to deeply analyze the characteristics to determine the threshold. The threshold is preliminarily set based on the comprehensive results and experience. The reserved verification operation efficiency, equipment operating status and safety index data sets are used for verification and adjustment. After multiple rounds of iterative optimization, a comprehensive performance threshold that can reflect the actual performance and has stable generalization capabilities is determined, and a threshold update mechanism is established.

[0067] After the ship unloader is adjusted to the new operating area, the performance status is analyzed in combination with the ship unloader status and safety assessment indicators. The ship unloaders below the comprehensive performance threshold are prioritized and re-ordered to generate a new task priority list.

[0068] It should be noted that after the ship unloader adjusts its position according to the new operating area, the status data of the ship unloader at this time is collected, including various parameters of the equipment operation, such as motor temperature, vibration frequency, current value, etc., to reflect the operating health of the equipment. At the same time, based on the information such as the hull inclination angle monitored by the safety protection module, the safe distance between the ship unloader and the surrounding facilities, combined with the pre-set safety assessment index calculation method, a detailed safety assessment result is obtained. Then, the ship unloader status data and safety assessment index results are compared and analyzed with the previously determined comprehensive performance threshold. For those ship unloaders that are below the comprehensive performance threshold under the comprehensive evaluation of various indicators, the priority is reduced according to the established rules. After reducing the priority, all ship unloaders are re-sorted according to the new priority order, thereby generating a new task priority list, providing an accurate basis for subsequent task allocation.

[0069] Re-allocate resources to each ship unloader based on the new task priority list and total available resources; It should be noted that first, a new task priority list of the order and importance of each ship unloader task is obtained, and then resources are allocated to the ship unloaders according to priority from high to low. The specific allocation amount for each ship unloader is determined based on task requirements, current operating conditions and the total available resources. When allocating, the reasonable matching and utilization efficiency of resources are comprehensively considered. The dynamic programming algorithm is used to decompose the resource allocation problem into sub-problems. The global optimal solution is gradually obtained by solving the sub-problems. After completing the resource allocation of one ship unloader, the remaining total available resources are continuously updated and allocated to subsequent ship unloaders in order of priority until all ship unloaders are allocated or the resources are allocated.

[0070] According to the resource allocation results and task priority list, the task is assigned to the ship unloader, and the operation instruction is sent to start the operation.

[0071] It should be noted that, according to the previously determined resource allocation results, the specific resource situation allocated to each ship unloader is understood, and the importance and sequence of each task are clarified by referring to the new task priority list. Then, the task is matched with the ship unloader. According to the order of task priority from high to low, a suitable ship unloader is found for each task in turn. For the task with the highest priority, a ship unloader with the resources required to complete the task and the appropriate state will be found in the resource allocation results. Here, "appropriate state" means that the ship unloader currently has no other higher priority tasks to be executed, and its own equipment is in good condition and can work normally. After finding a matching ship unloader, an operation instruction is generated according to the specific requirements of the task and the actual situation of the ship unloader. These operation instructions contain key information such as the task's objectives, operation steps, parameter settings, such as the location of the material to be grabbed, the quantity to be grabbed, the time limit of the operation, etc. Finally, the generated operation instruction is sent to the corresponding ship unloader through the communication protocol. After receiving the operation instruction, the ship unloader starts the corresponding equipment and procedures and starts to operate according to the instruction requirements.

[0072] In summary, the present invention realizes a customized ship unloading operation plan by: using the Q-learning algorithm to generate a multi-machine collaborative operation plan, and optimizing it with a genetic algorithm. This not only improves the operating efficiency and resource utilization, but also reduces manual intervention and reduces operating costs. At the same time, based on the three-dimensional model data generated by 3D laser scanning technology, combined with the path planning algorithm, the optimal operating area of ​​​​each ship unloader is determined to ensure that the equipment is accurately positioned at the working position, thereby improving the operating accuracy and safety. This method effectively avoids the risk of equipment collision, reduces energy consumption and maintenance costs, and brings significant economic and environmental benefits. In summary, the combined effect of intelligent scheduling and precise operation has greatly improved the overall performance, realized efficient, safe and economical ship unloading operations, and provided a solid foundation for remote fully automatic multi-machine collaborative control.

[0073] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A remote fully automatic multi-machine collaborative intelligent control system based on a ship unloader, characterized by: include, The task generation module generates a multi-machine collaborative operation plan based on the ship berthing information through the Q-learning algorithm, and optimizes it through the genetic algorithm to obtain the optimal multi-machine collaborative operation plan; The 3D modeling module uses 3D laser scanning to collect hull data and cabin material data based on the optimal multi-machine collaborative operation solution, and then splices and fuses them to generate 3D model data; The initial alignment module matches the hatch position based on the 3D model data, analyzes the best operating area of ​​each ship unloader through the path planning algorithm combined with the 3D model data, and adjusts the ship unloader to move to the specified position; The grabbing module combines the 3D model data with the real-time scanning data, uses a multi-objective genetic algorithm to generate the next grabbing point of the grab bucket, sends the next best grabbing point to the ship unloader through the communication protocol, and performs grabbing; The safety protection module monitors the tilt of the hull and the safety distance through the camera, and dynamically adjusts the operating position of the ship unloader; The dynamic resource scheduling module adjusts task priorities and resource allocation based on the dynamically adjusted ship unloader operation position.

2. The remote fully automatic multi-machine collaborative intelligent control system based on ship unloader according to claim 1 is characterized in that: According to the ship berthing information, a multi-machine collaborative intelligent control operation plan is generated through the Q-learning algorithm. The specific steps are as follows: Obtain ship berthing information, remove noise data through the standard deviation method, and use the median filling method to fill in missing values; The processed ship berthing information is calculated through the Q-learning algorithm to obtain a multi-machine collaborative operation plan.

3. The remote fully automatic multi-machine collaborative intelligent control system based on ship unloader according to claim 2 is characterized in that: The optimization by genetic algorithm is used to obtain the optimal multi-machine collaborative operation plan. The specific steps are as follows: Genetic algorithm is used to optimize the generated multi-machine collaborative operation scheme, and the multi-objective weighted scoring method is used to define the fitness function to measure the optimization effect of multi-machine collaborative operation; The optimal multi-machine collaborative operation solution is obtained through iterative selection, crossover and mutation processes.

4. The remote fully automatic multi-machine collaborative intelligent control system based on ship unloader according to claim 3 is characterized in that: Based on the optimal multi-machine collaborative operation solution, 3D laser scanning is used to collect hull data and cabin material data, and splicing and fusion are used to generate 3D model data. The specific steps are as follows: Through 3D laser scanning, a grid scanning strategy is used to scan the hull and interior of the same cabin area multiple times from multiple angles to obtain 3D laser scanning raw data; The original 3D laser scanning data is input into Geomagic Wrap, and the ICP algorithm is used for point cloud registration. The point cloud data after registration is obtained by minimizing the distance error between the two groups of points. The improved Poisson surface reconstruction algorithm is then input to merge the data into a complete 3D model.

5. The remote fully automatic multi-machine collaborative intelligent control system based on ship unloader according to claim 4 is characterized in that: The method of matching hatch positions based on the three-dimensional model data and analyzing the optimal operating area of ​​each ship unloader by combining the three-dimensional model data with the path planning algorithm is as follows: Use Geomagic Wrap to analyze the complete 3D model data, locate each hatch, and record the coordinate information; The optimal path is obtained by using the path planning algorithm based on the hatch coordinate information and the moving range and arm span of the ship unloader; The optimal path is analyzed through the area division method to obtain the optimal operating area of ​​each ship unloader.

6. The remote fully automatic multi-machine collaborative intelligent control system based on ship unloader according to claim 5 is characterized in that: The specific steps of adjusting the ship unloader to move to the specified position are as follows: Based on the optimal path and optimal operating area, the target position coordinates and operating parameter instructions are sent to each ship unloader. After receiving the instructions, each ship unloader performs self-diagnosis, moves to the designated position and starts operation.

7. The remote fully automatic multi-machine collaborative intelligent control system based on ship unloader according to claim 6 is characterized in that: The three-dimensional model data and the real-time scanning data are combined to generate the next grabbing point of the grab bucket using a multi-objective genetic algorithm. The specific steps are as follows: Synchronize and integrate the static 3D model data with the real-time 3D laser scanning data, and use the ICP algorithm to align the data to obtain the integrated 3D model data; Based on the integrated 3D model data, the objective function of the next grabbing point is defined through a multi-objective optimization method of material volume and obstacle distance; The multi-objective genetic algorithm is used to optimize the objective function and obtain the next best grasping point.

8. The remote fully automatic multi-machine collaborative intelligent control system based on ship unloader according to claim 7 is characterized in that: The specific steps of sending the next best grabbing point to the ship unloader through the communication protocol and grabbing are as follows: Based on the calculated next best grabbing point, a grabbing instruction including the three-dimensional coordinates of the target position and operation parameters is generated, and the grabbing instruction is sent to the ship unloader. The ship unloader moves to the designated position and grabs according to the grabbing instruction.

9. The remote fully automatic multi-machine collaborative intelligent control system based on ship unloader according to claim 8, characterized in that: The camera is used to monitor the tilt of the hull and the safety distance, and the operating position of the ship unloader is dynamically adjusted. The specific steps are as follows: The camera collects the data of the tilt angle of the hull and the distance between the hull and the ship unloader in real time, and uses the Kalman filter to perform denoising and smoothing. Based on the processed data of the ship hull tilt angle and the distance between the hull and the ship unloader, the safety assessment method is used to calculate the safety assessment index, and the multi-objective genetic algorithm is used to recalculate the optimal operating area of ​​each ship unloader. According to the new optimal operating area allocation plan, instructions are sent to each ship unloader to adjust to the designated position to continue working, and the environment and ship unloader status changes are continuously monitored.

10. The remote fully automatic multi-machine coordinated intelligent control system based on ship unloader according to claim 9, characterized in that: The specific steps of adjusting task priority and resource allocation based on the dynamically adjusted ship unloader operation position are as follows: Perform statistical analysis on historical operation data to obtain comprehensive performance thresholds; After the ship unloader is adjusted to the new operating area, the performance status is analyzed by combining the ship unloader status and safety assessment indicators, and the ship unloaders below the comprehensive performance threshold are prioritized and re-ordered to generate a new task priority list; Re-allocate resources to each ship unloader based on the new task priority list and total available resources; According to the resource allocation results and task priority list, the task is assigned to the ship unloader, and the operation instruction is sent to start the operation.

Images