Ocean salvage operation intelligent planning system based on big data of Internet of Things

Abstract

The invention relates to the technical field of ocean salvage, and discloses an Internet of Things big data-based ocean salvage operation intelligent planning system, which comprises a data acquisition and preprocessing module for acquiring ocean operation environment data, ship state data and target object data through an Internet of Things sensor network, cleaning, fusing and storing the collected data; and the intelligent planning module is used for performing decomposition, ship resource allocation and path optimization on an ocean salvage operation task based on the data processed by the data acquisition and preprocessing module, and generating an optimal planning scheme of salvage operation. Through real-time data acquisition and intelligent planning, the efficiency of ocean salvage operation is improved, and the cost is reduced; through a dynamic monitoring and adjusting module, the operation safety and the environment adaptability are enhanced; and through a multi-ship collaborative operation mechanism, tasks are reasonably allocated, resources are dynamically scheduled, and the resource utilization rate is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of ocean salvage, and in particular to an intelligent planning system for ocean salvage operations based on Internet of Things big data. Background Art

[0002] At present, ocean salvage operations are used in shipwreck salvage, marine garbage cleaning and other deep-sea rescue scenarios. However, the existing salvage operation methods mainly rely on the experience of operators and limited equipment information support, and plan operations by manually judging the status of salvage targets and changes in the marine environment.

[0003] In the existing technology, although some salvage operation systems have begun to introduce single-function sensors or monitoring equipment to collect information about the marine environment and target objects, these systems generally have the following problems as a whole: First, the ability to perceive the marine environment and the status of the ship is relatively limited, and it is impossible to integrate multi-source data in real time and dynamically adjust the operation plan; second, there is a lack of intelligent task planning capabilities, and it is impossible to scientifically allocate ship resources and optimize routes, resulting in low operation efficiency and high costs; third, the collaborative operation capability is insufficient, and the information isolation between ships is high. When the main ship fails or the environment changes suddenly, it is impossible to effectively dispatch spare ships to take over the task. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides an intelligent planning system for ocean salvage operations based on Internet of Things big data, which solves the problems in the prior art of insufficient perception of the marine environment and ship status, unscientific task planning, and lack of multi-ship collaborative operation capabilities.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent planning system for ocean salvage operations based on Internet of Things big data, comprising: The data collection and preprocessing module is used to collect ocean-going operating environment data, ship status data and target object data through the IoT sensor network, and clean, fuse and store the collected data; Intelligent planning module, which is used to decompose the ocean salvage operation tasks, allocate vessel resources and optimize the path based on the data processed by the data acquisition and preprocessing modules, and generate the optimal planning scheme for the salvage operation; The collaborative operation module is used to achieve task collaboration and information sharing among multiple ships based on the optimal planning solution generated by the intelligent planning module; Dynamic monitoring and adjustment module, which is used to monitor environmental data, vessel status and operation progress in real time during ocean salvage operations, dynamically adjust salvage operation plans based on monitoring data, and trigger risk warning mechanisms; The data interaction center is used to manage the data flow between modules and coordinate task allocation and program execution.

[0006] Preferably, the data acquisition and preprocessing module includes: Ship sensors are used to collect information about the ship’s fuel level, load, and equipment operating status; Environmental sensors, used to collect information on ocean current velocity, wave height, and wind speed in the marine environment; External meteorological data interface, used to obtain weather forecast data from weather stations or satellites; The data cleaning and fusion unit is used to filter outliers, fill in missing values ​​and normalize the collected data.

[0007] Preferably, the intelligent planning module includes: The task modeling unit is used to decompose the overall salvage task into subtasks of target positioning, salvage operation and target transportation; Resource allocation unit, used to optimize the task allocation of multiple ships using heuristic algorithms based on task requirements, ship performance and environmental conditions; The path planning unit is used to generate the optimal navigation path for the ship by combining environmental and economic factors such as ocean current speed, wind speed and fuel consumption; The salvage strategy recommendation unit is used to select the appropriate salvage method according to the size, weight and depth of the target.

[0008] Preferably, the resource allocation unit generates a task allocation scheme based on the following optimization objectives: Maximize efficiency: minimize operation time T toal ; Cost minimization: Reduce fuel consumption F total ; Safety optimization: Prioritize vessels that are adapted to environmental conditions.

[0009] Preferably, the path planning unit adopts a dynamic path planning algorithm, which constructs a dynamic route map according to the sea environment and generates an optimal path in combination with ocean current velocity, wind speed and fuel consumption.

[0010] Preferably, the collaborative operation module includes: The main and auxiliary collaboration unit is used to coordinate the division of tasks between the main salvage ship and the auxiliary ship. The main salvage ship completes the core tasks, and the auxiliary ship completes the logistics support and transportation tasks; A distributed communications network for real-time communications between ships and between ships and command centers; The task relay mechanism automatically dispatches nearby ships to take over the task when a ship is unable to continue operating due to lack of fuel or equipment failure.

[0011] Preferably, the dynamic monitoring and adjustment module includes: Real-time monitoring unit, used to collect and monitor operating sea area environmental data, target status and ship operation progress; Risk warning unit, used to predict potential risks based on monitoring data, including bad weather, equipment failure and fuel shortage, and trigger warning signals; The emergency response mechanism is used to dynamically adjust the salvage plan and dispatch spare vessels when risks occur.

[0012] Preferably, the risk warning unit calculates the risk probability based on historical data and current monitoring data, and generates a risk value through the following formula: Among them, R is the risk value, P i is the probability of risk occurrence, C i The cost of risk.

[0013] Preferably, the data interaction center includes: The task management center is used to aggregate the input data from the data acquisition and preprocessing modules and distribute them to the intelligent planning module; Data flow scheduling system, used to dynamically manage the data flow between modules; The operation command platform is used to provide a visual display of the operation progress and support manual intervention.

[0014] Preferably, the dynamic monitoring and adjustment module adopts a digital twin model to simulate a virtual operating environment, predict potential problems of the current solution in real time and generate an optimization solution.

[0015] The present invention provides an intelligent planning system for ocean salvage operations based on IoT big data. It has the following beneficial effects: 1. The present invention integrates multi-source sensors and Internet of Things technology to collect ship status, target characteristics and marine environment data in real time, and uses task decomposition, resource optimization allocation and path dynamic planning in the intelligent planning module to generate accurate and efficient operation plans. Compared with traditional salvage methods that rely on manual experience, the present invention achieves a significant improvement in operation efficiency. At the same time, by optimizing ship paths and task allocation, it reduces fuel consumption and equipment usage costs, making the overall operation more economical and efficient.

[0016] 2. The present invention monitors environmental conditions and ship operating status in real time through a dynamic monitoring and adjustment module. Combined with a risk warning mechanism and a dynamic task relay mechanism, it can quickly identify potential risks and adjust operation plans to ensure the safety of operations in complex marine environments. In addition, the digital twin support unit simulates potential problems in a virtual environment and optimizes adjustment plans, so that the system can quickly adapt to emergencies such as bad weather or equipment failures, thereby reducing the risk of accidents.

[0017] 3. The present invention constructs a main-auxiliary collaboration mechanism and a distributed communication network through collaborative operation modules, which can dynamically coordinate the task division and real-time information sharing of multiple ships. Through the reasonable division of labor between the main ship and the auxiliary ship, and combined with the dynamic task relay mechanism, when a ship fails due to equipment failure or lack of fuel, the system can automatically dispatch other ships to take over the task to avoid waste of resources. At the same time, the real-time progress synchronization function of multiple ships further optimizes the efficiency of resource utilization, so that complex salvage tasks can be completed efficiently. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a structural diagram of the present invention. DETAILED DESCRIPTION

[0019] The following is a description of the invention with reference to the accompanying drawings Figure 1 , the technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Example: Please see attached picture Figure 1 The embodiment of the present invention provides an intelligent planning system for ocean salvage operations based on Internet of Things big data, including: The data collection and preprocessing module is used to collect ocean-going operating environment data, ship status data and target object data through the IoT sensor network, and clean, fuse and store the collected data; In this embodiment, the data acquisition and preprocessing module is mainly used to obtain multi-dimensional data source information from the offshore salvage environment and preprocess the collected data, including data cleaning, fusion and storage. The function of this module is to provide reliable and standardized data input for the subsequent intelligent planning module to ensure the global perception and efficient planning of the salvage operation.

[0021] Specifically, this module relies on the Internet of Things technology and uses a variety of sensors and communication networks installed in ocean salvage vessels, target areas, and external environments to achieve real-time collection and dynamic processing of operation-related data. This module includes a data acquisition unit, a data cleaning unit, a data fusion unit, and a data storage unit.

[0022] Data acquisition unit In a possible implementation, the data acquisition unit obtains multi-dimensional data from the offshore operating environment through a multi-source sensor network. Specifically, it includes the following aspects: Vessel sensors: Sensors installed on operating vessels to monitor the operating status and operating capabilities of the vessel in real time.

[0023] For example, the fuel sensor can be used to detect the remaining fuel, the load sensor is used to monitor the current load status of the vessel, and the equipment status sensor monitors the operating status and health of the salvaging equipment (such as a boom or a mechanical gripper) in real time.

[0024] Environmental sensors: Buoy sensors and sonar equipment distributed in the target area can be used to obtain environmental parameters, such as: Oceanographic environmental information on current speed, wave height and sea temperature; Sonar equipment uses underwater sound wave signal echoes to obtain the specific location of the target, such as the location coordinates (x, y, z) as well as the depth and shape characteristics.

[0025] External data interface: Obtain weather forecast information such as wind speed, wind direction, precipitation, and possible typhoon path through satellites or marine weather stations. This data is essential for planning safe salvage missions.

[0026] As an option, the collected real-time data can be transmitted to the data exchange center through 5G communication modules or satellite communication systems. For long-distance ship operation environments, the high coverage of satellite communication is particularly suitable, while 5G communication provides low-latency data transmission when the network coverage is good near the coast or in the operating sea area.

[0027] It should be noted that the data collected by the above sensors may contain noise or be missing due to network transmission interruption, so it needs to be subsequently cleaned and preprocessed to ensure the integrity and accuracy of the data.

[0028] Data cleaning unit In this embodiment, the data cleaning unit is used to perform quality improvement processing on the collected data to eliminate abnormal values, fill in data gaps, and standardize the dimensions of multi-dimensional data.

[0029] As an implementation method, the data cleaning unit filters the noise data through an outlier detection algorithm. For example, the time series data is smoothed based on a sliding average method to eliminate random noise caused by sensor failure or environmental interference.

[0030] In some embodiments, in order to fill in the missing values ​​caused by network interruption or sensor failure, a filling method based on the K-nearest neighbor (KNN) algorithm can be used. Specifically, by analyzing the sensor data at adjacent time points, multiple data points closest to the current moment are selected for weighted averaging, thereby obtaining a reasonable estimate of the missing value.

[0031] It should be noted that in order to ensure the uniformity of different data sources, the data cleaning unit normalizes the multi-dimensional data collected by the sensor. For example, the dimensions of ocean current speed (unit: m / s), wind speed (unit: km / h) and load (unit: ton) are quite different, so the following normalization formula can be used: in: X is the original data; X min and X max are the minimum and maximum values ​​of the data respectively; X' is the normalized data.

[0032] Through normalization, all data are mapped to the interval [0,1], thereby avoiding the influence of data of different dimensions on subsequent algorithm processing.

[0033] Data fusion unit In a possible implementation, the data fusion unit is used to semantically fuse data from multiple source sensors to form a unified data format.

[0034] Specifically, the data fusion unit combines the time-space synchronization algorithm and distributed fusion technology to ensure the temporal and spatial consistency between different data sources. For example, when the target location information provided by the sonar device and the environmental data of the buoy sensor are transmitted to the system at the same time, the system first calibrates the timestamp of the sensor and then performs spatial mapping according to the coordinate system of the target area to ensure that all data are integrated into a unified reference frame.

[0035] It should be noted that in order to eliminate conflicting data that may be generated by multi-source sensors (for example, two sensors have different measurements of the same parameter), the data fusion unit uses a weighted average method, and the weights are dynamically adjusted based on the historical reliability of the sensors. current , and the calculation formula of its fusion value is: in: v i is the ocean current speed measured by the i-th sensor; w i is the corresponding weight, satisfying

[0036] As an option, the data fusion unit can be combined with edge computing technology to complete preliminary data fusion locally on the sensor device, thereby reducing the pressure on network transmission and central processing.

[0037] Data storage unit In this embodiment, the data storage unit uses a distributed storage system to achieve long-term storage of historical data and high-speed processing of real-time data.

[0038] Exemplarily, HDFS (Hadoop Distributed File System) can be used as the underlying storage architecture to store data in blocks in multiple nodes and provide redundant backup functions to ensure the security and availability of massive data.

[0039] To meet the needs of real-time data processing, stream processing frameworks such as Apache Kafka can be deployed in the system to write dynamic data into the stream processing pipeline, supporting subsequent modules to quickly query real-time data.

[0040] It should be understood that the data storage unit stores both structured data (such as ship status) and unstructured data (such as sonar echo signal images) and optimizes query efficiency through an indexing mechanism. For example, a query based on the target coordinates (x, y, z) can directly call the spatial index to improve the retrieval speed.

[0041] Extension Technology In some embodiments, the data acquisition and preprocessing module can also combine artificial intelligence technology to analyze historical data to predict future environmental conditions or possible locations of targets. For example, by training the time series data of ocean current speed through a long short-term memory network (LSTM), the distribution of ocean currents in the next time period can be predicted to provide guidance for path planning.

[0042] It should be noted that although this embodiment focuses on the application scenario of ocean salvage operations, the above data collection and preprocessing technology is also applicable to other complex marine engineering tasks, such as deep-sea exploration, marine garbage cleaning or marine energy development.

[0043] Intelligent planning module, which is used to decompose the ocean salvage operation tasks, allocate vessel resources and optimize the path based on the data processed by the data acquisition and preprocessing modules, and generate the optimal planning scheme for the salvage operation; In this embodiment, the intelligent planning module is responsible for generating an optimized planning scheme for ocean salvage operations based on preprocessed data, including tasks decomposition, ship resource allocation, path optimization, and salvage strategy recommendation. Through this module, it is possible to achieve reasonable planning of complex salvage tasks, make full use of ship resources, improve salvage efficiency, and provide flexible response plans in a dynamic environment. Specifically, the intelligent planning module completes the entire process from salvage task analysis to operation plan generation through the collaborative work of the task modeling unit, resource allocation unit, path planning unit, and salvage strategy recommendation unit.

[0044] Mission Modeling Unit In this embodiment, the task modeling unit is used to decompose the overall salvage operation task into a number of subtasks and perform parameterized modeling on key elements of the task.

[0045] In one possible implementation, the task modeling unit first analyzes the characteristics of the target object (such as size, weight, and location) and environmental conditions (such as ocean currents and wind speed), and divides the overall task into three subtasks: target positioning, salvage operations, and transportation.

[0046] It should be noted that the core of task modeling is the parameterized representation of key elements. For example, the state of the target object can be represented as: Target={(x,y,z),W,D} Among them, (x, y, z) are the three-dimensional coordinates of the target object, W is the weight, and D is the size.

[0047] The parameters of the operating environment can be expressed as: Environment = {v current ,h wave ,v wind} Among them, v current is the ocean current speed, h wave is the wave height, v wind is the wind speed.

[0048] In addition, the parameters of the vessel performance can be expressed as: Vessel={C max ,F max ,D cap} Among them, C max is the load capacity, F max is the maximum fuel capacity, D cap The capacity of the lifting equipment.

[0049] As an option, the mission modeling unit can also combine historical data to predict the location of the target. For example, in some cases, the target may drift due to ocean currents and wind speeds, and the mission modeling unit can estimate the future location of the target through the trajectory analysis model.

[0050] Resource Allocation Unit In this embodiment, the resource allocation unit is used to generate a task allocation plan for the vessel based on the task modeling results and the available vessel resources. The goal of this unit is to optimize the salvage efficiency, reduce the operation cost, and ensure the safety of the operation.

[0051] In a possible implementation, the resource allocation unit allocates ship resources by constructing an optimization model. The optimization objective can be expressed as: minZ=αTtotal +βF total Among them, T total is the total time to complete the task, F total is the total amount of fuel consumption, α and β are weight coefficients used to balance the importance of time and fuel consumption.

[0052] It should be noted that the allocation of ships needs to meet the following constraints: C i ≥W,D i ≥D,F i ≤F max Among them, C i is the load requirement assigned to vessel i, D i For its lifting capacity, F i For fuel consumption.

[0053] As an option, the resource allocation unit uses a genetic algorithm to generate an optimal allocation solution. Specifically, the implementation of the algorithm includes the following steps: Initialize the population: randomly generate several task allocation schemes; Fitness function: Take the optimization target Z as the fitness value; Selection and crossover: Generate a new generation of allocation schemes through selection and crossover operations; Iteration: After multiple iterations, the optimal solution is output.

[0054] It should be understood that the resource allocation unit can also dynamically adjust the task allocation in combination with the current environmental conditions. For example, when a ship cannot continue to operate due to insufficient fuel, the system can reallocate other ships to take over the task.

[0055] Path planning unit In this embodiment, the path planning unit generates an optimal path from the current position to the target area for each ship by analyzing the environmental data. The optimization goal of this unit is to minimize the sailing time and fuel consumption while ensuring the safety of the path.

[0056] In a possible implementation, the path planning unit first constructs a dynamic environment route map, in which each node represents a sea area grid, and the weights between nodes are calculated by ocean current speed, wind speed and fuel consumption.

[0057] Exemplarily, the total path cost L can be expressed as: Among them, d ij is the distance between nodes i and j, w current is the influence weight of ocean current, v current,ij is the ocean current speed along this path.

[0058] As an option, the path planning unit uses an improved ant colony algorithm to optimize the path. Specifically: Pheromone update: update pheromones according to the quality of path selection, giving priority to low-cost paths; Visibility calculation: Combine the path distance and ocean current speed to calculate the feasibility of the path; Dynamic adjustment: Replan the route when the environment changes (such as a typhoon).

[0059] It should be noted that the path planning unit can also work in conjunction with the resource allocation unit. For example, after a ship is assigned to a specific task, the path planning unit can dynamically adjust the path according to its task priority.

[0060] Salvage Strategy Recommended Unit In this embodiment, the salvage strategy recommendation unit selects the most suitable salvage method according to the characteristics of the target object and the operating environment.

[0061] In a possible implementation, the salvage strategy recommendation unit generates a salvage strategy through a rule base and an inference model. For example: When the target object is on the surface (less than 50 meters deep) and of moderate size, it is recommended to use a mechanical gripper for clamping and salvaging; when the target object is in the deep sea (more than 200 meters deep), it is recommended to use a dragging method or underwater robot-assisted salvage.

[0062] It should be understood that the salvage strategy recommendation unit can also generate a comprehensive strategy in combination with the multi-objective optimization model. For example, for a complex target (heavy weight, irregular shape), the target can be first moved to the surface by dragging, and then the lifting equipment can be used to complete the final salvage.

[0063] The collaborative operation module is used to achieve task collaboration and information sharing among multiple ships based on the optimal planning solution generated by the intelligent planning module; In this embodiment, the collaborative operation module is used to realize task collaboration, information sharing and dynamic task relay of multiple ships in ocean salvage operations. Through this module, the division of labor of different ships in salvage tasks can be coordinated, and efficient collaborative operations between ships can be ensured through real-time communication and progress synchronization.

[0064] Specifically, the collaborative operation module includes the main and auxiliary collaboration mechanism, distributed communication network, task progress synchronization unit and dynamic task relay mechanism. These sub-functional units work closely with each other to complete the full process control of multi-ship collaboration in complex tasks.

[0065] Primary and secondary collaboration mechanism In this embodiment, the main-auxiliary collaboration mechanism is responsible for coordinating the functional division of multiple vessels in the salvage operation and reasonably allocating the task roles of different vessels.

[0066] In one possible implementation, the collaborative operation module divides the ships into main salvage ships and auxiliary ships. Specifically, the main salvage ships are responsible for core tasks such as target positioning, lifting operations and target capture, while the auxiliary ships are responsible for secondary tasks, including target transportation, logistical support and monitoring of the operation site.

[0067] It should be noted that the main-auxiliary collaboration mechanism will dynamically adjust the task boundaries of the main ship and the auxiliary ship based on the performance of the ship and the current task requirements. For example, when the equipment of the main salvage ship fails, the system can assign an auxiliary ship with relevant functions to temporarily take over part of the main ship's tasks to ensure that the operation is not interrupted.

[0068] As an option, the main-auxiliary collaboration mechanism can also introduce real-time communication between the main ship and the auxiliary ship. For example, after the main salvage ship completes the capture of the target object, it can send a transportation task instruction to the auxiliary ship through the communication network, and the auxiliary ship will transport the target object to the designated location according to the instruction.

[0069] Distributed communication network In this embodiment, the distributed communication network is used to realize real-time information sharing between multiple ships and between ships and data exchange centers. The communication network is centered on low latency and high reliability to ensure the efficiency and stability of multi-ship collaborative operations.

[0070] In one possible implementation, the distributed communication network includes satellite communication and 5G communication modules. Satellite communication is suitable for offshore areas and can cover a wide range of operations, while 5G communication is suitable for near-shore operation scenarios and can provide higher communication bandwidth and lower latency.

[0071] Specifically, the distributed communication network supports the following functions: Real-time data transmission: including information such as vessel position, equipment status, fuel remaining and target status; Task status sharing: supports synchronization of task progress data between vessels to ensure consistency in collaborative work.

[0072] As an option, the distributed communication network can also introduce edge computing technology into ship communications. For example, when certain tasks require fast local processing, the ship can use edge computing nodes to complete preliminary data processing and transmit the results to the central system.

[0073] It should be noted that distributed communication networks still need to maintain communication stability in high-risk operating environments (such as severe storm conditions). Therefore, the reliability of the network can be improved by designing redundant communication paths (such as enabling satellite and 5G communications at the same time).

[0074] Task progress synchronization unit In this embodiment, the task progress synchronization unit is used to dynamically track the task completion status of each ship and synchronize the task status to the data exchange center and other collaborative ships in real time.

[0075] In one possible implementation, the task progress synchronization unit updates the task status based on a timestamp mechanism. For example, when a ship completes a specific sub-step of a task (such as completing the target location), the system generates a status update message with a timestamp and broadcasts it to all related ships.

[0076] It should be noted that the task progress synchronization unit plays a key role in the time management of tasks. For example, the system can dynamically adjust the time schedule of subsequent tasks according to the current task completion progress of each ship. For example, when an auxiliary ship delays a transportation task due to ocean currents, the system will notify the main ship in advance to adjust the subsequent operation rhythm.

[0077] As an option, the mission progress synchronization unit can also work in conjunction with the path planning unit to predict the vessel's operation time and generate an early warning when progress delays are expected.

[0078] Dynamic task relay mechanism In this embodiment, the dynamic task relay mechanism is used to dispatch other ships to take over the unfinished tasks when a ship is unable to continue to complete the task. This mechanism is particularly important when dealing with emergencies such as ship equipment failure, fuel shortage or bad weather.

[0079] Specifically, the dynamic task relay mechanism determines the current state of the ship based on real-time monitoring data. When the system detects that a ship is in an abnormal state (such as the remaining fuel is below the safety threshold), the task relay mechanism will automatically start and reallocate tasks according to the following steps: Select the ship that is closest to the current mission point and has execution capabilities from the available ships; Transmitting parameters of unfinished missions (such as target location, depth, etc.) to the replacement vessel; Dynamically adjust mission planning based on the status of the replacement vessel, such as recalculating the path or adjusting the operation time.

[0080] It should be noted that the dynamic task relay mechanism will give priority to the fuel remaining, equipment status and environmental conditions of the ship when assigning the successor task. For example, if a task requires the successor ship to have a certain deep-sea lifting capability, the system will select the ship that best meets the requirements based on the ship's equipment parameters.

[0081] As an option, the dynamic task relay mechanism can also work in conjunction with a distributed communication network and a data exchange center. For example, when multiple ships need to relay to complete a complex task, the system can simultaneously dispatch multiple replacement ships under the guidance of the data exchange center.

[0082] Extended technical content In some embodiments, the collaborative operation module can also analyze the historical data of multi-ship collaboration in combination with machine learning technology to optimize the collaboration strategy. For example, by analyzing the efficiency of primary and secondary collaboration in historical tasks, the priority of different task allocations can be adjusted.

[0083] It should be understood that although the collaborative operation module is used for ocean salvage as its core application scenario, its technical framework is also applicable to other complex multi-agent collaborative task scenarios, such as marine debris cleaning, deep-sea exploration or marine wind farm maintenance.

[0084] Dynamic monitoring and adjustment module, which is used to monitor environmental data, vessel status and operation progress in real time during ocean salvage operations, dynamically adjust salvage operation plans based on monitoring data, and trigger risk warning mechanisms; In this embodiment, the dynamic monitoring and adjustment module is used to monitor the environmental status, ship operation status and task progress of the ocean salvage operation in real time, and adjust the operation plan according to dynamic changes. Through this module, the system can flexibly respond to emergencies in a complex and changeable ocean environment to ensure the smooth progress of the task. The module includes a real-time monitoring unit, a risk warning unit, a dynamic adjustment unit and a digital twin support unit. Each unit works together to complete the whole process from data monitoring to operation adjustment.

[0085] Real-time monitoring unit In this embodiment, the real-time monitoring unit performs real-time data monitoring of the core elements of the salvage operation, including the marine environment, the state of the vessel, and the state of the target object, by accessing a multi-source data acquisition network.

[0086] In a possible implementation, the real-time monitoring unit dynamically collects the following data through environmental sensors, ship sensors, and a data exchange center: Marine environmental data: including ocean current speed, wave height, sea water temperature, wind speed and direction.

[0087] For example, the ocean current velocity v current and Langgao waveIt has a significant impact on the safety of salvage operations. The system obtains these parameters in real time and uploads them to the central server.

[0088] Vessel operation data: including fuel remaining, deadweight, equipment operation status and current position.

[0089] Specifically, the ship's sensors monitor the amount of fuel F current , triggering an early warning when it detects that the fuel level is below a safety threshold.

[0090] Target status data: The sonar system can be used to obtain the position, depth and drift speed of the target in real time.

[0091] When the target object may drift due to ocean currents, the system can capture its dynamic position changes and generate new position information (x, y, z).

[0092] As an option, the real-time monitoring unit can also compare and analyze the monitoring data in combination with historical data to identify abnormal patterns. For example, when the power consumption of a ship's equipment exceeds three standard deviations of the historical average, the system marks it as abnormal.

[0093] It should be noted that the monitoring frequency of the real-time monitoring unit can be dynamically adjusted according to the importance of the task. For example, under severe weather conditions, the system can encrypt the monitoring frequency to improve the response speed.

[0094] Risk Early Warning Unit In this embodiment, the risk warning unit is responsible for predicting and evaluating potential risks that may affect the salvage operation, and issuing warnings to relevant ships and the command center when necessary.

[0095] In a possible implementation, the risk warning unit calculates the risk value R through a risk assessment model based on historical data and current environmental data. The calculation formula of the risk value is: in: P i represents the probability of risk i occurring; C i represents the potential cost of risk i; N is the number of risk factors.

[0096] It should be noted that the risk factors of the risk warning unit may include bad weather, equipment failure, target drift beyond the expected range, etc. For example, when the wind speed v is monitored wind Exceeding the critical value v critical , the system will generate a high risk alert and recommend pausing the job.

[0097] As an option, the risk warning unit can also combine machine learning algorithms to improve the accuracy of risk prediction by analyzing historical data to train models. For example, the possibility of equipment failure can be predicted based on a decision tree model, combined with real-time power consumption and temperature change data for risk classification.

[0098] For example, when the risk value R exceeds the preset threshold R threshold When the system triggers the following warning measures: Send risk warnings to the main ship and auxiliary ships; Adjust the operation plan, such as suspending the operation or replanning the route to avoid risk areas.

[0099] Dynamic adjustment unit In this embodiment, the dynamic adjustment unit is used to update the current task plan in real time when the operating conditions change, including task allocation, path optimization and time adjustment.

[0100] In a possible implementation, the dynamic adjustment unit first determines the change of the operating conditions through real-time monitoring data. For example: When a ship's equipment detects an operational anomaly, the dynamic adjustment unit will reallocate other ships to take over its tasks; When the drift velocity v of the target drift When the planned range is exceeded, the path is replanned to track the target.

[0101] It should be noted that the task update of the dynamic adjustment unit is based on the optimization model. Specifically, the priority of task allocation can be recalculated by the following formula: in: T est Indicates the estimated completion time of the task; W risk represents the risk weight; R represents the risk value.

[0102] As an option, the dynamic adjustment unit can be combined with the path planning unit to update the ship's path in real time. For example, when the ocean current speed in a certain area is detected to increase, the system will recalculate the path to avoid the ship entering the high current area.

[0103] It should be understood that the response speed of the dynamic adjustment unit is crucial to the safety of the mission. Therefore, the unit can be combined with edge computing technology to quickly complete the adjustment calculation locally on the ship and synchronize the update with the data exchange center.

[0104] Digital Twin Support Unit In this embodiment, the digital twin support unit constructs a virtual environment to simulate various possibilities in the actual operation process in real time to support dynamic adjustment decisions.

[0105] In one possible implementation, the digital twin support unit uses sensor data and historical data to build a virtual model of the target area and the ship. Specifically: Virtual sea area model: simulate the dynamic changes of ocean currents, wave heights and wind speeds; Virtual ship model: simulates the operating status of the ship, including fuel consumption, equipment load, etc.

[0106] It should be noted that the digital twin support unit can verify the feasibility of the adjustment plan in the simulation environment. For example, when the system recommends replanning the path, the digital twin model can calculate the cost and time of the adjusted path and compare it with the original plan.

[0107] As an option, the digital twin support unit can also be used to predict potential problems. For example, when simulating the possible consequences of a piece of equipment being overloaded, the system generates early warnings and recommends replacing mission equipment.

[0108] Extended technical content In some embodiments, the dynamic monitoring and adjustment module can also combine deep learning technology to model dynamic change patterns under complex operating conditions. For example, the wave image data is processed by a convolutional neural network (CNN) to predict the wave height change trend.

[0109] It should be understood that although the dynamic monitoring and adjustment module is mainly used in ocean salvage operations, its technical framework is also applicable to other marine engineering scenarios, such as deep-sea exploration, offshore wind farm operation and maintenance, etc. The data interaction center is used to manage the data flow between modules and coordinate task allocation and program execution.

[0110] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent planning system for ocean salvage operations based on IoT big data, characterized in that: include: The data collection and preprocessing module is used to collect ocean-going operating environment data, ship status data and target object data through the IoT sensor network, and clean, fuse and store the collected data; Intelligent planning module, which is used to decompose the ocean salvage operation tasks, allocate vessel resources and optimize the path based on the data processed by the data acquisition and preprocessing modules, and generate the optimal planning scheme for the salvage operation; The collaborative operation module is used to achieve task collaboration and information sharing among multiple ships based on the optimal planning solution generated by the intelligent planning module; Dynamic monitoring and adjustment module, which is used to monitor environmental data, vessel status and operation progress in real time during ocean salvage operations, dynamically adjust salvage operation plans based on monitoring data, and trigger risk warning mechanisms; The data interaction center is used to manage the data flow between modules and coordinate task allocation and program execution.

2. According to claim 1, an intelligent planning system for ocean salvage operations based on Internet of Things big data is characterized in that: The data acquisition and preprocessing module includes: Ship sensors are used to collect information about the ship’s fuel level, load, and equipment operating status; Environmental sensors, used to collect information on ocean current velocity, wave height, and wind speed in the marine environment; External meteorological data interface, used to obtain weather forecast data from weather stations or satellites; The data cleaning and fusion unit is used to filter outliers, fill in missing values ​​and normalize the collected data.

3. According to claim 1, an intelligent planning system for ocean salvage operations based on Internet of Things big data is characterized in that: The intelligent planning module includes: The task modeling unit is used to decompose the overall salvage task into subtasks of target positioning, salvage operation and target transportation; Resource allocation unit, used to optimize the task allocation of multiple ships using heuristic algorithms based on task requirements, ship performance and environmental conditions; The path planning unit is used to generate the optimal navigation path for the ship by combining environmental and economic factors such as ocean current velocity, wind speed and fuel consumption; The salvage strategy recommendation unit is used to select the appropriate salvage method according to the size, weight and depth of the target.

4. According to claim 1, an intelligent planning system for ocean salvage operations based on Internet of Things big data is characterized in that: The resource allocation unit generates a task allocation scheme based on the following optimization objectives: Maximize efficiency: minimize operation time T total ; Cost minimization: Reduce fuel consumption F total ; Safety optimization: Prioritize vessels that are adapted to environmental conditions.

5. According to claim 1, the intelligent planning system for ocean salvage operations based on Internet of Things big data is characterized in that: The path planning unit adopts a dynamic path planning algorithm, which constructs a dynamic route map according to the sea environment and generates an optimal path in combination with ocean current velocity, wind speed and fuel consumption.

6. The intelligent planning system for ocean salvage operations based on Internet of Things big data according to claim 1 is characterized in that: The collaborative operation module includes: The main and auxiliary collaboration unit is used to coordinate the division of tasks between the main salvage ship and the auxiliary ship. The main salvage ship completes the core tasks, and the auxiliary ship completes the logistics support and transportation tasks; A distributed communications network for real-time communications between ships and between ships and command centers; The task relay mechanism automatically dispatches nearby ships to take over the task when a ship is unable to continue operating due to lack of fuel or equipment failure.

7. The intelligent planning system for ocean salvage operations based on Internet of Things big data according to claim 1 is characterized in that: The dynamic monitoring and adjustment module includes: Real-time monitoring unit, used to collect and monitor operating sea area environmental data, target status and ship operation progress; Risk warning unit, used to predict potential risks based on monitoring data, including bad weather, equipment failure and fuel shortage, and trigger warning signals; The emergency response mechanism is used to dynamically adjust the salvage plan and dispatch spare vessels when risks occur.

8. The intelligent planning system for ocean salvage operations based on Internet of Things big data according to claim 1 is characterized in that: The risk warning unit calculates the risk probability based on historical data and current monitoring data, and generates a risk value through the following formula: Among them, R is the risk value, P i is the probability of risk occurrence, C i The cost of risk.

9. The intelligent planning system for ocean salvage operations based on Internet of Things big data according to claim 1 is characterized in that: The data interaction center includes: The task management center is used to aggregate the input data from the data acquisition and preprocessing modules and distribute them to the intelligent planning module; Data flow scheduling system, used to dynamically manage the data flow between modules; The operation command platform is used to provide a visual display of the operation progress and support manual intervention.

10. The intelligent planning system for ocean salvage operations based on Internet of Things big data according to claim 1 is characterized in that: The dynamic monitoring and adjustment module adopts a digital twin model to simulate a virtual operating environment, predict potential problems of the current solution in real time, and generate an optimization solution.

Images