Decision planning method and system for ship collaborative multi-task system

Abstract

The invention provides a ship collaborative multi-task system decision planning method and system, and relates to the technical field of ship task decision, and the method comprises the specific steps: collecting ship characteristic parameters and task parameters of each ship at the current moment, obtaining the known ship characteristic parameters of a plurality of ships, inputting the ship characteristic parameters of each ship at the current moment into the trained ship characteristic model, obtaining the characteristic coefficient of each ship, carrying out the data processing of the ship characteristic coefficient of the ship at the current moment, the environment influence coefficient and the task characteristic coefficient, generating the task adaptation coefficient of the ship at the current moment, and obtaining the task adaptation coefficient of the ship at the current moment. The task adaptation coefficients of all the ships at the current moment are ranked from large to small, a priority list is generated, and all the ships execute tasks in sequence according to the priority list. According to the method, the ship and the task can be accurately matched, the task can be efficiently executed, potential safety hazards are avoided, and reasonable priority ranking can be performed according to the emergency degree and importance of the task.

Description

Technical Field

[0001] The present invention relates to the technical field of ship mission decision making, and in particular to a ship collaborative multi-task system decision planning method and system. Background Art

[0002] The decision-making and planning method of ship collaborative multi-task system aims to formulate the optimal resource scheduling and task execution plan by comprehensively considering multiple factors of tasks, ships and environment, so as to achieve efficient and safe task completion. In practical applications, this method can improve the operating efficiency of ships, reduce costs, and increase the success rate of tasks. With the development of technology, especially the application of artificial intelligence and big data analysis, the decision-making and planning method of ship collaborative multi-task will become more and more intelligent and automated.

[0003] In existing ship collaborative operations, especially when dealing with multiple tasks concurrently, there are many technical challenges. First, ship characteristic parameters (such as ship type, load, speed, etc.) will directly affect its performance in different tasks. For example, some ships may perform well in high-speed tasks, while other ships may be more suitable for heavy-load transportation. When there are various types of tasks with different levels of urgency, how to quickly and accurately assign suitable ships to corresponding tasks has become a complex and thorny problem; secondly, changes in external environmental conditions will also bring uncertainty to ship decision-making. Fluctuations in factors such as wave height, visibility, and current speed will affect the navigation safety and operating efficiency of ships. In bad weather, ships may not be able to perform tasks according to the planned schedule, resulting in waste of resources and delays in tasks. In this case, traditional static decision-making methods often fail to reflect environmental changes in a timely manner, resulting in inefficient task execution and increased safety hazards, leading to delays in rescue operations, thereby exacerbating the consequences of accidents; in addition, due to the lack of real-time data-driven analysis, when ships face multiple tasks, it is often difficult to reasonably prioritize them according to the urgency and importance of the tasks. This static priority setting not only affects the timely execution of tasks, but may also lead to resource mismatches, causing some ships to be assigned to tasks that are not suitable for their characteristics, further reducing overall operating efficiency.

[0004] However, there are still the following deficiencies. As can be seen from the above statements, the above information disclosed in the background technology section is only used to enhance the understanding of the background of the present disclosure, so it may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of the present invention is to provide a ship collaborative multi-task system decision-making planning method and system to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A decision-making planning method for a ship cooperative multi-task system, the specific steps comprising:

[0008] S1. Collect the ship characteristic parameters, task parameters, and external environment parameters of each ship at the current moment, wherein the ship characteristic parameters include the ship load, ship speed, and ship type code reflecting the ship type, and the external environment parameters include the wave height, visibility, current speed, water temperature, and tide height at the ship, and the task parameters include the task type identification code, task urgency code, time difference between the task start time and the current time, and time required for the task, and the task type identification code and task urgency code are used to reflect the task type and task urgency of the ship respectively;

[0009] S2. Obtain several known ship characteristic parameters, determine the ship characteristic coefficient based on the expert scoring method, the ship characteristic coefficient is used to reflect the quality of the comprehensive performance of the ship, build a ship characteristic model, take the known ship characteristic parameters as input, and use the corresponding ship characteristic coefficient as a label training model to obtain a trained ship characteristic model;

[0010] S3. Input the ship characteristic parameters of each ship at the current moment into the trained ship characteristic model to obtain the ship characteristic coefficients of each ship;

[0011] S4. Process the wind speed, wave height, visibility, current speed, water temperature and tide height collected at the current moment to generate the environmental impact coefficient at the current moment, process the task type identification code, task urgency code, time difference between the task start time and the current time, and task required time collected at the current moment to generate the task characteristic coefficient of the ship at the current moment, process the ship characteristic coefficient, environmental impact coefficient and task characteristic coefficient of the ship at the current moment to generate the task adaptation coefficient of the ship at the current moment;

[0012] S5. Sort the task adaptation coefficients of each ship at the current moment from large to small, generate a priority list, and all ships perform tasks in sequence according to the priority list.

[0013] Furthermore, when the task type is scientific research, the ship identification code is 1; when the task type is transportation, the ship identification code is 2; when the task type is rescue, the ship identification code is 3; if the time difference between the task start time and the current time is within 3 hours, the task urgency code is 1; if the time difference between the task start time and the current time is within 2 hours, the task urgency code is 2; if the time difference between the task start time and the current time is within 1 hour, the task urgency code is 3.

[0014] Furthermore, the ship feature model is constructed by a deep neural network based on a multilayer perceptron, and the deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer, and the first hidden layer, the second hidden layer and the third hidden layer each have at least two neurons, and each uses ReLU as an activation function.

[0015] Furthermore, the wave height, visibility, current speed, water temperature and tide height collected at the current moment are processed to generate the environmental impact coefficient of the ship at the current moment, based on the following formula:

[0016]

[0017] Among them, XS hj is the environmental impact coefficient of the ship at the current moment, H is the wave height, V is the visibility, C is the current speed, T is the water temperature, T 0 is the reference temperature, L is the tidal height, L 0 is the reference tide height, α is the weight coefficient of wave height, β is the weight coefficient of visibility, γ is the weight coefficient of tide height, 0<γ<α<β<1, γ+α+β=1.

[0018] Furthermore, the task type identification code, task urgency code, time difference between task start time and current time, and task required time collected at the current moment are processed to generate the task characteristic coefficient of the ship at the current moment, based on the following formula:

[0019]

[0020] Among them, XS rw is the mission characteristic coefficient of the ship at the current moment, R type is the task type identification code, P level is the task urgency code, ET is the time required for the task, SC is the time difference between the task start time and the current time, and w 1 is the weight of the task type identification code, w 2 The weight for encoding task urgency, w 3 is the weight of the time required for the task, λ is the exponential decay coefficient, 0.1<λ<1, 0 <w 3 <w 1 <w 2 <1,w 3 +w 1 +w 2 =1.

[0021] Furthermore, the ship characteristic coefficient, environmental impact coefficient and task characteristic coefficient at the current moment are processed to generate the task adaptation coefficient of the ship at the current moment, according to the following formula:

[0022]

[0023] Among them, A s-e-t is the mission adaptation coefficient of the ship at the current moment, XS sh is the ship characteristic coefficient of the ship at the current moment.

[0024] Furthermore, when there are two or more ships with equal task adaptation coefficients, the priority of the ships is arranged according to the task urgency codes.

[0025] To achieve the above object, the present invention also provides the following technical solutions:

[0026] A ship collaborative multi-task system decision-making and planning system, used to execute any of the above-mentioned ship collaborative multi-task system decision-making and planning methods, comprising:

[0027] A data acquisition module, used to collect the ship characteristic parameters, task parameters, and external environment parameters of each ship at the current moment, wherein the ship characteristic parameters include the ship load, ship speed, and ship type code reflecting the ship type, and the external environment parameters include the wave height, visibility, current speed, water temperature, and tide height at the ship, and the task parameters include the task type identification code, the task urgency code, the time difference between the task start time and the current time, and the time required for the task, and the task type identification code and the task urgency code are used to reflect the task type and task urgency of the ship respectively;

[0028] The model building module is used to obtain several known ship characteristic parameters of the ship, determine the ship characteristic coefficient based on the expert scoring method, and the ship characteristic coefficient is used to reflect the quality of the comprehensive performance of the ship. The ship characteristic model is constructed, and the known ship characteristic parameters are used as input and the corresponding ship characteristic coefficient is used as a label training model to obtain a trained ship characteristic model;

[0029] The characteristic coefficient acquisition module is used to input the ship characteristic parameters of each ship at the current moment into the trained ship characteristic model to obtain the ship characteristic coefficient of each ship;

[0030] A data processing module is used to process the wind speed, wave height, visibility, current speed, water temperature and tide height collected at the current moment to generate the environmental impact coefficient of the ship at the current moment, process the task type identification code, task urgency code, time difference between the task start time and the current time, and time required for the task collected at the current moment to generate the task characteristic coefficient of the ship at the current moment, and process the ship characteristic coefficient, environmental impact coefficient and task characteristic coefficient of the ship at the current moment to generate the task adaptation coefficient of the ship at the current moment;

[0031] The priority sorting module is used to sort the task adaptation coefficients of each ship at the current moment from large to small, generate a priority list, and all ships perform tasks in sequence according to the priority list.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] The present invention collects the ship characteristic parameters of each ship at the current moment, and the external environment parameters at the ship, constructs a ship characteristic model, inputs the ship characteristic parameters of each ship at the current moment into the ship characteristic model after training, obtains the ship characteristic coefficient of each ship, processes the ship characteristic coefficient, environmental impact coefficient and task characteristic coefficient of the ship at the current moment, generates the task adaptation coefficient of the ship at the current moment, sorts the task adaptation coefficients of each ship at the current moment from large to small, generates a priority list, and all ships perform tasks in sequence according to the priority list. Therefore, by processing and analyzing the ship characteristic parameters, task parameters and external environment parameters of the ship, the ship and the task can be accurately matched, the task can be efficiently performed, the occurrence of safety hazards can be avoided, and reasonable priority sorting can be performed according to the urgency and importance of the task. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0035] Figure 2 This is a block diagram of the module composition of the present invention. DETAILED DESCRIPTION

[0036] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0037] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0038] Embodiment 1:

[0039] See also Figure 1 , the present invention provides a technical solution:

[0040] A decision-making planning method for a ship cooperative multi-task system, the specific steps comprising:

[0041] S1. Collect the ship characteristic parameters, task parameters, and external environment parameters of each ship at the current moment, wherein the ship characteristic parameters include the ship load, ship speed, and ship type code reflecting the ship type, and the external environment parameters include the wave height, visibility, current speed, water temperature, and tide height at the ship, and the task parameters include the task type identification code, task urgency code, time difference between the task start time and the current time, and time required for the task, and the task type identification code and task urgency code are used to reflect the task type and task urgency of the ship respectively;

[0042] S2. Obtain several known ship characteristic parameters, determine the ship characteristic coefficient based on the expert scoring method, the ship characteristic coefficient is used to reflect the quality of the comprehensive performance of the ship, build a ship characteristic model, take the known ship characteristic parameters as input, and use the corresponding ship characteristic coefficient as a label training model to obtain a trained ship characteristic model;

[0043] S3. Input the ship characteristic parameters of each ship at the current moment into the trained ship characteristic model to obtain the ship characteristic coefficients of each ship;

[0044] S4. Process the wind speed, wave height, visibility, current speed, water temperature and tide height collected at the current moment to generate the environmental impact coefficient of the ship at the current moment, process the task type identification code, task urgency code, time difference between the task start time and the current time, and task required time collected at the current moment to generate the task characteristic coefficient of the ship at the current moment, process the ship characteristic coefficient, environmental impact coefficient and task characteristic coefficient of the ship at the current moment to generate the task adaptation coefficient of the ship at the current moment;

[0045] S5. Sort the task adaptation coefficients of each ship at the current moment from large to small, generate a priority list, and all ships perform tasks in sequence according to the priority list.

[0046] Based on the above embodiments, the device and method for obtaining wind speed, wave height, visibility, current speed, water temperature and tide height are as follows:

[0047] The wave height meter is installed beside the ship or fixed on the seabed to record the changes in water surface fluctuations and measure the wave height;

[0048] Install visibility meters on ships to monitor visibility regularly or in real time;

[0049] Fix the acoustic Doppler current profiler on the seabed or hang it on a ship to monitor the flow velocity and direction of the water body in real time;

[0050] Immerse a thermocouple or thermistor temperature sensor in water to record the water temperature periodically or in real time;

[0051] Install tide gauges on the coastline or near ships to monitor tide heights in real time.

[0052] On the basis of the above embodiment, when the task type is scientific research, the ship identification code is 1, when the task type is transportation, the ship identification code is 2, when the task type is rescue, the ship identification code is 3, and the time difference between the task start time and the current time is within 3 hours, indicating that the task urgency is low, and the task urgency code is 1; the time difference between the task start time and the current time is within 2 hours, indicating that the task urgency is medium, and the task urgency code is 2; the time difference between the task start time and the current time is within 1 hour, indicating that the task urgency is high, and the task urgency code is 3. The higher the task urgency, the greater the task urgency code.

[0053] On the basis of the above embodiment, the ship feature model is constructed by a deep neural network based on a multilayer perceptron, and the deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer, and the first hidden layer, the second hidden layer and the third hidden layer each have at least two neurons, and each uses ReLU as an activation function.

[0054] In this embodiment, the input features of the deep neural network of the multilayer perceptron include three features: ship type code, corresponding ship load and ship speed.

[0055] The structure of a deep neural network with a multilayer perceptron is:

[0056] Input layer: receives input of 3 features;

[0057] The first hidden layer has 64 neurons and uses ReLU as the activation function.

[0058] The second hidden layer has 128 neurons and also uses the ReLU activation function.

[0059] The third hidden layer has 64 neurons and uses the ReLU activation function.

[0060] Output layer: has a single neuron, the ship characteristic coefficient of the ship at the current moment.

[0061] The process of training the ship feature model is as follows:

[0062] According to several known ship type codes, corresponding ship load and ship speed, the ship characteristic coefficient is determined based on the expert scoring method. The larger the ship characteristic coefficient is, the better the performance of the ship is.

[0063] The ship type code, the corresponding ship load and ship speed are used as input, and the ship characteristic coefficient is used as the output label for training. The mean square error is used as the loss function. When the mean square error is in the range of [0, 0.1], the training of the ship characteristic model is completed.

[0064] Based on the above embodiment, when the wave height H increases, the environmental risk will increase. hj The larger the wave height H and the environmental impact factor XS hj Positive correlation.

[0065] As visibility V increases and environmental risk decreases, the environmental impact coefficient XS hj will be reduced, so the visibility V and environmental impact factor XS hj Negative correlation.

[0066] The increase of ocean current velocity C will cause the environmental risk to increase, and the environmental impact coefficient XS hj will increase, so the ocean current velocity C and the environmental impact factor XS hj Positive correlation.

[0067] As the water temperature T increases, the environmental risk increases, and the environmental impact coefficient XS hjwill increase, so the water temperature T and environmental impact coefficient XS hj Positive correlation.

[0068] The increase in tidal height L will increase environmental risks, XS hj The larger the tidal height L and the environmental impact coefficient XS hj Positive correlation.

[0069] Therefore, the wave height, visibility, current speed, water temperature and tide height collected at the current moment are processed to generate the environmental impact coefficient of the ship at the current moment. The formula is as follows:

[0070]

[0071] Among them, XS hj is the environmental impact coefficient of the ship at the current moment, H is the wave height, V is the visibility, C is the current speed, T is the water temperature, T 0 is the reference temperature, L is the tidal height, L 0 is the reference tide height, α is the weight coefficient of wave height, β is the weight coefficient of visibility, and γ is the weight coefficient of tide height.

[0072] XS hj The range of the value is [0,10]. Within this range:

[0073] When XS hj When it is close to 0, it means that the ship is highly safe under the current environmental conditions;

[0074] When XS hj When it approaches 10 o'clock, it means that the ship is facing great risks under the current environmental conditions and needs to navigate with caution.

[0075] The reasons for using the above function form to express the wave height, visibility, current speed, water temperature, tide height and the environmental impact coefficient of the ship are as follows:

[0076] First, the (α·H-β·V) in the formula directly expresses the linear relationship between wave height and visibility. Higher wave heights usually increase the risk of ship navigation, while lower visibility increases the difficulty of navigation, thereby increasing the risk. The weight coefficients α and β are adjusted to reflect the actual situation in different environments.

[0077] Second, the current speed C indicates the strength of the current, which affects the navigation status of the ship. The higher the current speed, the greater the challenges and risks faced by the ship;

[0078] Temperature difference TT 0 , used to measure the difference between the current water temperature and the reference water temperature, T is the current water temperature, T 0is the reference or base temperature;

[0079] Exponential decay function When the temperature difference TT 0 When the water temperature is close to the reference temperature, the exponential term The value of is larger, which means that the ocean current velocity contributes more to the environmental impact coefficient;

[0080] As the temperature difference increases, It decreases rapidly, indicating that temperature changes will significantly reduce the impact of ocean current speed on the environment. This characteristic reflects the regulatory effect of temperature changes on the interaction between ocean currents and the environment.

[0081] The reduction of visibility V usually has a greater impact on the safety of marine operations and may lead to navigation hazards and accidents. Therefore, the model shows that the negative impact of visibility V is stronger than the positive impact of wave height H; in the actual marine environment, low visibility will immediately affect the safety of navigation, while the change of wave height H, although it may affect comfort and stability, has relatively little impact on short-term safety.

[0082] Although changes in tidal height L will affect the ship's berthing, generally speaking, in most marine operations, changes in wave height H play a more critical role in the dynamic stability and safety of the ship; during navigation, the impact of waves is often directly related to the navigation safety and stability of the ship. If the wave height H is too high, it may even cause the ship to capsize, which makes the impact of wave height more significant than the impact of tidal height L in many cases.

[0083] Therefore, the weight coefficient β of visibility is greater than the weight coefficient α of wave height, and the weight coefficient of wave height is greater than the weight coefficient γ of tide height, that is, 0<γ<α<β<1. In the absence of other factors, γ+α+β=1 is set.

[0084] Based on the above embodiment, the task type directly affects the value of the numerator. The task type identification code R type Increase (the larger the identification code, the more important the task type), the task characteristic coefficient XS rw Therefore, the task type is positively correlated with the task characteristic coefficient.

[0085] As the task urgency code increases, the task urgency increases, and the task characteristic coefficient XS rw Therefore, the task urgency coding and task characteristic coefficient XS rw Positive correlation.

[0086] The time difference SC between the task start time and the current time increases, the task urgency decreases, and the task characteristic coefficient XS rwTherefore, SC and task characteristic coefficient XS rw Negative correlation.

[0087] The time required for the task ET increases, the urgency of the task decreases, and the task characteristic coefficient XS rw Therefore, the time required for the task ET and the task characteristic coefficient XS rw Negative correlation.

[0088] Therefore, the task type identification code, task urgency code, time difference between task start time and current time, and task required time collected at the current moment are processed to generate the task characteristic coefficient of the ship at the current moment. The formula is as follows:

[0089]

[0090] Among them, XS rw is the mission characteristic coefficient of the ship at the current moment, R type is the task type identification code, P level is the task urgency code, ET is the time required for the task, SC is the time difference between the task start time and the current time, and w 1 is the weight of the task type identification code, w 2 The weight for encoding task urgency, w 3 is the weight of the time required for the task, λ is the exponential decay coefficient, 0.1<λ<1.

[0091] XS rw The range of the value is [0,10]. Within this range:

[0092] When XS hj When it is close to 0, it indicates that the urgency of the task under the current environmental conditions is low and the task can continue to be executed as planned;

[0093] When XS hj When it is close to 10 o'clock, it means that the urgency of the task is high under the environmental conditions, and it is necessary to re-evaluate the feasibility of the task and prepare to take countermeasures.

[0094] The reasons for using the above function form to express the task type identification code, task urgency code, time difference between the task start time and the current time, task time and the task characteristic coefficient of the ship are as follows:

[0095] First, e λ·SC The introduction of can effectively simulate the decay of the importance of tasks over time. When the task start time is far away from the current time, its importance decreases, and vice versa. This dynamic reflects the timeliness in actual situations.

[0096] Second, in the processing of the task time ET, the use of logarithmic functions can avoid the negative impact of too long time on the characteristic coefficient. This method ensures that even if the task takes a long time, the calculation of the characteristic coefficient remains within a reasonable range.

[0097] Third, the task type identification code R type :Different missions may have different natures (such as rescue, transportation, cruising, etc.), and each type of mission has different requirements for ship operations and resources;

[0098] Task urgency code P level : A higher level indicates a more urgent task. For example, urgent tasks may need to be processed immediately, while low-urgency tasks can be postponed.

[0099] w 1 、w 2 Weight is a parameter used to adjust the effect of task type and urgency on task characteristic coefficient. By setting different weights, the importance of certain factors can be emphasized according to the actual situation. In some environments, the urgency of the task may be more important (such as in emergency rescue situations), then w can be increased. 2 In other cases, the type of task may be more influential.

[0100] In most task management and scheduling systems, task urgency coding is often the most important factor. Therefore, the weight of task urgency coding is w 2 It is usually set high to ensure that important tasks are processed in a timely manner.

[0101] The weight of the task type identification code w 1 The weight of the task type identifier w will vary according to the complexity and processing requirements of different types of tasks. In some cases, specific types of tasks require more resources or time, so the weight of the task type identifier w 1 will be higher than the weight w of the time required for the task 3 .

[0102] The weight of the time required for the task w 3 Typically smaller because, while time is an important consideration, in many cases it is not the only determining factor, especially when influenced by the urgency and type of task.

[0103] Therefore, the weight of the task urgency code is greater than the weight of the task type identification code, and the weight of the task type identification code is greater than the weight of the task time required, that is, 0 <w 3 <w 1 <w 2 <1, if there is no other factor affecting, set w 3 +w 1 +w2 =1.

[0104] Based on the above embodiment, the ship characteristic coefficient XS sh : Represents the performance and status of the ship. The higher the value, the more suitable the ship is for the current environment and mission.

[0105] Environmental impact factor XS hj : Describes the impact of the environment on ship performance. The lower the value, the more favorable the environmental conditions.

[0106] Task characteristic coefficient XS rw : Indicates the urgency of task execution. The larger the value, the more urgent the task.

[0107] Therefore, the ship characteristic coefficient, environmental impact coefficient and task characteristic coefficient at the current moment are processed to generate the task adaptation coefficient at the current moment, based on the following formula:

[0108]

[0109] Among them, A s-e-t is the task adaptation coefficient at the current moment, XS sh is the ship characteristic coefficient at the current moment.

[0110] For the task adaptation coefficient A s-e-t , and its range is set to [0,20].

[0111] When it is close to 0, it means that the ship, environment and mission are not well adapted and need to be optimized;

[0112] When it is close to 20, it means that the adaptability is good and the ship can complete the task efficiently in the current environment.

[0113] It reflects the relationship between ship characteristics and environmental impacts. Ship performance directly affects the mission adaptation coefficient in the numerator, while environmental impact plays a weakening role in the denominator. That is, when environmental conditions deteriorate (XS hj Increase), task adaptation coefficient A s-e-t It will be negatively affected, reflecting the negative correlation between the two.

[0114] Reflecting the influence of task characteristics, as task urgency (XS rw ) increases, the task adaptation coefficient A s-e-t It gradually decreases, indicating the negative impact of task urgency on adaptability. Since the square term is used, the impact of task urgency on the adaptability coefficient is nonlinear. The higher the urgency, the faster the adaptability decreases.

[0115] On the basis of the above embodiment, the task adaptation coefficients of each ship at the current moment are sorted from large to small to generate a priority list, and all ships perform tasks in sequence according to the priority list.

[0116] On the basis of the above embodiment, when there are two or more ships with equal task adaptation coefficients, the priority of the ships is arranged according to the task urgency codes.

[0117] See also Figure 2 , the present invention also provides a technical solution:

[0118] A ship collaborative multi-task system decision-making and planning system, used to execute any of the above-mentioned ship collaborative multi-task system decision-making and planning methods, comprising:

[0119] A data acquisition module, used to collect the ship characteristic parameters, task parameters, and external environment parameters of each ship at the current moment, wherein the ship characteristic parameters include the ship load, ship speed, and ship type code reflecting the ship type, and the external environment parameters include the wave height, visibility, current speed, water temperature, and tide height at the ship, and the task parameters include the task type identification code, the task urgency code, the time difference between the task start time and the current time, and the time required for the task, and the task type identification code and the task urgency code are used to reflect the task type and task urgency of the ship respectively;

[0120] The model building module is used to obtain several known ship characteristic parameters of the ship, determine the ship characteristic coefficient based on the expert scoring method, and the ship characteristic coefficient is used to reflect the quality of the comprehensive performance of the ship. The ship characteristic model is constructed, and the known ship characteristic parameters are used as input and the corresponding ship characteristic coefficient is used as a label training model to obtain a trained ship characteristic model;

[0121] The characteristic coefficient acquisition module is used to input the ship characteristic parameters of each ship at the current moment into the trained ship characteristic model to obtain the ship characteristic coefficient of each ship;

[0122] A data processing module is used to process the wind speed, wave height, visibility, current speed, water temperature and tide height collected at the current moment to generate the environmental impact coefficient of the ship at the current moment, process the task type identification code, task urgency code, time difference between the task start time and the current time, and time required for the task collected at the current moment to generate the task characteristic coefficient of the ship at the current moment, and process the ship characteristic coefficient, environmental impact coefficient and task characteristic coefficient of the ship at the current moment to generate the task adaptation coefficient of the ship at the current moment;

[0123] The priority sorting module is used to sort the task adaptation coefficients of each ship at the current moment from large to small, generate a priority list, and all ships perform tasks in sequence according to the priority list.

[0124] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0125] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by computer software, electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software depends on the specific application and design constraints of the technical solution.

[0126] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0127] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

[0128] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0129] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A decision-making and planning method for a ship cooperative multi-task system, characterized in that: The specific steps include: S1. Collect the ship characteristic parameters, task parameters, and external environment parameters of each ship at the current moment, wherein the ship characteristic parameters include the ship load, ship speed, and ship type code reflecting the ship type, and the external environment parameters include the wave height, visibility, current speed, water temperature, and tide height at the ship, and the task parameters include the task type identification code, task urgency code, time difference between the task start time and the current time, and time required for the task, and the task type identification code and task urgency code are used to reflect the task type and task urgency of the ship respectively; S2. Obtain several known ship characteristic parameters, determine the ship characteristic coefficient based on the expert scoring method, the ship characteristic coefficient is used to reflect the quality of the comprehensive performance of the ship, build a ship characteristic model, take the known ship characteristic parameters as input, and use the corresponding ship characteristic coefficient as a label training model to obtain a trained ship characteristic model; S3. Input the ship characteristic parameters of each ship at the current moment into the trained ship characteristic model to obtain the characteristic coefficients of each ship; S4. Process the wind speed, wave height, visibility, current speed, water temperature and tide height collected at the current moment to generate the environmental impact coefficient of the ship at the current moment, process the task type identification code, task urgency code, time difference between the task start time and the current time, and task required time collected at the current moment to generate the task characteristic coefficient of the ship at the current moment, process the ship characteristic coefficient, environmental impact coefficient and task characteristic coefficient of the ship at the current moment to generate the task adaptation coefficient of the ship at the current moment; S5. Sort the task adaptation coefficients of each ship at the current moment from large to small, generate a priority list, and all ships perform tasks in sequence according to the priority list.

2. The decision-making planning method for a ship cooperative multi-task system according to claim 1 is characterized in that: When the mission type is scientific research, the ship identification code is 1; when the mission type is transportation, the ship identification code is 2; when the mission type is rescue, the ship identification code is 3; if the time difference between the mission start time and the current time is within 3 hours, the mission urgency code is 1; if the time difference between the mission start time and the current time is within 2 hours, the mission urgency code is 2; if the time difference between the mission start time and the current time is within 1 hour, the mission urgency code is 3.

3. The decision-making and planning method for a ship cooperative multi-task system according to claim 1, characterized in that: The ship feature model is constructed by a deep neural network based on a multilayer perceptron, and the deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer. The first hidden layer, the second hidden layer and the third hidden layer each have at least two neurons, and each uses ReLU as an activation function.

4. The decision-making and planning method for a ship cooperative multi-task system according to claim 2, characterized in that: The wave height, visibility, current speed, water temperature and tide height collected at the current moment are processed to generate the environmental impact coefficient of the ship at the current moment. The formula is as follows: Among them, XS hj is the environmental impact coefficient of the ship at the current moment, H is the wave height, V is the visibility, C is the current speed, T is the water temperature, T0 is the reference temperature, L is the tide height, L0 is the reference tide height, α is the weight coefficient of the wave height, β is the weight coefficient of visibility, γ is the weight coefficient of the tide height, 0<γ<α<β<1, γ+α+β=1.

5. The decision-making and planning method for a ship cooperative multi-task system according to claim 4, characterized in that: The task type identification code, task urgency code, time difference between the task start time and the current time, and task required time collected at the current moment are processed to generate the task characteristic coefficient of the ship at the current moment. The formula is as follows: Among them, XS rw is the mission characteristic coefficient of the ship at the current moment, R type is the task type identification code, P level is the task urgency code, ET is the time required for the task, SC is the time difference between the task start time and the current time, w1 is the weight of the task type identification code, w2 is the weight of the task urgency code, w3 is the weight of the task time required, λ is the exponential decay coefficient, 0.1<λ<1, 0 <w3<w1<w2<1,w3+w1+w2=1。 6. The decision-making and planning method for a ship cooperative multi-task system according to claim 5, characterized in that: The ship characteristic coefficient, environmental impact coefficient and mission characteristic coefficient of the ship at the current moment are processed to generate the mission adaptation coefficient of the ship at the current moment. The formula is as follows: Among them, A s-e-t is the mission adaptation coefficient of the ship at the current moment, XS sh is the ship characteristic coefficient of the ship at the current moment.

7. The decision-making and planning method for a ship cooperative multi-task system according to claim 6, characterized in that: When there are two or more ships with equal mission adaptation coefficients, the priority of the ships is arranged according to the mission urgency codes.

8. A ship collaborative multi-task system decision-making and planning system, used to execute a ship collaborative multi-task system decision-making and planning method according to any one of claims 1 to 7, characterized in that: include: A data acquisition module, used to collect the ship characteristic parameters, task parameters, and external environment parameters of each ship at the current moment, wherein the ship characteristic parameters include the ship load, ship speed, and ship type code reflecting the ship type, and the external environment parameters include the wave height, visibility, current speed, water temperature, and tide height at the ship, and the task parameters include the task type identification code, the task urgency code, the time difference between the task start time and the current time, and the time required for the task, and the task type identification code and the task urgency code are used to reflect the task type and task urgency of the ship respectively; The model building module is used to obtain several known ship characteristic parameters of the ship, determine the ship characteristic coefficient based on the expert scoring method, and the ship characteristic coefficient is used to reflect the quality of the comprehensive performance of the ship. The ship characteristic model is constructed, and the known ship characteristic parameters are used as input and the corresponding ship characteristic coefficient is used as a label training model to obtain a trained ship characteristic model; The characteristic coefficient acquisition module is used to input the ship characteristic parameters of each ship at the current moment into the trained ship characteristic model to obtain the ship characteristic coefficient of each ship; A data processing module is used to process the wind speed, wave height, visibility, current speed, water temperature and tide height collected at the current moment to generate the environmental impact coefficient of the ship at the current moment, process the task type identification code, task urgency code, time difference between the task start time and the current time, and time required for the task collected at the current moment to generate the task characteristic coefficient of the ship at the current moment, and process the ship characteristic coefficient, environmental impact coefficient and task characteristic coefficient of the ship at the current moment to generate the task adaptation coefficient of the ship at the current moment; The priority sorting module is used to sort the task adaptation coefficients of each ship at the current moment from large to small, generate a priority list, and all ships perform tasks in sequence according to the priority list.

Images