A method and system for power distribution of a combined fleet based on intelligent control

Abstract

The present invention provides a method and system for power distribution of a combined fleet based on intelligent control, which relates to the technical field of data processing. The method includes: predicting the total power demand of the fleet at a future moment according to effective operation data and historical operation data; calculating the power output capacity data of each ship based on the operation state of each ship, the maximum power output limit of the ship, the current load condition and the operation efficiency; distributing the power demand among the ships based on the power margin, power efficiency and task priority of each ship; sending corresponding power instructions to the power systems of the ships to adjust the power output of each ship; monitoring the actual operation state of the fleet, obtaining operation feedback data, comparing the operation feedback data with the power demand data, and if the deviation exceeds a preset deviation threshold, updating the effective operation data. The present invention improves the autonomy and accuracy of power distribution of the combined fleet.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a combined fleet power distribution method and system based on intelligent control. Background Art

[0002] In a ship power system, the power distribution of a combined fleet is one of the key links. In the prior art, a rule-based fixed distribution method or a simple load balancing strategy is usually adopted to distribute power resources among the ships in the fleet. Such methods rely on the historical operation data and preset parameters of the ships, and perform static or semi-static power distribution through preset power distribution ratios. Some systems also incorporate PID controllers or fuzzy control algorithms to achieve a certain degree of adaptive adjustment. In specific applications, the dispatching system mainly distributes power according to factors such as the load, speed requirement, and navigation path of the ship, so as to meet the requirements of the overall navigation task.

[0003] However, the existing combined fleet power distribution methods have certain limitations in practical applications. Taking a port tugboat fleet as an example, tugboats usually need to adjust their power output according to real-time load changes during collaborative operations. The existing methods lack the ability to deeply analyze real-time data, resulting in a lag in power distribution adjustment. Especially when dealing with sudden load changes or bad sea conditions, the system often cannot respond quickly, and it is easy to occur that some tugboats are overloaded with power while other tugboats have redundant power. This not only affects the overall power economy of the fleet, but also may cause abnormal wear of the tugboat equipment and shorten the service life of the equipment. Therefore, how to achieve more accurate and efficient power distribution based on intelligent control means has become an urgent problem to be solved in the current technology. Summary of the Invention

[0004] The purpose of the present invention is to provide a combined fleet power distribution method and system based on intelligent control, aiming to solve the problems mentioned in the background art.

[0005] To solve the above technical problems, the technical solution of the present invention is as follows:

[0006] In the first aspect, a combined fleet power distribution method based on intelligent control, the method includes:

[0007] Predict the total power demand of the fleet at a future moment based on effective operation data and historical operation data to obtain power demand data;

[0008] Based on the power demand data, combined with the operation status of each ship, calculate the power output capacity data of each ship based on the maximum power output limit, current load condition, and operation efficiency of the ship;

[0009] Based on the power demand data and power output capacity data, allocate the power demand among the ships according to the power margin, power efficiency, and task priority of each ship to generate power allocation data;

[0010] According to the power allocation data, send corresponding power commands to the power systems of each ship to adjust the power output of each ship;

[0011] Monitor the actual operating status of the fleet, obtain operation feedback data, compare the operation feedback data with the power demand data. If the deviation exceeds the preset deviation threshold, update the effective operation data and power demand data, and re - perform power allocation.

[0012] Preferably, according to the effective operation data and historical operation data, predict the total power demand of the fleet at a future time to obtain power demand data, including:

[0013] Construct a time series for the effective operation data, extract dynamic features including the position change rate, speed change gradient, and load fluctuation range to form feature sequence data;

[0014] Use the sliding window method to divide the historical operation data, match the data within each sliding window with the feature sequence data to capture the change trend in the historical data and obtain trend data;

[0015] According to the trend data, construct a demand prediction model with a multi - stage input structure, and calculate the short - term power demand value and the medium - term power demand value respectively;

[0016] Perform weighted fusion on the short - term power demand value and the medium - term power demand value to obtain power demand data.

[0017] Preferably, according to the power demand data, combined with the operating status of each ship, calculate the power output capacity data of each ship based on the maximum power output limit, current load condition, and operating efficiency of the ship, including:

[0018] Based on the propulsion system specifications of the ship in the current voyage segment, determine its maximum output power parameter to generate a maximum output parameter set;

[0019] Based on the current load condition and operating efficiency of the ship, calculate the actual available output ratio through the current load ratio, propulsion resistance, and unit power energy consumption to form an output adjustment coefficient;

[0020] Match the maximum output parameter set with the output adjustment coefficient ship - by - ship, calculate the corresponding available output power to form preliminary power output capacity data;

[0021] Calculate the ship operation stability within a preset time period based on historical operation data, so as to correct the preliminary power output capacity data and generate power output capacity data.

[0022] Preferably, based on the power demand data and the power output capacity data, and based on the power margin, power efficiency, and task priority of each ship, distribute the power demand among the ships to generate power distribution data, including:

[0023] Calculate the power margin of each ship according to the power output capacity data to generate a margin data set, where the power margin is the power output capacity data minus the power required for its basic navigation;

[0024] Normalize the margin data set, and combine the unit power consumption rate and the current operation task weight of the corresponding ship to generate an allocation priority matrix;

[0025] According to the allocation priority matrix, allocate the power demand data step by step from top to bottom according to the task priority to generate initial allocation data;

[0026] Adjust the initial allocation data to ensure that the single-ship allocation value does not exceed the upper limit of its power output capacity data to obtain power distribution data.

[0027] Preferably, monitor the actual operation status of the fleet, obtain operation feedback data, compare the operation feedback data with the power demand data, and if the deviation exceeds the preset deviation threshold, update the effective operation data and the power demand data, and re-perform power distribution, including:

[0028] Obtain the operation feedback data of each ship in real time, where the operation feedback data includes the speed deviation, the actual power consumption value, the load, and the actual and expected deviation of the task completion time;

[0029] According to the operation feedback data, calculate the actual power demand of the current ship based on the current speed, load, and actual power consumption;

[0030] Compare the actual power demand with the power demand data, and if the deviation exceeds the preset deviation threshold, trigger the dynamic update process;

[0031] In the dynamic update process, adjust the effective operation data according to the deviation between the actual power demand and the expected power demand, re-generate the effective operation data and the power demand data, and re-perform power distribution.

[0032] Preferably, calculate the ship operation stability within a preset time period based on historical operation data, so as to correct the preliminary power output capacity data and generate power output capacity data, including:

[0033] Extract the speed fluctuations, load changes, and power consumption fluctuations of each ship within a preset time period based on historical operation data to generate a stability analysis data set;

[0034] Calculate the stability index of each ship within a preset time period based on the stability analysis data set;

[0035] Normalize the stability index of each ship and associate the stability index with the preliminary power output capacity data to obtain a stability correction coefficient;

[0036] Adjust the preliminary power output capacity data according to the stability correction coefficient to generate power output capacity data.

[0037] Preferably, normalize the margin data set, and combine the unit power consumption rate and the current operation task weight of the corresponding ship to generate an allocation priority matrix, including:

[0038] Normalize the data in the margin data set to a unified range according to the margin data set to form a normalized margin data set;

[0039] Calculate the task weight coefficient of each ship according to the unit power consumption rate of the ship, combined with the urgency and importance of the current operation task, to generate a task priority data set;

[0040] Multiply the normalized power margin by the task weight coefficient according to the task priority data set and the normalized margin data set to obtain the priority weight data of each ship, and generate an allocation priority matrix.

[0041] In a second aspect, a combined fleet power distribution system based on intelligent control, the system includes:

[0042] A data acquisition module for collecting fleet operation data, including the real-time position, speed, load information, and power consumption rate of each ship, to form initial operation data;

[0043] A data preprocessing module for preprocessing the initial operation data, removing abnormal data and filling in missing data to obtain valid operation data;

[0044] A power demand calculation module for predicting the total power demand of the fleet at a future moment based on the valid operation data and historical operation data to obtain power demand data;

[0045] A power output calculation module for calculating the power output capacity data of each ship according to the power demand data, combined with the operation status of each ship, based on the maximum power output limit, current load condition, and operation efficiency of the ship;

[0046] A power distribution planning module, which is used to allocate power demand among each ship based on the power margin, power efficiency and task priority of each ship according to the power demand data and power output capacity data, and generate power distribution data;

[0047] A power distribution execution module, which is used to send corresponding power instructions to the power systems of each ship according to the power distribution data to adjust the power output of each ship;

[0048] A feedback adjustment module, which is used to monitor the actual operation status of the fleet, obtain operation feedback data, compare the operation feedback data with the power demand data, and if the deviation exceeds the preset deviation threshold, update the effective operation data and power demand data, and re-perform power distribution.

[0049] The above solutions of the present invention at least include the following beneficial effects:

[0050] First of all, by collecting data such as the real-time position, speed, load and power consumption rate of the fleet, the present invention can generate accurate initial operation data, and remove abnormal data and complete missing data through preprocessing, ensuring the integrity and reliability of the data. This step improves the system's perception ability of the actual operation of the fleet, and provides solid data support for subsequent power demand prediction.

[0051] Secondly, the present invention adopts a time series analysis method in power demand prediction. Combining the historical operation data and real-time data of the fleet, it can more accurately predict the power demand at future moments. This method overcomes the drawbacks of static allocation in the prior art. Especially when dealing with sudden load changes and bad sea conditions, the present invention can adjust the power distribution in real time, avoiding overload or redundancy caused by system lag, and ensuring the efficient operation of the fleet under complex conditions.

[0052] Furthermore, the present invention combines the actual operation status, maximum power output limit, load condition and operation efficiency of each ship to calculate the power output capacity of each ship, and based on this, accurately allocates the power demand. By dynamically adjusting the power output capacity of each ship, the present invention can effectively avoid power imbalance between ships, reduce energy waste, and at the same time avoid overload loss of equipment, significantly extending the service life of ship equipment.

[0053] In addition, the system also monitors the feedback data in real time, discovers and responds to operation deviations in time, and ensures automatic adjustment of power distribution when the deviation exceeds the preset threshold. This feedback mechanism improves the self-adaptability of the fleet system, enables the ship to flexibly adjust according to the actual operation situation and external environment changes, and further optimizes the power distribution and power economy of the fleet.

[0054] Generally speaking, the present invention not only improves the accuracy and flexibility of the power distribution of the fleet, but also effectively reduces energy consumption, decreases equipment wear, ensures the high efficiency, economy and safety of the fleet operation, and has significant technical advantages and application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 is a flowchart of a combined fleet power distribution method based on intelligent control provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0056] Hereinafter, exemplary embodiments of the present disclosure will be described in more detail with reference to the drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art.

[0057] As Figure 1 shown, an embodiment of the present invention proposes a combined fleet power distribution method based on intelligent control, and the method includes:

[0058] S100. Collect the operation data of the fleet, including the real-time position, speed, load information and power consumption rate of each ship, and form initial operation data;

[0059] S200. Preprocess the initial operation data, remove abnormal data and complete missing data to obtain effective operation data;

[0060] S300. Predict the total power demand of the fleet at a future moment according to the effective operation data and historical operation data to obtain power demand data;

[0061] S400. According to the power demand data, combined with the operation status of each ship, calculate the power output capacity data of each ship based on the maximum power output limit, current load condition and operation efficiency of the ship;

[0062] S500. According to the power demand data and the power output capacity data, distribute the power demand among the ships based on the power margin, power efficiency and task priority of each ship to generate power distribution data;

[0063] S600. According to the power distribution data, send corresponding power instructions to the power systems of each ship to adjust the power output of each ship;

[0064] S700 monitors the actual operating status of the fleet, obtains operation feedback data, compares the operation feedback data with the power demand data. If the deviation exceeds the preset deviation threshold, the effective operation data and the power demand data are updated, and the power distribution is performed again.

[0065] In the embodiments of the present invention, by collecting the real-time operation data of the fleet, including the speed, position, load information and power consumption rate of each ship, a comprehensive and accurate data basis is provided for further processing and analysis. The initial data is preprocessed to remove outliers and fill in missing values, thus ensuring the reliability and accuracy of subsequent data analysis. This process can effectively eliminate the errors caused by incomplete or inaccurate data, thereby enhancing the system's ability to predict the total power demand of the fleet.

[0066] Furthermore, by combining the effective operation data and historical data, the present invention can predict the total power demand of the fleet at future moments. This prediction not only considers the current operating conditions of the fleet, but also integrates the past data trends, making the prediction of future power demand more accurate and avoiding the deviation that may be brought by a single data source. Accurate power demand prediction enables each ship to reasonably allocate its power output according to its specific task requirements, thereby optimizing the overall operating efficiency of the fleet.

[0067] During the power distribution process, the system automatically adjusts the power output according to the power margin, power efficiency and task priority of each ship, avoiding energy waste and uneven load among ships. This dynamic distribution mechanism ensures the optimal utilization of the fleet resources, reduces unnecessary energy consumption and reduces the risk of ship failures. By real-time monitoring the operating status of the fleet, timely obtaining feedback data, and comparing it with the predicted power demand, the system can adjust the power distribution when the deviation exceeds the preset threshold, ensuring that the fleet is always in the best operating state.

[0068] Among them, collecting the fleet operation data, including the real-time position, speed, load information and power consumption rate of each ship, forms the initial operation data. Specifically:

[0069] First, the operation data of each ship in the fleet is collected in real time through a data acquisition system. These data include but are not limited to the real-time position, speed, load information and power consumption rate of each ship.

[0070] Real-time position: Through the Global Positioning System (GPS) or other positioning devices, the real-time position coordinates (such as longitude and latitude) of each ship in the sea or other navigation areas are accurately obtained. This data can help the system to understand the accurate position of the ship in the water area in real time, providing a basis for subsequent navigation path planning, navigation time estimation and fleet collaborative operations.

[0071] Ship speed: The ship speed is an important parameter to measure the traveling speed of a ship and is usually measured in real time by radar, GPS or other ship speed sensors. This data helps to calculate the voyage that the ship may complete within a specific time and can also be used to adjust the power demand to ensure the timeliness and accuracy of power distribution.

[0072] Load information: The load data of the ship is obtained through load sensors or the ship's load management system. Load is a key factor affecting the power consumption, ship speed and required power of the ship. Therefore, accurate load information is crucial for calculating the power demand of the ship.

[0073] Power consumption rate: The power consumption data of the ship is usually monitored in real time by sensors, reflecting the fuel consumption or power consumption during the ship's voyage. This data helps the system to evaluate the energy use efficiency of the ship and avoid excessive energy consumption during power distribution.

[0074] Through the collection of these real-time data, the system can form initial operation data and provide reliable input data for subsequent power demand prediction and distribution. These data are further preprocessed to remove outliers and complete missing data to ensure the accuracy and integrity of the data, laying a solid foundation for subsequent analysis and decision-making.

[0075] In a preferred embodiment of the present invention, based on the effective operation data and historical operation data, the total power demand of the fleet at a future moment is predicted to obtain power demand data, including:

[0076] Construct a time series for the effective operation data, extract dynamic features including the position change rate, ship speed change gradient and load fluctuation range to form feature sequence data;

[0077] Use the sliding window method to divide the historical operation data, and match the data in each sliding window with the feature sequence data to capture the change trend in the historical data and obtain trend data;

[0078] According to the trend data, construct a demand prediction model with a multi-stage input structure, and calculate the short-term power demand value and the medium-term power demand value respectively;

[0079] Weightedly fuse the short-term power demand value and the medium-term power demand value to obtain power demand data; where,

[0080] ,

[0081] : The final total power demand, representing the total power demand of the fleet;

[0082] 、 : Weighting coefficient, satisfying , which respectively control the influence of short-term demand and medium-term demand on the total power demand;

[0083] : Short-term power demand, based on changes in ship speed, power consumption, and load fluctuations;

[0084] : Medium-term power demand, based on the long-term trends of ship speed, power consumption, and load changes;

[0085] , , : Weight coefficients in the calculation of short-term power demand, which respectively control the influence of changes in ship speed, power consumption, and load fluctuations on short-term power demand;

[0086] : Rate of change of ship speed, reflecting the change in ship speed;

[0087] : Rate of change of power consumption, reflecting the rate of change in ship power consumption;

[0088] : Rate of change of load, reflecting the rate of change in ship load;

[0089] : Ship speed;

[0090] : Power consumption;

[0091] : Load;

[0092] : Time period;

[0093] , , : Weight coefficients of the trends of ship speed, power consumption, and load changes in the medium-term demand model;

[0094] , , : Respectively represent the trend intensities of changes in ship speed, power consumption, and load;

[0095] : Maximum change in ship speed;

[0096] : Maximum change in power consumption;

[0097] : Maximum change in load;

[0098] : Wind speed disturbance correction coefficient;

[0099] : Ocean current disturbance correction coefficient;

[0100] : Section length, which refers to the distance that the ship is expected to sail;

[0101] : Average sailing speed;

[0102] : Section correction coefficient;

[0103] , , , : Unit conversion coefficient, which is respectively used to convert , , , into dimensionless numbers to unify the dimension of the calculation formula.

[0104] In the embodiment of the present invention, when predicting the total power demand of the fleet, the present invention uses the time series analysis method to construct the effective operation data, and matches the historical operation data with the current characteristic sequence data through the sliding window method, so as to identify the dynamic change trend in the ship operation. This process can capture the dynamic change characteristics such as the ship position, speed and load, and predict the future power demand based on these characteristics. This method overcomes the limitations of the traditional static prediction model, can more accurately reflect the changes of the ship in actual operation, and improves the flexibility and real-time performance of the power demand prediction.

[0105] Through the demand prediction model with a multi-stage input structure, the power demand values in the short term and medium term can be calculated respectively, and the final power demand data is obtained by weighted fusion of these two demand values. This method combines the predicted demands in different time periods, enables the system to better adapt to the changes in different sections and tasks, and thus improves the flexibility and adaptability of the fleet operation.

[0106] The core advantage of this method lies in the dynamic adjustment and real-time optimization, making the energy distribution among ships more reasonable, avoiding waste or shortage of resources, and further enhancing the overall economy and efficiency of the fleet.

[0107] Among them, when constructing the time series of the effective operation data, dynamic characteristics including the position change rate, speed change gradient and load fluctuation range are extracted to form the characteristic sequence data. Specifically:

[0108] For the effective operation data, first, a time series construction method is adopted to arrange the collected ship operation data in chronological order to form a time series. The data at each time point will include information such as the real-time position, speed, load, and power consumption of the ship. The time series data provides strong support for subsequent trend analysis and demand prediction.

[0109] Through dynamic feature extraction, the system can identify and extract key change information during ship operation, including but not limited to:

[0110] Position change rate: By analyzing the displacement of the ship within a specific time period, the position change rate of the ship can be calculated. This feature reveals the speed of position change during the ship's navigation and is crucial for understanding the ship's motion characteristics.

[0111] Speed change gradient: The speed change gradient reflects the fluctuation amplitude of the ship's speed within a certain period of time and can reveal the acceleration and deceleration trends of the ship's speed during operation. This feature helps analyze the ship's adaptability to environmental changes and plays an important role in dynamically adjusting the power.

[0112] Load fluctuation range: Through the time series analysis of the ship's load information, the load fluctuation range of the ship can be extracted. The load fluctuation may directly affect the ship's power demand, so this feature is crucial for accurately estimating the ship's power demand.

[0113] The features extracted above form the feature sequence data, which can reflect the changes of various dynamic factors during the ship's navigation and provide a key basis for subsequent power demand prediction.

[0114] Among them, the sliding window method is used to divide the historical operation data, and the data within each sliding window is matched with the feature sequence data to capture the change trend in the historical data and obtain the trend data. Specifically:

[0115] To improve the prediction accuracy of the ship operation trend, the present invention adopts the sliding window method to divide the historical operation data. The sliding window method refers to setting a window with a fixed length in the data sequence, and the data within the window will slide forward over time, and the data points in the window will be updated sequentially according to the time series.

[0116] Specifically, the time series in the historical operation data will be divided into multiple subsequences according to a fixed window size. Within each window, the system will match the feature sequence data with the historical operation data. In this way, the system can capture the change trends in the data, such as the acceleration and deceleration trends of the speed and the change patterns of the load.

[0117] The data within each sliding window is called a local data segment. In this way, the system can not only identify the change trend of each local time period, but also observe the periodic characteristics of the ship's operation from a longer time dimension. This method enables the system to accurately predict the future operating state of the ship according to the actual situation of time and environmental changes.

[0118] Among them, according to the trend data, a demand prediction model with a multi-stage input structure is constructed, and the short-term power demand value and the medium-term power demand value are calculated respectively. Specifically:

[0119] Based on the trend data obtained by the sliding window method, the present invention further constructs a demand prediction model with a multi-stage input structure. This model combines historical data of multiple stages and current dynamic characteristics, and can accurately predict the power demand of the fleet according to the actual operating state of the ship, environmental factors and task requirements.

[0120] Short-term power demand value: This value is mainly calculated based on the data trend within the current time period, reflecting the power demand of the ship in the short term. This demand prediction can quickly respond to the dynamic changes of the ship, such as sudden changes in speed or sudden increase in load, ensuring that the power distribution system can make timely adjustments to avoid power shortage or overload of the ship.

[0121] Medium-term power demand value: By analyzing the historical data of a longer time period, the system can predict the power demand of the ship in the future for a period of time. This prediction can take into account the long-term operation trend of the ship, including periodic changes in navigation, load fluctuations and other factors, providing a more robust power demand prediction result for the system.

[0122] These two power demand values (short-term and medium-term) are calculated separately and weighted and fused according to different weights, and finally accurate power demand data is generated, providing a precise basis for the power distribution of the fleet.

[0123] Among them, the short-term power demand value and the medium-term power demand value are weighted and fused to obtain the power demand data. Specifically:

[0124] In the present invention, after the short-term power demand value and the medium-term power demand value are calculated separately, the system will weight and fuse these two values according to the actual situation. The purpose of weighted fusion is to adjust the reliability of the prediction result according to the data fluctuation degree within different time periods.

[0125] The short-term power demand value is usually more sensitive to the change of real-time data, so a higher weight needs to be given during calculation to ensure that the system can quickly respond to the rapid change of the ship's state.

[0126] The medium-term power demand value takes into account the trends over a relatively long period, so its weight is relatively low and is used to smooth the prediction results of the system, avoiding excessive influence of short-term fluctuations on the prediction results.

[0127] Through weighted fusion, the system can combine the short-term and medium-term power demand prediction results to obtain more accurate and balanced power demand data, thereby making more reasonable decisions in the power distribution process.

[0128] In a preferred embodiment of the present invention, according to the power demand data, combined with the operating status of each ship, based on the maximum power output limit, current load condition and operating efficiency of the ship, calculate the power output capacity data of each ship, including:

[0129] Based on the propulsion system specifications of the ship in the current voyage segment, determine its maximum output power parameter and generate a maximum output parameter set;

[0130] Based on the current load condition and operating efficiency of the ship, calculate the actual available output ratio through the current load ratio, propulsion resistance and unit power consumption, and form an output adjustment coefficient;

[0131] Match the maximum output parameter set with the output adjustment coefficient ship by ship, calculate the corresponding available output power, and form preliminary power output capacity data;

[0132] According to the historical operation data, calculate the ship operation stability within a preset time period, so as to correct the preliminary power output capacity data and generate power output capacity data.

[0133] In the embodiment of the present invention, the present invention accurately calculates the power output capacity data of each ship by calculating the maximum power output capacity of the ship and combining the load condition and operating efficiency of the ship. Through data such as the current load ratio, propulsion resistance and unit power consumption, the system can generate an output adjustment coefficient to further correct the preliminary power output capacity data. In this way, the system not only relies on theoretical calculations, but also combines the actual operating environment and the specific situation of the ship, providing a more accurate basis for power distribution.

[0134] By calculating the stability index of the ship within a preset time period based on the historical operation data, the system can correct the power output capacity according to the ship operation stability. This method improves the adaptability of the ship under complex sea conditions and load changes, ensuring that the ship can provide sufficient and stable power output under any given working conditions.

[0135] This adjustment of the power output capacity based on stability correction not only improves the operating efficiency of the ship, but also reduces failures and equipment wear caused by insufficient power or overload, extends the service life of the ship, and improves the long-term economic benefits of the fleet.

[0136] Among them, based on the propulsion system specifications of the ship in the current voyage segment, its maximum available output power parameter is determined, and a maximum output parameter set is generated. Specifically:

[0137] During the operation of the combined fleet, to achieve precise power distribution, it is necessary to first determine the maximum power that each ship can provide in the current voyage segment. This maximum power depends on factors such as the propulsion system specifications, load status, and voyage operation conditions of each ship.

[0138] The specifications of the propulsion system include the rated output power of the engine, the efficiency of the propeller, the characteristics of the transmission system, etc. These parameters are usually given by the ship designer or manufacturer at the time of factory shipment. In actual operation, these specification parameters need to be combined with the current navigation environment and mission requirements. Based on the current voyage segment, it is necessary to correct the propulsion ability of the ship. For example, when the ship is sailing against the current or in a voyage segment with increased wind resistance, its actual available output power will be affected to a certain extent.

[0139] In addition, the load status of the ship will also affect the output performance of the propulsion system. When the ship is operating at full load, the power required to be output by the propulsion system is relatively high. At this time, the maximum output capacity needs to consider the power conversion efficiency and stability constraints of the system; while in the light load or no-load state, the propulsion system may not be able to operate at the rated power for a long time, so its maximum output power should be adjusted downward accordingly.

[0140] By comprehensively analyzing and processing the above multiple influencing factors, the system can generate a set of maximum output power parameter sets that can be dynamically updated over time for each ship. This set is the maximum output parameter set. In the subsequent power distribution process, all distribution upper limits need to be constrained by this parameter set to ensure safe and efficient navigation ability.

[0141] In a preferred embodiment of the present invention, according to the power demand data and power output ability data, based on the power margin, power efficiency, and task priority of each ship, the power demand is distributed among the ships to generate power distribution data, including:

[0142] According to the power output ability data, calculate the power margin of each ship to generate a margin data set. The power margin is the power output ability data minus the power required for its basic navigation;

[0143] Normalize the margin data set, and combine the unit power consumption rate and the current operation task weight of the corresponding ship to generate an allocation priority matrix;

[0144] According to the allocation priority matrix, allocate the power demand data level by level from top to bottom according to the task priority to generate initial allocation data;

[0145] Adjust the initial allocation data to ensure that the single-ship allocation value does not exceed the upper limit of its power output capacity data, and obtain the power allocation data.

[0146] In the embodiment of the present invention, during the power allocation process, according to the power output capacity data and power demand data of each ship, the system first calculates the power margin of each ship. The power margin refers to the remaining available power of the ship under the current load and navigation conditions, excluding the power required to complete the basic navigation tasks. By calculating the power margin and generating a margin data set, the system can effectively balance the load according to the power conditions of each ship, ensuring the reasonable allocation of the fleet's power resources among each ship.

[0147] By normalizing the margin data set and combining factors such as the unit power consumption rate of the ship and the urgency and importance of the current operation task, the system can generate an allocation priority matrix. This matrix helps the system determine which ships' burdens should be reduced first and which ships should undertake more power tasks, thereby optimizing the task execution efficiency and power utilization efficiency of the entire fleet.

[0148] During this process, the system allocates the power demand data level by level from top to bottom according to the task priority, ensuring the reasonable scheduling of each ship according to the task urgency and available capacity. The generated initial allocation data is then adjusted to ensure that the power allocation of each ship does not exceed its maximum power output capacity limit, avoiding the situation of power overload or imbalance. Through this optimized power allocation method, the fleet can efficiently complete tasks, while minimizing energy waste, improving navigation economy and extending the service life of ship equipment.

[0149] Among them, adjusting the initial allocation data to ensure that the single-ship allocation value does not exceed the upper limit of its power output capacity data and obtaining the power allocation data specifically means:

[0150] In order to achieve intelligent and dynamic power resource regulation, after initially completing the allocation of the fleet's power demand, it is necessary to adjust the initial allocation result to ensure that it meets the physical output capacity limit of each ship. This step is an indispensable part of the power allocation process and has the dual functions of restraint and safety.

[0151] During the implementation process, the system first reads the power output capacity data corresponding to each ship, which is the result of a comprehensive evaluation based on parameters such as the ship's propulsion system specifications, operating efficiency, and stability. Immediately afterwards, the system compares the initial allocated power value of each ship with the corresponding power output capacity upper limit one by one. If it is found that the allocated value of a certain ship exceeds its capacity upper limit, the adjustment mechanism will be immediately triggered.

[0152] During the adjustment process, the system will first reduce the allocation value of the ship to within the range that its output capacity can bear, avoiding risks such as system alarms, decreased power conversion efficiency, and increased component wear due to overloading. At the same time, to avoid waste of resources caused by changes in the overall allocation volume, the system will also redistribute this excess power among other ships with surplus output capacity, achieving local redistribution of power resources.

[0153] Finally, through this adjustment step, power allocation data that meets all constraint conditions is generated, ensuring that each ship operates within its physical bearing capacity and improving the overall operation stability and energy efficiency performance of the fleet.

[0154] In a preferred embodiment of the present invention, the actual operating state of the fleet is monitored to obtain operating feedback data, and the operating feedback data is compared with the power demand data. If the deviation exceeds the preset deviation threshold, the effective operating data and the power demand data are updated, and power allocation is performed again, including:

[0155] Obtain the operating feedback data of each ship in real time, where the operating feedback data includes the speed deviation, actual power consumption value, load, and the actual and expected deviation of the task completion time;

[0156] Based on the operating feedback data, calculate the actual power demand of the current ship based on the current speed, load, and actual power consumption;

[0157] Compare the actual power demand with the power demand data. If the deviation exceeds the preset deviation threshold, trigger the dynamic update process;

[0158] In the dynamic update process, adjust the effective operating data according to the deviation between the actual power demand and the expected power demand, regenerate the effective operating data and the power demand data, and perform power allocation again.

[0159] In an embodiment of the present invention, by obtaining the operating feedback data of each ship in real time, including the speed deviation, actual power consumption value, and the deviation between the task completion time and the expected time, the system can timely obtain the actual operating conditions of the ship. These feedback data are compared with the original power demand data. If the deviation exceeds the set threshold, the system will automatically trigger the dynamic update process.

[0160] In the dynamic update process, the system will correct the original effective operating data according to the deviation between the actual power demand and the expected power demand, and regenerate the power demand data. Through this process, the system can adapt to unpredictable changes during ship operation, such as sudden climate changes, speed fluctuations, or other external factors, ensuring that the fleet can always maintain an efficient and stable operating state.

[0161] At the core of this process, the introduction of real-time dynamic feedback ensures that each ship obtains reasonable power instructions according to its real-time situation, which can not only ensure the efficient operation of the ship, but also effectively avoid resource waste and energy consumption caused by data lag or prediction errors. Through continuous optimization and adjustment, the fleet management system of the present invention can adapt to complex and changing environmental conditions, improving the overall operation flexibility and resource utilization efficiency of the fleet.

[0162] In a preferred embodiment of the present invention, according to historical operation data, the ship operation stability within a preset time period is calculated, so as to correct the preliminary power output capacity data and generate power output capacity data, including:

[0163] Extract the speed fluctuation, load change and power consumption fluctuation of each ship within a preset time period according to historical operation data to generate a stability analysis data set;

[0164] Calculate the stability index of each ship within a preset time period according to the stability analysis data set;

[0165] Normalize the stability index of each ship, and associate the stability index with the preliminary power output capacity data to obtain a stability correction coefficient;

[0166] Adjust the preliminary power output capacity data according to the stability correction coefficient to generate power output capacity data; where,

[0167] ,

[0168] : The corrected power output capacity represents the actual available power of the ship;

[0169] : The maximum output power of the ship is determined by the design of the ship propulsion system;

[0170] : Output adjustment coefficient;

[0171] : Stability correction coefficient;

[0172] : Propulsion resistance ratio, representing the ratio of the actual resistance of the ship under the current load and environment to the design resistance;

[0173] : Power consumption rate per unit load, representing the power consumption per unit load;

[0174] : Current load ratio, representing the ratio of the actual load to the maximum rated load;

[0175] , , : respectively represent the influence coefficients of resistance, power consumption, and load on efficiency; these coefficients need to be determined through empirical data or model training;

[0176] , , : respectively represent the standard deviations of ship speed, power consumption, and load, which describe the fluctuation of the ship within a preset time period;

[0177] : the maximum tolerance of stability, which is the tolerance threshold set for the stability of the ship during operation;

[0178] , , : the weighting coefficients of the stability factor, which are used to weight the stability influence of the fluctuations of ship speed, power consumption, and load;

[0179] : the unit conversion coefficient, which is used to convert into dimensionless.

[0180] In the embodiment of the present invention, the operation stability correction of the ship is realized by analyzing historical operation data and extracting key data such as the speed fluctuation, load change, and power consumption fluctuation of each ship within a preset time period. By generating a stability analysis data set, the system can deeply understand the performance of each ship under different operation conditions, so as to calculate the stability index of the ship more accurately.

[0181] The stability index is associated with the preliminary power output capacity data after normalization processing to generate a stability correction coefficient. This correction coefficient can dynamically adjust the power output capacity according to the historical performance of the ship to ensure the stability and efficiency of the ship during operation. Through this method, the system can adjust its power output capacity in real time according to the actual operation performance of the ship, so as to improve the performance of the ship under various complex conditions.

[0182] This mechanism based on stability correction improves the safety and predictability of the ship during navigation, and reduces the failures and maintenance costs caused by power imbalance or overload. It ensures that the ship maintains stable operation during a long voyage, not only improves the navigation efficiency of the ship, but also extends the service life of the ship and reduces the maintenance and repair costs.

[0183] In a preferred embodiment of the present invention, the margin data set is normalized, and combined with the unit power consumption rate of the corresponding ship and the current operation task weight, a distribution priority matrix is generated, including:

[0184] Normalize the data according to the margin data set to form a normalized margin data set within a unified range;

[0185] Calculate the task weight coefficient of each ship according to the unit power consumption rate of the ship, combined with the urgency and importance of the current operation task, and generate a task priority data set;

[0186] According to the task priority data set and the normalized margin data set, multiply the normalized power margin by the task weight coefficient to obtain the priority weight data of each ship, and generate an allocation priority matrix.

[0187] In the embodiment of the present invention, by normalizing the power margin of each ship to form a margin data set within a unified range, the system can more intuitively compare the available power of each ship, ensuring that each ship can be reasonably allocated according to its remaining power and task requirements.

[0188] On this basis, combined with the urgency and importance of the current operation task, the system calculates the task weight coefficient of each ship and generates a task priority data set. This data set not only considers the current state of the ship, but also comprehensively evaluates the urgency and importance of the ship's task, thus providing a more scientific basis for subsequent power allocation.

[0189] According to the task priority data set and the normalized margin data set, the system multiplies the power margin of each ship by the task weight coefficient to obtain the priority weight data of each ship and generates the final allocation priority matrix. This priority matrix ensures the efficient completion of tasks, while avoiding waste or overloading of the power resources of any ship. Through this optimized allocation strategy, the fleet can complete tasks efficiently and balancedly, maximize the use of existing power resources, and improve the overall efficiency and economy of navigation.

[0190] Among them, calculating the task weight coefficient of each ship according to the unit power consumption rate of the ship, combined with the urgency and importance of the current operation task, and generating a task priority data set, specifically:

[0191] During the collaborative operation process of the fleet, the tasks undertaken by each ship often have different time sensitivities and strategic importance. Therefore, to achieve precise scheduling of power resources, a comprehensive evaluation model needs to be established to generate a distinguishable task priority data set.

[0192] This process first evaluates the energy efficiency level of each ship based on its unit power consumption rate. The unit power consumption rate usually refers to the amount of power consumed by a ship for each ton of cargo carried, reflecting the energy efficiency performance of the ship under a specific load. Ships with a high consumption rate have a higher energy usage cost. If the task urgency is low, their power allocation should be reduced first to optimize power economy.

[0193] Secondly, the system introduces an evaluation index for the urgency of tasks. For example, in the scenario of tugboat cooperation at a port, the tugboat responsible for assisting a large cargo ship to berth has a limited task time window and high urgency. While for a ship performing routine patrol or fleet translation, its task can be postponed and has low urgency. The system assigns an urgency weight to each task based on indicators such as the scheduling plan, arrival time, and operation sequence.

[0194] In addition, the importance of the task needs to be evaluated, that is, whether the task belongs to the critical path and whether it affects the execution efficiency of the entire navigation task or operation cycle. For example, although some tasks are not urgent, but have important dependencies on subsequent operations, they should also be prioritized in the allocation.

[0195] The system forms a unified task weight coefficient through normalizing the above multiple indicators, which serves as the core reference for power allocation ranking. Finally, a clear task priority label is established for each ship in the fleet, forming a complete dataset for guiding subsequent optimization of allocation strategies, resource pre-adjustment, and energy consumption control.

[0196] An embodiment of the present invention also provides a combined fleet power allocation system based on intelligent control, and the system includes:

[0197] A data acquisition module, which is used to acquire the operation data of the fleet, including the real-time position, speed, load information, and power consumption rate of each ship, and form initial operation data;

[0198] A data preprocessing module, which is used to preprocess the initial operation data, remove abnormal data and complete missing data to obtain effective operation data;

[0199] A power demand calculation module, which is used to predict the total power demand of the fleet at a future moment based on the effective operation data and historical operation data to obtain power demand data;

[0200] A power output calculation module, which is used to calculate the power output capacity data of each ship based on the power demand data and in combination with the operation status of each ship, based on the maximum power output limit, current load condition, and operation efficiency of the ship;

[0201] A power allocation planning module, which is used to allocate the power demand among each ship based on the power demand data and power output capacity data, based on the power margin, power efficiency, and task priority of each ship, and generate power allocation data;

[0202] A power allocation execution module, which is used to send corresponding power instructions to the power systems of each ship according to the power allocation data to adjust the power output of each ship;

[0203] A feedback adjustment module is used to monitor the actual operation status of the fleet, obtain operation feedback data, compare the operation feedback data with the power demand data. If the deviation exceeds the preset deviation threshold, the effective operation data and the power demand data are updated, and the power distribution is carried out again.

[0204] It should be noted that this system corresponds to the above method. All implementation manners in the above method embodiments are applicable to this embodiment and can also achieve the same technical effects.

[0205] An embodiment of the present invention also provides a computing device, including: a processor and a memory storing a computer program. When the computer program is run by the processor, it executes the method as described above. All implementation manners in the above method embodiments are applicable to this embodiment and can also achieve the same technical effects.

[0206] An embodiment of the present invention also provides a computer-readable storage medium storing instructions. When the instructions are run on a computer, the computer is made to execute the method as described above. All implementation manners in the above method embodiments are applicable to this embodiment and can also achieve the same technical effects.

[0207] The above are the preferred embodiments of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle described in the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A method for power distribution of a combined fleet based on intelligent control, characterized in that The method includes: Collecting the operation data of the fleet, including the real-time position, speed, load information, and power consumption rate of each ship, to form initial operation data; preprocessing the initial operation data to remove abnormal data and complete missing data, obtaining effective operation data; Predicting the total power demand of the fleet at a future moment based on the effective operation data and historical operation data, obtaining power demand data; Calculating the power output capacity data of each ship according to the power demand data and the operation status of each ship, based on the maximum power output limit, current load condition, and operation efficiency of the ship; Distributing the power demand among the ships based on the power margin, power efficiency, and task priority of each ship according to the power demand data and power output capacity data, generating power distribution data; Sending corresponding power instructions to the power systems of each ship according to the power distribution data to adjust the power output of each ship; Monitoring the actual operation status of the fleet, obtaining operation feedback data, comparing the operation feedback data with the power demand data, if the deviation exceeds the preset deviation threshold, then updating the effective operation data and power demand data, and re-performing power distribution; Predicting the total power demand of the fleet at a future moment based on the effective operation data and historical operation data, obtaining power demand data, including: Constructing a time series for the effective operation data, extracting dynamic features including the position change rate, speed change gradient, and load fluctuation range, forming feature sequence data; Dividing the historical operation data using a sliding window method, matching the data within each sliding window with the feature sequence data to capture the change trend in the historical data, obtaining trend data; Constructing a demand prediction model with a multi-stage input structure according to the trend data, calculating the short-term power demand value and the medium-term power demand value respectively; Performing weighted fusion on the short-term power demand value and the medium-term power demand value to obtain power demand data; Calculating the power output capacity data of each ship according to the power demand data and the operation status of each ship, based on the maximum power output limit, current load condition, and operation efficiency of the ship, including: Determining its maximum output power parameter based on the propulsion system specifications of the ship in the current voyage section, generating a set of maximum output parameters; Calculating the actual available output ratio through the current load ratio, propulsion resistance, and unit power consumption based on the current load condition and operation efficiency of the ship, forming an output adjustment coefficient; Matching the set of maximum output parameters with the output adjustment coefficient ship by ship, calculating the corresponding available output power, forming preliminary power output capacity data; Calculating the operation stability of the ship within a preset time period according to the historical operation data, thereby correcting the preliminary power output capacity data, generating power output capacity data.

2. The method for power distribution of a combined fleet based on intelligent control according to claim 1, wherein Distributing the power demand among the ships based on the power margin, power efficiency, and task priority of each ship according to the power demand data and power output capacity data, generating power distribution data, including: Calculate the power margin of each ship based on the power output capacity data to generate a margin data set, where the power margin is the power output capacity data minus the power required for its basic navigation; Perform normalization processing on the margin data set, and combine the unit power consumption rate and the current operation task weight of the corresponding ship to generate an allocation priority matrix; According to the allocation priority matrix, allocate the power demand data level by level from top to bottom according to the task priority to generate initial allocation data; Adjust the initial allocation data to ensure that the single-ship allocation value does not exceed the upper limit of its power output capacity data to obtain power allocation data.

3. The method for power distribution of a combined fleet based on intelligent control according to claim 2, wherein Monitor the actual operation status of the fleet, obtain operation feedback data, compare the operation feedback data with the power demand data, and if the deviation exceeds the preset deviation threshold, update the effective operation data and the power demand data, and re-perform power allocation, including: Obtain the operation feedback data of each ship in real time, where the operation feedback data includes the speed deviation, the actual power consumption value, the load, and the actual and expected deviation of the task completion time; Based on the operation feedback data, calculate the actual power demand of the current ship based on the current speed, load, and actual power consumption; Compare the actual power demand with the power demand data, and if the deviation exceeds the preset deviation threshold, trigger the dynamic update process; In the dynamic update process, adjust the effective operation data according to the deviation between the actual power demand and the expected power demand, regenerate the effective operation data and the power demand data, and re-perform power allocation.

4. A method for power distribution of a combined fleet based on intelligent control according to claim 1, characterized in that, According to the historical operation data, calculate the ship operation stability within a preset time period, so as to correct the preliminary power output capacity data to generate power output capacity data, including: Extract the speed fluctuation, load change, and power consumption fluctuation of each ship within the preset time period from the historical operation data to generate a stability analysis data set; Calculate the stability index of each ship within the preset time period according to the stability analysis data set; Perform normalization processing on the stability index of each ship, associate the stability index with the preliminary power output capacity data to obtain a stability correction coefficient; Adjust the preliminary power output capacity data according to the stability correction coefficient to generate power output capacity data.

5. A method for power distribution of a combined fleet based on intelligent control according to claim 4, characterized in that Perform normalization processing on the margin data set, and combine the unit power consumption rate and the current operation task weight of the corresponding ship to generate an allocation priority matrix, including: According to the margin data set, normalize the data to a unified range to form a normalized margin data set; According to the unit power consumption rate of the ship, combine the urgency and importance of the current operation task to calculate the task weight coefficient of each ship to generate a task priority data set; According to the task priority data set and the normalized margin data set, multiply the normalized power margin by the task weight coefficient to obtain the priority weight data of each ship to generate an allocation priority matrix.

6. A combined fleet power distribution system based on intelligent control, characterized in that, Applied to the method according to any one of claims 1 to 5, the system includes: A data acquisition module for acquiring fleet operation data, including the real-time position, speed, load information, and power consumption rate of each ship to form initial operation data; A data preprocessing module for preprocessing initial operation data, removing abnormal data and filling in missing data to obtain valid operation data; A power demand calculation module for predicting the total power demand of the fleet at a future moment based on the valid operation data and historical operation data to obtain power demand data; A power output calculation module for calculating the power output capacity data of each ship based on the power demand data, combined with the operation status of each ship, based on the maximum power output limit, current load condition and operation efficiency of the ship; A power distribution planning module for distributing the power demand among the ships based on the power demand data and power output capacity data, based on the power margin, power efficiency and task priority of each ship, to generate power distribution data; A power distribution execution module for sending corresponding power instructions to the power systems of the ships according to the power distribution data to adjust the power output of the ships; A feedback adjustment module for monitoring the actual operation status of the fleet, obtaining operation feedback data, comparing the operation feedback data with the power demand data, and if the deviation exceeds a preset deviation threshold, updating the valid operation data and power demand data and re-performing power distribution.

7. A computing device, characterized in that, Comprising: One or more processors; A storage device for storing one or more programs, which when executed by the one or more processors cause the one or more processors to implement the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, A program is stored in the computer-readable storage medium, and when the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images