A method and system for auxiliary decision-making of power switching for tugboat operation

Through the power switching assisted decision-making method of tugboat operation, the power switching analysis model and cluster analysis are used to solve the problem of inaccurate state judgment during switching of tugboat power system, the accuracy of power demand prediction and the refinement of energy consumption management are improved, and the The application and promotion of oil-electric hybrid tugs.

CN118514824BActive Publication Date: 2024-11-15SHANGHAI INTERNATIONAL PORT +2
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410985640.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-15
Estimated Expiration
2044-07-23

AI Technical Summary

Technical Problem

The existing tug power system cannot effectively judge the operating status of the tug when switching different modes, which affects the correctness and effectiveness of decision-making, resulting in inaccurate prediction of power demand, and affects the application effect and promotion prospects of oil-electric hybrid tugs.

Method used

Using the power switching assisted decision-making method of tugboat operation, a power switching analysis model is established by obtaining historical and real-time operation information, performing cluster analysis to determine the operation status, and providing power switching suggestions based on the analysis results, optimizing the model to improve the accuracy of power demand prediction .

Benefits of technology

Improve the accuracy of the power switching timing of the tugboat and the refinement of energy consumption management to ensure the safe operation and energy efficiency of the oil-electric hybrid tugboat.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118514824B_ABST
    Figure CN118514824B_ABST
Patent Text Reader

Abstract

The present invention discloses a tugboat power switching auxiliary decision method and system, which comprises the following steps: obtaining the tugboat's historical operation information and operation status, and establishing a power switching analysis model; obtaining the tugboat's real-time operation information; performing cluster analysis on the real-time operation information to determine the tugboat's operation status; inputting the real-time operation information and operation status into the power switching analysis model to obtain a tugboat power switching suggestion. By obtaining the status information to determine the tugboat's status, a machine learning method is used to realize the combination of theoretical data and actual operation experience of the tugboat's power switching timing, thereby improving the accuracy of power demand prediction and power switching prediction, and making the tugboat's energy consumption management more refined.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of port transportation informationization, and in particular to a method and system for auxiliary decision-making on power switching for tugboat operations. Background Art

[0002] Tugboats are one of the indispensable equipment in port operations. Their main function is to provide power support when ships berth or leave. Tugboats are relatively concentrated in ports and are an important source of emissions in ports.

[0003] Most traditional tugboats use direct diesel propulsion, and the power system is generally designed for 100% main engine power to ensure strong towing or thrust during tugboat operations. However, since its operations are mainly divided into three states: free navigation, escort, and auxiliary berthing and unberthing operations, the main engine is in low-load operation (free navigation, escort) for most of the working time every day. According to statistics, a tugboat is in free navigation or escort state for nearly 80% of the time, and the diesel engine runs at less than 20% load. Long-term operation at low load will lead to incomplete combustion of the diesel engine, high fuel consumption, poor emissions, and will also have an adverse effect on the service life of the diesel engine.

[0004] The new oil-electric hybrid tugboat uses an oil-electric hybrid power system as a propulsion system. It is equipped with both traditional diesel engine and motor propulsion systems. The operation mode includes three propulsion modes: traditional diesel propulsion, motor propulsion and hybrid propulsion. After the launch of the new oil-electric hybrid tugboat, it has attracted attention at home and abroad, and has been successfully applied in several large ports in my country, achieving good demonstration effects. In actual operation, diesel engine propulsion is used under high load to make the diesel engine fully burn, and motor propulsion is used under low load to save energy and reduce emissions. The hybrid propulsion mode is flexibly applied according to actual conditions to improve efficiency. The reliable switching of the power system in different modes is the key to ensure the safe operation of the tugboat. In order to achieve reliable and convenient mode switching, it is necessary to study the switching process characteristics of the oil-electric hybrid system, optimize the mode switching control measurement, and simplify the mode switching control process.

[0005] In the prior art, the switching of different modes of the tugboat power system mainly comes from personal operating experience, lacks machine-assisted decision-making, and has the problem of improper timing. When using machine-assisted decision-making, it is impossible to effectively judge the operating status of the tugboat, which affects the effectiveness of the decision. The lack of a large number of sample training will also affect the correctness of the decision. Therefore, how to effectively predict power demand and give power switching suggestions in a timely manner has become a technical difficulty in the operation of hybrid tugboats, which is related to the actual application effect and promotion prospects of hybrid tugboats. Summary of the invention

[0006] In view of the problem that the current switching of different modes of the tugboat power system cannot effectively determine the operating state of the tugboat, affecting the correctness and effectiveness of the decision, the present invention provides a tugboat operation power switching auxiliary decision-making method, which clusters the real-time operation information of the tugboat, and analyzes it to obtain the tugboat power switching suggestion, optimizes it according to the result of each operation, realizes the combination of theoretical data and actual operation experience of the tugboat operation power switching timing, and improves the accuracy of power demand prediction and power switching prediction.

[0007] To achieve the above object, the embodiments of the present invention adopt the following technical solutions:

[0008] A tugboat operation power switching auxiliary decision method comprises the following steps:

[0009] Obtain the historical operation information and operation status of the tugboat and establish a power switching analysis model;

[0010] Obtain real-time tugboat operation information;

[0011] Perform cluster analysis on real-time operation information to determine the operation status of the tugboat;

[0012] The real-time operation information and operation status are input into the power switching analysis model to obtain the tugboat power switching recommendation.

[0013] According to one aspect of the present invention, cluster analysis of real-time operation information to determine the tugboat operation status includes:

[0014] Perform initial clustering of tugboat operation information to determine whether the tugboat is in a free navigation state;

[0015] The operation information of tugboats that are not in a free navigation state is clustered twice to determine the operation status of the tugboats.

[0016] According to one aspect of the present invention, the operating status includes free navigation, escort, and assisted berthing and unberthing.

[0017] According to one aspect of the present invention, the step of obtaining historical operation information and operation status of the tugboat and establishing a power switching analysis model includes:

[0018] Obtain the tugboat's historical operation information and operation status including power switching information;

[0019] Establish a power switching analysis model and use the tugboat's historical operation information and operation status to train the power switching analysis model;

[0020] The power switching analysis model is optimized based on the power switching information.

[0021] According to one aspect of the present invention, the tugboat operation power switching auxiliary decision method further includes: executing a tugboat power switching operation according to a tugboat power switching suggestion.

[0022] According to one aspect of the present invention, the tugboat power switching auxiliary decision method further includes: recording the tugboat power switching result, calculating the optimal solution according to the power switching result, and optimizing and updating the power switching analysis model using the optimal solution.

[0023] According to one aspect of the present invention, the power switching result includes the actual energy consumption and power output performance of the task.

[0024] According to one aspect of the present invention, the acquiring of the real-time operation information of the tugboat includes: acquiring the real-time operation information of the tugboat through configured sensors.

[0025] According to one aspect of the present invention, the tugboat operation power switching auxiliary decision method further includes: using wireless communication technology to upload real-time operation information of the tugboat acquired by the sensor as input of the power switching analysis model.

[0026] A tugboat operation power switching auxiliary decision system, comprising:

[0027] A data acquisition module is used to obtain real-time operation information of the tugboat;

[0028] The status recognition module is used to perform cluster analysis on real-time operation information and determine the operation status of the tugboat;

[0029] The power switching analysis model is established based on the acquired historical operation information and operation status of the tugboat, and is used to analyze the input real-time operation information and operation status to obtain the power switching suggestion of the tugboat.

[0030] Advantages of the present invention: The auxiliary decision-making method for power switching of tugboat operation described in the present invention includes the following steps: obtaining the historical operation information and operation status of the tugboat, and establishing a power switching analysis model; obtaining the real-time operation information of the tugboat; performing cluster analysis on the real-time operation information to determine the operation status of the tugboat; inputting the real-time operation information and operation status into the power switching analysis model to obtain a power switching suggestion for the tugboat. By obtaining the status information to determine the state of the tugboat, a machine learning method is used to realize the combination of theoretical data and actual operation experience of the timing of power switching of tugboat operation, improve the accuracy of power demand prediction and power switching prediction, and make the energy consumption management of the tugboat more refined. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0032] Figure 1 This is a flow chart of the auxiliary decision method for power switching of tugboat operation according to the first embodiment of the present invention;

[0033] Figure 2 This is a flow chart of the auxiliary decision method for power switching of tugboat operation according to the second embodiment of the present invention;

[0034] Figure 3 This is a structural diagram of the auxiliary decision-making system for tugboat operation power switching according to the third embodiment of the present invention;

[0035] Figure 4 This is a schematic diagram of the structure of the auxiliary decision-making device for power switching of tugboat operations according to the fourth embodiment of the present invention. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] The terms "including" and "having" and any variations thereof in the embodiments of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product or equipment comprising a series of steps or modules is not necessarily limited to those steps or modules explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products or equipment.

[0038] The naming or numbering of the steps in the embodiments of the present invention does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The execution order of the named or numbered process steps can be changed according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved.

[0039] Reference to an "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0040] Embodiment 1

[0041] like Figure 1 As shown, a tugboat operation power switching auxiliary decision method includes the following steps:

[0042] Step S1: Obtain the historical operation information and operation status of the tugboat and establish a power switching analysis model;

[0043] Step S11: Acquire historical operation information and operation status of the tugboat including power switching information;

[0044] The historical operation information obtained includes the operation information obtained by sensors during the historical operation process, including but not limited to speed, position, wind speed, wave height and flow rate, etc., and also includes the power switching information in the driver's historical operation projects; the operation status includes free navigation, escort, and assisted berthing and unberthing (such as pushing and towing).

[0045] The operating status of a tugboat includes pushing, towing, free and escorting. When predicting the energy consumption of a tugboat, accurately identifying the current operating status is crucial for accurately predicting energy consumption. The operating status directly affects the energy consumption level of the tugboat and is crucial for assisting decision-making on tugboat power switching. The operating status can usually be identified manually or automatically based on various parameters during the tugboat operation. In addition, the operating status of the tugboat can be directly obtained based on the task information performed by the tugboat.

[0046] Step S12: Establishing a power switching analysis model, and using the tugboat's historical operation information and operation status to train the power switching analysis model;

[0047] A power switching analysis model is established, and the historical operation information of the tugboat is used as the input variable of the power switching analysis model. The operating status of the tugboat is determined by analyzing the historical operation information, and the historical operating status is compared and verified with the operating status obtained by analysis to correct the power switching analysis model; the power switching recommendation is used as the output of the optimized power switching analysis model.

[0048] The input historical operation information is preprocessed, including primary clustering and secondary clustering. The ship's speed, heading and its first-order and second-order derivatives are used as basic data through primary clustering, and the big data clustering method is used to identify the ship's free navigation state or non-free navigation state; through secondary clustering, the ship's escort or assisted berthing and unberthing state is identified.

[0049] Power switching recommendations include: for free navigation and escort status, it is recommended to use the electric mode, and for assisted berthing and unberthing status, it is recommended to use the fuel mode. At the same time, in the electric mode, record the relationship between the motor output power and the speed and heading, identify the situation of insufficient power, and recommend the use of the fuel mode.

[0050] Step S13: Optimizing the power switching analysis model according to the power switching information.

[0051] The power switching information in the historical operation information is analyzed, and a comprehensive evaluation is performed by analyzing the energy consumption and power output performance of the tasks to which it belongs. The power switching analysis model is optimized based on the comprehensive evaluation so that the power switching analysis model can output the optimal power switching timing.

[0052] Step S2: Acquire real-time operation information of the tugboat;

[0053] The real-time operation information of the tugboat is obtained through the configured sensors, which include but are not limited to speed, position, wind speed, wave height and flow rate sensors. The real-time operation information obtained includes various types of perception data, and the various types of perception data include but are not limited to internal and external operation data of the tugboat collected from fuel flow meters, speed sensors, GPS positioning systems, speed sensors, power consumption monitoring sensors and external environment sensors including wind, wave and current detection.

[0054] It is understandable that in the process of obtaining real-time operating status information of tugboats using onboard sensors, both diesel and electric tugboats may encounter multiple sources of error, which have a direct impact on the accuracy and reliability of the data. First, the accuracy error of the sensor itself is inevitable, which depends on the design, manufacturing quality and calibration status of the sensor. Secondly, if the calibration is improper, it will lead to systematic deviations, further affecting the data quality. In addition, environmental factors such as temperature, humidity and seawater salinity may also affect sensor performance and measurement results. During the data transmission process, problems such as packet loss, delay or signal interference may occur, resulting in incomplete or inaccurate received data. Time synchronization errors, that is, if the timestamp of sensor data is inaccurate or there is a deviation in the time synchronization between different sensors, may cause data alignment problems, which is particularly critical for energy consumption prediction models that rely on time series analysis. Finally, human operations, including sensor installation, maintenance and data entry processes, may also introduce errors. In order to reduce the impact of these errors on the performance of the detection system, measures can be taken, including regular calibration of sensors, selection of high-quality sensors, implementation of strict data quality control and preprocessing processes, adoption of advanced data transmission and storage technologies, and consideration of measurement errors during model training.

[0055] Wireless communication technology is used to obtain real-time operation information of the tugboat from sensors and upload it as input to the power switching analysis model. Sensors distributed throughout the tugboat use wireless communication technologies including but not limited to CAN bus, Bluetooth, Wifi, ZigBee, etc.

[0056] Step S3: performing cluster analysis on the real-time operation information to determine the operation status of the tugboat;

[0057] In the tugboat energy consumption prediction system, the operating status includes free navigation, escort, and assisted berthing and unberthing. Accurately identifying the current operating status is crucial for accurately predicting the timing of power switching.

[0058] Step S31: Perform initial clustering on the tugboat operation information to determine whether the tugboat is in a free navigation state;

[0059] The initial clustering is based on the ship's speed, heading and its first-order and second-order derivatives to perform data clustering to identify the free navigation state or non-free navigation state. The key point of identifying the free navigation and non-free navigation states through clustering is that the state changes of the tugboat in the free navigation state are variable. Since there is no need to follow or cooperate with other ships, the speed and heading of the free navigation ship change most frequently and irregularly. This irregularity will become more obvious after the introduction of the first-order and second-order derivatives of the speed and heading, making it easier to extract and identify. For a possible embodiment, the main steps of clustering identification are as follows:

[0060] Step S311: Initialization, from the collected tugboat status set D Select k The initial center point

[0061] Step S312: Initial cluster allocation, creating an initial cluster allocation Each cluster is initially empty.

[0062] Step S313: Assign data points to the nearest center point. For each cluster center and each data point Calculate the distance between them Then each data point Assigned to the cluster represented by the center point closest to it;

[0063] Step S314: Update the cluster center. For each cluster, update the cluster center according to the new average position of all points in the cluster.

[0064] Step S315: Check convergence. If the cluster allocation result remains consistent (i.e., no longer changes), the algorithm terminates. Calculate its maximum average speed And output clusters If the cluster allocation results are inconsistent, that is, the points in the cluster have changed, then return to step S313 and use the updated cluster center to redistribute the data points.

[0065] It is understandable that for automatic identification of tugboat operating status, the precautions involve the need to comprehensively utilize multiple sensor data through effective data fusion strategies, and rely on having sufficient labeled data to train machine learning models. The difficulties of automatic identification mainly focus on adapting to complex and changing operating environments and designing efficient and accurate recognition algorithms, which places high demands on the algorithm's generalization ability and recognition accuracy. In addition, the automatic identification system also needs to have the ability to process sensor data in real time to provide instant operating status information, which challenges the system's processing capabilities and algorithm efficiency.

[0066] Step S32: Perform secondary clustering on the operation information of the tugboat that is not in a free navigation state to determine the operation state of the tugboat.

[0067] Secondary clustering is to supplement the speed and heading data of large ships for secondary clustering to identify the escort state or the auxiliary docking and undocking state. After identifying that it is currently in a non-free navigation state, it is necessary to further identify the escort state and the auxiliary docking and undocking state. Since the essence of the escort state is still low-load operation that does not require additional power, it is advisable to use electric drive. The core difference between the auxiliary docking and undocking state and the escort state is that the tugboat in the escort state has a longer operating distance and a stable change in speed and heading, while the tugboat in the auxiliary docking and undocking state often moves back and forth at a low speed in a very small area. In these two states, the performance of the large ship is also very different. In the escort state, the large ship still sails autonomously, while in the auxiliary docking and undocking state, the large ship relies entirely on the tugboat to move parallel to the docking and undocking.

[0068] It is understandable that the above-mentioned state differences can be further clustered by adding the large ship speed and heading information on the basis of the primary clustering to identify the current operating state. In addition to adding the large ship information, the secondary clustering method is similar to the primary clustering method, so the program code burden can be minimized.

[0069] Step S4: input the real-time operation information and operation status into the power switching analysis model to obtain the tugboat power switching suggestion.

[0070] The power switching recommendations mainly include four types: electric drive is recommended in free navigation status, electric drive is recommended in escort status, diesel engine drive is recommended in assisted berthing and unberthing status, and the relationship between motor output power and speed and heading is recorded in electric mode to identify insufficient power and recommend the use of fuel mode.

[0071] Electric drive is recommended for free navigation, mainly due to its high energy efficiency and low emission advantages. Electric drive provides an environmentally friendly solution that can significantly reduce greenhouse gas emissions while maintaining higher energy efficiency in low-load operations. However, high-capacity and high-efficiency energy storage systems and intelligent power management systems are still the constraints of current hybrid tugboats. Under electric drive, it is necessary to pay attention to power performance and battery power in a timely manner to ensure that the vessel has sufficient endurance and optimize energy use.

[0072] Electric drive is recommended in the escort state because it can provide flexible power regulation and precise speed control, which is critical for maintaining synchronization with the host ship. The rapid response capability of the power system is conducive to dealing with emergencies that may occur during the escort process, but due to current technology, the integration of the power system and other systems of the tugboat cannot achieve a rapid and timely response. At the same time, the escort state also has the problem of battery power monitoring that occurs during free navigation.

[0073] Assisted berthing and unberthing is the main operation of tugboats. Diesel engines are recommended for assisted berthing and unberthing operations because these operations usually require greater immediate power output. Diesel engines have excellent high-load performance and can provide fast and powerful power support, especially in emergency operations. However, the challenge of using diesel engines is the need to effectively control emissions to reduce the impact on the environment, and an efficient power conversion mechanism is required to achieve a smooth switch from electricity to diesel.

[0074] In electric mode, recording the relationship between motor output power and speed and heading is essential for monitoring system performance and optimizing electric drive strategies. This continuous data collection and analysis helps identify possible power shortages and recommends switching to fuel mode in a timely manner to ensure the normal operation of the vessel.

[0075] Aiming at the problems of inaccurate and untimely identification of tugboat operation status and poor adaptability to environmental changes in auxiliary decision-making for power switching timing of tugboat berthing and unberthing operations, a method for auxiliary decision-making for power switching of tugboat operation is proposed. The method makes comprehensive use of real-time sensor data and historical energy consumption records from the tugboat, and realizes stable and high-speed identification of the current operation status of the tugboat through sophisticated feature engineering and efficient data processing technology. In particular, the classic K-means clustering method is adopted, which has a small amount of program code, fast calculation speed and high stability. Generally, only 5-10 iterations are needed to identify the tugboat operation status. Combined with the real-time data processing mechanism, it can adapt to the dynamic changes of the tugboat operation environment and ensure the real-time nature of the prediction results. The present invention successfully solves the key technical problems in auxiliary decision-making for power switching timing of tugboat berthing and unberthing operations, including the accuracy and completeness of data, the adaptability of the model and the real-time nature of the prediction, and provides an effective technical means for energy consumption management and optimization in the field of water transportation.

[0076] Embodiment 2

[0077] like Figure 2 As shown, a tugboat operation power switching auxiliary decision method includes the following steps:

[0078] Step S1: Obtain the historical operation information and operation status of the tugboat and establish a power switching analysis model;

[0079] Step S11: Acquire historical operation information and operation status of the tugboat including power switching information;

[0080] The historical operation information obtained includes the operation information obtained by sensors during the historical operation process, including but not limited to speed, position, wind speed, wave height and flow rate, etc., and also includes the power switching information in the driver's historical operation projects; the operation status includes free navigation, escort, and assisted berthing and unberthing (such as pushing and towing).

[0081] The operating status of a tugboat includes pushing, towing, free and escorting. When predicting the energy consumption of a tugboat, accurately identifying the current operating status is crucial for accurately predicting energy consumption. The operating status directly affects the energy consumption level of the tugboat and is crucial for assisting decision-making on tugboat power switching. The operating status can usually be identified manually or automatically based on various parameters during the tugboat operation. In addition, the operating status of the tugboat can be directly obtained based on the task information performed by the tugboat.

[0082] Step S12: Establishing a power switching analysis model, and using the tugboat's historical operation information and operation status to train the power switching analysis model;

[0083] A power switching analysis model is established, and the historical operation information of the tugboat is used as the input variable of the power switching analysis model. The operating status of the tugboat is determined by analyzing the historical operation information, and the historical operating status is compared and verified with the operating status obtained by analysis to correct the power switching analysis model; the power switching recommendation is used as the output of the optimized power switching analysis model.

[0084] The input historical operation information is preprocessed, including primary clustering and secondary clustering. The ship's speed, heading and its first-order and second-order derivatives are used as basic data through primary clustering, and the big data clustering method is used to identify the ship's free navigation state or non-free navigation state; through secondary clustering, the ship's escort or assisted berthing and unberthing state is identified.

[0085] Power switching recommendations include: for free navigation and escort status, it is recommended to use the electric mode, and for assisted berthing and unberthing status, it is recommended to use the fuel mode. At the same time, in the electric mode, record the relationship between the motor output power and the speed and heading, identify the situation of insufficient power, and recommend the use of the fuel mode.

[0086] Step S13: Optimizing the power switching analysis model according to the power switching information.

[0087] The power switching information in the historical operation information is analyzed, and a comprehensive evaluation is performed by analyzing the energy consumption and power output performance of the tasks to which it belongs. The power switching analysis model is optimized based on the comprehensive evaluation so that the power switching analysis model can output the optimal power switching timing.

[0088] In addition to using historical operation information to optimize the power switching analysis model, it is also possible to record the timing of each time the driver completes the power switching, as well as the energy consumption and power output performance of the task based on machine learning methods, comprehensively evaluate and learn the optimal solution, and achieve continuous optimization and updating of the algorithm.

[0089] Step S2: Acquire real-time operation information of the tugboat;

[0090] The real-time operation information of the tugboat is obtained through the configured sensors, which include but are not limited to speed, position, wind speed, wave height and flow rate sensors. The real-time operation information obtained includes various types of perception data, and the various types of perception data include but are not limited to internal and external operation data of the tugboat collected from fuel flow meters, speed sensors, GPS positioning systems, speed sensors, power consumption monitoring sensors and external environment sensors including wind, wave and current detection.

[0091] It is understandable that in the process of obtaining real-time operating status information of tugboats using onboard sensors, both diesel and electric tugboats may encounter multiple sources of error, which have a direct impact on the accuracy and reliability of the data. First, the accuracy error of the sensor itself is inevitable, which depends on the design, manufacturing quality and calibration status of the sensor. Secondly, if the calibration is improper, it will lead to systematic deviations, further affecting the data quality. In addition, environmental factors such as temperature, humidity and seawater salinity may also affect sensor performance and measurement results. During the data transmission process, problems such as packet loss, delay or signal interference may occur, resulting in incomplete or inaccurate received data. Time synchronization errors, that is, if the timestamp of sensor data is inaccurate or there is a deviation in the time synchronization between different sensors, may cause data alignment problems, which is particularly critical for energy consumption prediction models that rely on time series analysis. Finally, human operations, including sensor installation, maintenance and data entry processes, may also introduce errors. In order to reduce the impact of these errors on the performance of the detection system, measures can be taken, including regular calibration of sensors, selection of high-quality sensors, implementation of strict data quality control and preprocessing processes, adoption of advanced data transmission and storage technologies, and consideration of measurement errors during model training.

[0092] Wireless communication technology is used to obtain real-time operation information of the tugboat from sensors and upload it as input to the power switching analysis model. Sensors distributed throughout the tugboat use wireless communication technologies including but not limited to CAN bus, Bluetooth, Wifi, ZigBee, etc.

[0093] Step S3: performing cluster analysis on the real-time operation information to determine the operation status of the tugboat;

[0094] In the tugboat energy consumption prediction system, the operating status includes free navigation, escort, and assisted berthing and unberthing. Accurately identifying the current operating status is crucial for accurately predicting the timing of power switching.

[0095] Step S31: Perform initial clustering on the tugboat operation information to determine whether the tugboat is in a free navigation state;

[0096] The initial clustering is based on the ship's speed, heading and its first-order and second-order derivatives to perform data clustering to identify the free navigation state or non-free navigation state. The key point of identifying the free navigation and non-free navigation states through clustering is that the state changes of the tugboat in the free navigation state are variable. Since there is no need to follow or cooperate with other ships, the speed and heading of the free navigation ship change most frequently and irregularly. This irregularity will become more obvious after the introduction of the first-order and second-order derivatives of the speed and heading, making it easier to extract and identify. For a possible embodiment, the main steps of clustering identification are as follows:

[0097] Step S311: Initialization, from the collected tugboat status set D Select k The initial center point

[0098] Step S312: Initial cluster allocation, creating an initial cluster allocation Each cluster is initially empty;

[0099] Step S313: Assign data points to the nearest center point. For each cluster center and each data point Calculate the distance between them Then each data point Assigned to the cluster represented by the center point closest to it;

[0100] Step S314: Update the cluster center. For each cluster, update the cluster center according to the new average position of all points in the cluster.

[0101] Step S315: Check convergence. If the cluster allocation result remains consistent (i.e., no longer changes), the algorithm terminates. Calculate its maximum average speed And output clusters If the cluster allocation results are inconsistent, that is, the points in the cluster have changed, then return to step S313 and use the updated cluster center to redistribute the data points.

[0102] It is understandable that for automatic identification of tugboat operating status, the precautions involve the need to comprehensively utilize multiple sensor data through effective data fusion strategies, and rely on having sufficient labeled data to train machine learning models. The difficulties of automatic identification mainly focus on adapting to complex and changing operating environments and designing efficient and accurate recognition algorithms, which places high demands on the algorithm's generalization ability and recognition accuracy. In addition, the automatic identification system also needs to have the ability to process sensor data in real time to provide instant operating status information, which challenges the system's processing capabilities and algorithm efficiency.

[0103] Step S32: Perform secondary clustering on the operation information of the tugboat that is not in a free navigation state to determine the operation state of the tugboat.

[0104] Secondary clustering is to supplement the speed and heading data of large ships for secondary clustering to identify the escort state or the auxiliary docking and undocking state. After identifying that it is currently in a non-free navigation state, it is necessary to further identify the escort state and the auxiliary docking and undocking state. Since the essence of the escort state is still low-load operation that does not require additional power, it is advisable to use electric drive. The core difference between the auxiliary docking and undocking state and the escort state is that the tugboat in the escort state has a longer operating distance and a stable change in speed and heading, while the tugboat in the auxiliary docking and undocking state often moves back and forth at a low speed in a very small area. In these two states, the performance of the large ship is also very different. In the escort state, the large ship still sails autonomously, while in the auxiliary docking and undocking state, the large ship relies entirely on the tugboat to move parallel to the docking and undocking.

[0105] It is understandable that the above-mentioned state differences can be further clustered by adding the large ship speed and heading information on the basis of the primary clustering to identify the current operating state. In addition to adding the large ship information, the secondary clustering method is similar to the primary clustering method, so the program code burden can be minimized.

[0106] Step S4: input the real-time operation information and operation status into the power switching analysis model to obtain the tugboat power switching suggestion.

[0107] The power switching recommendations mainly include four types: electric drive is recommended in free navigation status, electric drive is recommended in escort status, diesel engine drive is recommended in assisted berthing and unberthing status, and the relationship between motor output power and speed and heading is recorded in electric mode to identify insufficient power and recommend the use of fuel mode.

[0108] Electric drive is recommended for free navigation, mainly due to its high energy efficiency and low emission advantages. Electric drive provides an environmentally friendly solution that can significantly reduce greenhouse gas emissions while maintaining higher energy efficiency in low-load operations. However, high-capacity and high-efficiency energy storage systems and intelligent power management systems are still the constraints of current hybrid tugboats. Under electric drive, it is necessary to pay attention to power performance and battery power in a timely manner to ensure that the vessel has sufficient endurance and optimize energy use.

[0109] Electric drive is recommended in the escort state because it can provide flexible power regulation and precise speed control, which is critical for maintaining synchronization with the host ship. The rapid response capability of the power system is conducive to dealing with emergencies that may occur during the escort process, but due to current technology, the integration of the power system and other systems of the tugboat cannot achieve a rapid and timely response. At the same time, the escort state also has the problem of battery power monitoring that occurs during free navigation.

[0110] Assisted berthing and unberthing is the main operation of tugboats. Diesel engines are recommended for assisted berthing and unberthing operations because these operations usually require greater immediate power output. Diesel engines have excellent high-load performance and can provide fast and powerful power support, especially in emergency operations. However, the challenge of using diesel engines is the need to effectively control emissions to reduce the impact on the environment, and an efficient power conversion mechanism is required to achieve a smooth switch from electricity to diesel.

[0111] In electric mode, recording the relationship between motor output power and speed and heading is essential for monitoring system performance and optimizing electric drive strategies. This continuous data collection and analysis helps identify possible power shortages and recommends switching to fuel mode in a timely manner to ensure the normal operation of the vessel.

[0112] Step S5: executing the tugboat power switching operation according to the tugboat power switching suggestion;

[0113] Step S6: Record the tugboat power switching result, calculate the optimal solution according to the power switching result, and use the optimal solution to optimize and update the power switching analysis model.

[0114] The power switching results include the actual energy consumption and power output performance of this task. Based on the iterative optimization of machine learning methods, it can output the optimal power switching timing recommendations.

[0115] Recording the driver's power switching timing and conducting a comprehensive evaluation based on energy consumption and power output performance to learn the optimal solution, the technical key points include establishing a comprehensive data collection system, implementing performance monitoring and analysis, developing intelligent decision-making algorithms, and designing an intuitive human-computer interaction interface. These key points work together to ensure that operational data can be captured and analyzed in real time to optimize the efficiency and performance of the power system.

[0116] The main technical core of the comprehensive evaluation method lies in dealing with the complexity of the operating environment and the diversity of data, ensuring the accuracy and real-time performance of the algorithm, achieving system integration and compatibility, and improving user acceptance and ensuring that they can use these technologies effectively.

[0117] In the process of iterative optimization using machine learning methods, the optimization of power switching timing based on machine learning involves data preprocessing and feature engineering, appropriate model selection and training, application of iterative optimization strategies, performance evaluation and model adjustment, and the establishment of real-time data integration and feedback mechanisms. These key points together form a systematic framework that aims to learn and predict the optimal power switching strategy by analyzing historical and real-time data to improve energy efficiency and the overall performance of the power system.

[0118] In the process of realizing the optimization of power switching timing based on machine learning, the technical difficulties faced include processing high-dimensional data, ensuring the generalization ability of the model, making accurate decisions in complex environments, ensuring the real-time and resource efficiency of the algorithm, and improving user acceptance and system reliability. These difficulties require developers to adopt innovative methods and technologies in the design and implementation process to ensure the effectiveness and adaptability of the system.

[0119] This embodiment uses internal and external sensors configured on the tugboat to sense real-time status information during tugboat operations, and identifies the free navigation state or non-free navigation state of the ship through a big data clustering method. After identifying the non-free navigation state, the ship's escort or auxiliary berthing and unberthing state is identified by identifying the speed and heading information of the large ship, updating the data clustering data, and outputting the optimal power switching plan. The system uses machine learning methods to record the timing of each driver completing the power switching, combined with the energy consumption and power output performance of this task, comprehensively evaluate the current selection, learn the optimal solution, and realize the continuous optimization and update of the algorithm, so as to realize the combination of theoretical data and actual operation experience of the power switching timing of the tugboat berthing and unberthing operations, thereby improving the accuracy of power demand prediction and power switching prediction, and making the energy consumption management of the tugboat more refined.

[0120] Embodiment 3

[0121] like Figure 3 As shown, a tugboat operation power switching auxiliary decision system 300 includes:

[0122] The data acquisition module 301 (sensor module) is used to obtain the real-time operation information of the tugboat, and collect the energy consumption data and various operation status data during the operation of the tugboat through sensors;

[0123] The state recognition module 302 is used to perform cluster analysis on the real-time operation information to determine the operation state of the tugboat. The speed, heading and first-order and second-order derivative information of the tugboat and the operating large ship are screened and clustered twice to realize automatic recognition of the three states of the tugboat's free navigation, escort or berthing and unberthing operation;

[0124] The power switching analysis model 303 is established based on the acquired historical operation information and operation status of the tugboat, and is used to analyze the input real-time operation information and operation status to obtain the power switching suggestion of the tugboat;

[0125] In addition, the tugboat operation power switching auxiliary decision system 300 also includes:

[0126] The power observation module 304 is used to record the relationship between the motor output power and the speed and heading, identify the power shortage situation, and assist the power switching analysis model 303 in analysis;

[0127] The work evaluation module 305 is used to record the timing of the driver's power switching, combine energy consumption and power output performance, comprehensively evaluate the current selection, and learn the optimal solution.

[0128] The machine learning optimization module 306 is used to further iterate the optimization method through a machine learning algorithm to output an optimal power switching timing recommendation.

[0129] This embodiment provides a tugboat operation power switching auxiliary decision-making system, which can implement the technical solutions described in the tugboat operation power switching auxiliary decision-making methods in Embodiment 1 and Embodiment 2. The principles of the above modules or units can be found in the corresponding contents of Embodiment 1 and Embodiment 2, and will not be repeated here.

[0130] Embodiment 4

[0131] like Figure 4 As shown, a tugboat operation power switching auxiliary decision device, the electronic device 400 includes a sensor 401, a memory 402, a processor 403, a display 404 and a ship internal communication bus 405, Figure 4 Only some components of the electronic device 400 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0132] In some embodiments, the sensor 401 may be a fuel flow meter, a rotation speed sensor, a GPS positioning system, a speed sensor, a power consumption monitoring sensor, and an external environment sensor including wind wave current detection, etc., or may be an external signal port of other internal combustion engines, motors, and ship status control systems. The sensor 401 is used to read various internal and external status indicators of the tugboat operation in real time and transmit them to the memory 402 and the processor 403.

[0133] In some embodiments, the memory 402 may be an internal storage unit of the electronic device 400, such as a hard disk or memory of the electronic device 400. In other embodiments, the memory 402 may also be an external storage device of the electronic device 400, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 400.

[0134] Furthermore, the memory 402 may include both an internal storage unit of the electronic device 400 and an external storage device. The memory 402 is used to store application software installed in the electronic device 400 and various data.

[0135] In some embodiments, the processor 403 may be a central processing unit (CPU), a microprocessor or other data processing chip, which is used to run the program code or process data stored in the memory 402, such as the auxiliary decision method for the power switching timing of the tugboat berthing and unberthing operations in the present invention.

[0136] In some embodiments, the display 403 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 403 is used to display information of the electronic device 400 and to display a visual user interface. The components 401-403 of the electronic device 400 communicate with each other via the ship's internal communication bus 405.

[0137] In some embodiments, the ship's internal communication bus 405 may be a common system bus such as a CAN bus, a ProfiBus field bus, etc. In other embodiments, the ship's internal communication bus 405 may also be a wireless communication network such as ZigBee, Bluetooth, etc., or a mixture of wireless and wired communication networks. The ship's internal communication bus 405 is used for information and data transmission.

[0138] When the processor 401 executes the auxiliary decision-making program for the power switching timing of tugboat berthing and unberthing operations in the memory 402, the steps of the auxiliary decision-making method for power switching of tugboat operations described in the first embodiment and the second embodiment can be implemented.

[0139] It should be understood that: when the processor 401 executes the auxiliary decision-making program for the power switching timing of the tugboat berthing and unberthing operations in the memory 402, in addition to the above functions, other functions can also be realized. For details, please refer to the description of the corresponding method embodiment above.

[0140] Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 400 mentioned, and the electronic device 400 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic devices may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 400 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0141] Embodiment 5

[0142] A readable storage medium for auxiliary decision-making for power switching of tugboat operation, wherein a computer program is stored on the readable storage medium, and when the computer program is executed, the steps of the auxiliary decision-making method for power switching of tugboat operation described in Embodiment 1 and Embodiment 2 are implemented.

[0143] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0144] The present invention may be a system, method and / or computer program product. The computer program product may include a computer-readable storage medium (or medium) having computer-readable program instructions thereon, the computer-readable program instructions being used to cause a processor to perform aspects of the present invention.

[0145] The readable storage medium is a computer-readable storage medium, which can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer-readable storage medium can be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of computer-readable storage media includes the following: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device (such as a punch card or a raised structure in a groove with instructions recorded thereon), and any suitable combination of the above. The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to a corresponding computing / processing device or downloaded to an external computer or external storage device via a network (e.g., the Internet, a local area network, a wide area network, and / or a wireless network). The network may include copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in a computer-readable storage medium within the corresponding computing / processing device.

[0146] The computer programs described herein are computer-readable program instructions that can be downloaded from a computer-readable storage medium to a corresponding computing / processing device or downloaded to an external computer or external storage device via a network (e.g., the Internet, a local area network, a wide area network, and / or a wireless network). The network may include copper transmission cables, optical transmission fibers, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in a computer-readable storage medium in the corresponding computing / processing device.

[0147] The computer-readable program instructions for performing the operation of the present invention can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, and conventional procedural programming languages, such as "C" programming language or similar programming languages. The computer-readable program instructions can be executed completely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or completely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any type of network (including a local area network (LAN) or a wide area network (WAN)), or can be connected to an external computer (for example, by using the Internet of an Internet service provider). In some embodiments, an electronic circuit (including, for example, a programmable logic circuit, a field programmable gate array (FPGA) or a programmable logic array (PLA)) can execute a computer-readable program instruction to personalize the electronic circuit by utilizing the state information of the computer-readable program instructions, so as to perform aspects of the present invention.

[0148] Aspects of the present invention are described herein with reference to flowcharts of methods, systems, devices, and computer program products according to embodiments of the present invention and / or block diagrams. It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0149] These computer-readable program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine that, when executed by a processor of the computer or other programmable data processing apparatus, creates a device for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions may also be stored in a computer-readable storage medium that can instruct a computer, a programmable data processing apparatus, and / or other device to function in a particular manner, such that a computer-readable storage medium having instructions stored therein includes an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0150] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by any technician familiar with the art within the technical scope disclosed in the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A tugboat power switching auxiliary decision method, It is characterized in that The tugboat operation power switching auxiliary decision method comprises the following steps: Obtain the historical operation information and operation status of the tugboat and establish a power switching analysis model. The operation status includes free navigation, escort, and assisted berthing and unberthing; Obtain real-time tugboat operation information; Perform cluster analysis on real-time operation information to determine the operation status of the tugboat, specifically, perform primary clustering on the tugboat operation information to determine whether the tugboat is in a free navigation state, and perform secondary clustering on the operation information of the tugboat that is not in a free navigation state to determine the operation status of the tugboat. The primary clustering is based on the ship's speed, heading and its first-order and second-order derivatives to perform data clustering to identify the free navigation state or the non-free navigation state. The secondary clustering is to supplement the large ship's speed and heading data for secondary clustering to identify the escort state or the auxiliary berthing and unberthing state. The real-time operation information and operation status are input into the power switching analysis model to obtain the tugboat power switching recommendation.

2. The tugboat operation power switching auxiliary decision method according to claim 1, It is characterized in that The acquisition of historical operation information and operation status of the tugboat and establishment of a power switching analysis model includes: Obtain the tugboat's historical operation information and operation status including power switching information; Establish a power switching analysis model and use the tugboat's historical operation information and operation status to train the power switching analysis model; The power switching analysis model is optimized based on the power switching information.

3. The auxiliary decision method for power switching of tugboat operation according to claim 1, It is characterized in that The tugboat operation power switching auxiliary decision method further includes: executing a tugboat power switching operation according to a tugboat power switching suggestion.

4. The tugboat operation power switching auxiliary decision method according to claim 3, It is characterized in that The tugboat operation power switching auxiliary decision method also includes: recording the tugboat power switching result, calculating the optimal solution according to the power switching result, and optimizing and updating the power switching analysis model using the optimal solution.

5. The tugboat operation power switching auxiliary decision method according to claim 4, It is characterized in that The power switching result includes the actual energy consumption and power output performance of this task.

6. The tugboat operation power switching auxiliary decision method according to claim 1, It is characterized in that The obtaining of the real-time operation information of the tugboat includes: obtaining the real-time operation information of the tugboat through a configured sensor.

7. The tugboat operation power switching auxiliary decision method according to claim 6, It is characterized in that The tugboat operation power switching auxiliary decision method also includes: using wireless communication technology to upload real-time operation information of the tugboat obtained by the sensor as input of the power switching analysis model.

8. A tugboat power switching auxiliary decision system, It is characterized in that The tugboat operation power switching auxiliary decision system comprises: A data acquisition module is used to obtain real-time operation information of the tugboat; The power switching analysis model is established based on the acquired historical operation information and operation status of the tugboat, and is used to analyze the input real-time operation information and operation status to obtain the power switching suggestion of the tugboat. The operation status includes free navigation, escort, and assisted berthing and unberthing; The state recognition module is used to perform cluster analysis on the real-time operation information and determine the operation state of the tugboat. Specifically, the tugboat operation information is initially clustered to determine whether the tugboat is in a free navigation state, and the operation information of the tugboat that is not in a free navigation state is secondary clustered to determine the operation state of the tugboat. The initial clustering is based on the ship's speed, heading and its first-order and second-order derivatives to perform data clustering to identify the free navigation state or the non-free navigation state. The secondary clustering is to supplement the large ship's speed and heading data for secondary clustering to identify the escort state or the auxiliary berthing and unberthing state.