Power intelligent switching method and system for electric shaft double-push ship

Abstract

The invention relates to the technical field of power switching, and discloses an intelligent power switching method and system for an electric shaft double-push ship, and the method comprises the steps: dynamically adjusting the membership function adjustment factors of the ship under different navigation condition indexes based on the energy consumption index of the ship; fuzzy reasoning is carried out on whether power switching is carried out on the ship or not through the dynamically-adjusted membership function, and stability adjustment is carried out on the ship; a reinforcement learning model is adopted to generate a driving power distribution result of double shafts in the ship, a reverse torque feedback control algorithm is adopted to monitor torque fluctuation of a transmission system in the ship, and power output of a motor and an internal combustion engine is fed back and adjusted. The fuzzy reasoning precision is improved by adopting a dynamic membership function adjustment mechanism, a reverse torque feedback control algorithm is introduced, the power impact problem in the switching process of the motor and the internal combustion engine is effectively relieved, the stability and the dynamic response capability of the ship power system are improved, and continuous and efficient operation of the ship power system is guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of power switching, and in particular to a method and system for intelligent power switching of an electric shaft dual-thrust ship. Background Art

[0002] With the widespread promotion of green shipping concepts and the increasingly stringent greenhouse gas emission control standards of the International Maritime Organization (IMO), traditional marine systems that rely solely on internal combustion engines as a propulsion source are gradually failing to meet the current comprehensive requirements for high energy efficiency, low carbon emissions, and intelligent control. In complex navigation environments characterized by long voyages, high-load operations, or frequent speed changes, single internal combustion engine power systems suffer from numerous issues such as delayed response, high energy consumption, and inflexible regulation, making them difficult to adapt to the multiple demands of modern ships for energy efficiency, reliability, and operational flexibility.

[0003] To address this trend, modern ship propulsion systems are accelerating their development toward multi-energy synergy and intelligent scheduling. In particular, with the widespread adoption of hybrid propulsion systems, the dual-power mode, in which electric motors and internal combustion engines operate in tandem, has become a key development path for new green ships due to its flexibility, adjustability, and environmental friendliness. The Shaft Line Twin-Drive System, a typical multi-energy integrated propulsion structure, connects the electric motor and internal combustion engine to the left and right propeller shafts, respectively. This allows for efficient switching between various propulsion modes, such as all-electric propulsion, all-internal combustion engine propulsion, and electric-internal combustion hybrid propulsion, without requiring significant modifications to the propeller shaft structure.

[0004] Current research focuses on control methods for ship propulsion systems operating under multi-energy synergy. For example, CN118683722A discloses a propulsion motor speed control method for a ship power switching system. Its technical features include integrating solar, wind, and hydropower to form a clean energy supply unit, using stepless speed regulation to adjust the propulsion motor's operating state, combining current and speed feedback to form a closed-loop control system, and incorporating regenerative braking and dynamic braking technologies to achieve brake energy recovery. This method has certain engineering value in terms of unidirectional propulsion motor speed regulation, energy recovery, and system protection. However, this method does not respond promptly to torque anomalies such as sudden load changes and coupled vibrations in the transmission system (such as the gearbox and shafting), making it difficult to ensure overall system stability. The system primarily relies on an electric propulsion system with a passive diesel engine, lacking bidirectional regulation logic. This leads to large power output fluctuations and significant transmission shock in frequently changing operating conditions (such as berthing and unberthing, and sharp turns).

[0005] To address this problem, the present invention proposes an intelligent power switching method for electric-shaft dual-thrust ships to achieve dynamic coordination and switching of power output between electric motors and internal combustion engines. Summary of the Invention

[0006] The present invention provides an intelligent power switching method and system for an electric-shaft dual-thrust ship. Since traditional fuzzy control systems usually adopt a fixed membership function and cannot dynamically adapt to different navigation environments and energy consumption conditions, the membership function adjustment factor is introduced to dynamically adjust the position and shape of the membership function, so that the fuzzy reasoning system responds more sensitively and robustly to indicators such as speed, thereby improving the accuracy and adaptability of power switching judgment. A stability adjustment method is adopted to ensure that the power switching process is continuous and smooth, reducing the mechanical impact of the system and equipment loss. In a dual-shaft drive system, the asynchronous power response of the electric motor and the internal combustion engine may cause a torque phase difference, resulting in periodic load fluctuations. Therefore, the present application collects torque fluctuations in real time, executes a reverse torque feedback adjustment algorithm, and dynamically fine-tunes the dual-source power output to keep the torque output synchronous and stable.

[0007] To achieve the above-mentioned object, the present invention provides a method for intelligent power switching of an electric shaft dual-thrust ship, comprising the following steps: S1: Periodically collect the ship's navigation condition data for various navigation condition indicators and the ship's energy consumption indicators during navigation, dynamically adjust the ship's membership function adjustment factors for different navigation condition indicators based on the ship's energy consumption indicators, and dynamically adjust the membership functions of the navigation condition indicators; S2: Using the dynamically adjusted membership function to receive navigation condition data, output fuzzy language values ​​of the ship at different navigation condition indicators, and convert the fuzzy language values ​​using fuzzy rules to obtain the fuzzy reasoning result of whether the ship should perform power switching; S3: If the ship switches power, the ship's operating status is adjusted for stability, and the operating status after stability adjustment and navigation condition data constitute the ship's state space; S4: Taking the state space as input, a reinforcement learning model is used to generate the driving power distribution results of the dual shafts in the ship, dynamically adjust the power output of the electric motor and the internal combustion engine, and use the reverse torque feedback control algorithm to monitor the torque fluctuation of the transmission system in the ship during the dynamic adjustment process. The torque fluctuation feedback is used to adjust the power output of the electric motor and the internal combustion engine.

[0008] As a further improvement method of the present invention: Optionally, the navigation condition indicators include navigation speed, battery power, dual-shaft motor voltage, dual-shaft internal combustion engine speed, and navigation mode, and the energy consumption indicator of the ship is an energy consumption data sequence of the ship power system in the ship, including: The vessel is an electric-shaft twin-propulsion vessel, comprising two shafts, namely a left propulsion shaft and a right propulsion shaft, which transmit power output from the vessel's power system to the propellers. The vessel's power system is composed of an internal combustion engine and an electric motor. Energy consumption data of the vessel's power system is composed of electric motor energy consumption data and internal combustion engine energy consumption data. Sensors are deployed in the electric motor and the internal combustion engine to collect three-phase data of the electric motor and the speed and torque of the internal combustion engine, respectively, and calculate the electric motor energy consumption data and the internal combustion engine energy consumption data. Based on the ship's energy consumption index, the ship's membership function adjustment factor under different navigation conditions is dynamically calculated, specifically: Obtain the navigation mode of the ship and extract the standard energy consumption corresponding to the navigation mode, where the navigation mode categories include standby mode, low-speed navigation mode, cruising mode and high-speed navigation mode; Calculate the mean energy consumption data of the energy consumption data sequence. If the mean energy consumption data is higher than the standard energy consumption, the generation adjustment rule of the membership function adjustment factor is triggered, and the membership function adjustment factors of different navigation conditions of the ship are calculated. Otherwise, the membership function adjustment factor remains at the default value of 0. The generation formula of the membership function adjustment factor is: ; in, Indicates the The membership function adjustment factor of the navigation condition index is , where the 1st to 4th navigation condition indicators are speed, battery power, dual-axis motor voltage, and dual-axis internal combustion engine speed. represents a symbolic function, if Greater than 0, then , Less than 0, then , is equal to 0, then 0; Indicates selection The minimum value in ; represents the mean value of energy consumption data in the energy consumption data series, Indicates standard energy consumption, Indicates the The adjustment coefficient of the navigation condition index is in the range of 0.1 to 0.3. Adjust the factor for the preset maximum membership function, set is 0.25.

[0009] Optionally, dynamically adjusting the membership function of the navigation condition index using a membership function adjustment factor includes: The membership function of the navigation condition index is expressed as: ; in, Indicates the The membership function of the navigation condition index in the language value r, Represents the input membership function No. The normalized navigation condition data of the navigation condition indicators are They represent the membership function respectively The preset lower limit coefficient and upper limit coefficient, ,and ; The membership function adjustment factor is used to adjust the lower limit coefficient and the upper limit coefficient of the membership function to form a dynamically adjusted membership function, wherein the adjustment method of the lower limit coefficient and the upper limit coefficient is: ; ; in, for The adjustment results.

[0010] Optionally, the dynamically adjusted membership function is used to receive navigation condition data and output fuzzy language values ​​of the ship under different navigation condition indicators, including: The navigation condition data are normalized and used as the input value of the dynamically adjusted membership function to obtain the fuzzy language values ​​of the ship under different navigation condition indicators. The language value set of the fuzzy language value consists of three language values: "low", "medium" and "high".

[0011] Optionally, fuzzy rules are used to convert the fuzzy language value to obtain a fuzzy reasoning result on whether the ship should perform power switching, including: The fuzzy rules are based on IF, AND, THEN and OR to perform fuzzy reasoning under multiple conditions, where IF, AND, THEN and OR represent "if", "and", "then" and "or" respectively; The fuzzy rules include: IF the speed is low AND the battery level is high AND the dual-axis motor voltage is high THEN the fuzzy reasoning result = switch to pure electric mode; IF the speed is medium AND the battery level is medium AND the dual-shaft internal combustion engine speed is low THEN the fuzzy reasoning result = switch to hybrid mode; IF the battery level is low OR the dual-axis motor voltage is low THEN the fuzzy reasoning result = switch to hybrid mode; IF the ship speed is high AND the dual-shaft internal combustion engine speed is high AND the battery power is low THEN the fuzzy reasoning result = do not perform power switching; IF the battery level is high AND the speed is medium AND the dual-axis motor voltage is high THEN the fuzzy reasoning result = switch to pure electric mode; The pure electric mode is when the internal combustion engine in the ship power system is not working and the electric motor is working; the fuel-electric hybrid mode is when both the internal combustion engine and the electric motor are working in the ship power system.

[0012] Optionally, the ship's operating conditions are adjusted for stability, including: The ship's power switching mode includes switching from pure electric mode to fuel-electric hybrid mode, and vice versa; When the power switching mode is switched from pure electric mode to fuel-electric hybrid mode, the ship's operating stability is adjusted as follows: Gradually reduce the power of the electric motor and control the internal combustion engine to gradually increase the power at the same rate, so that the power handover process is smooth and the system disturbance caused by sudden load changes is avoided; A synchronous phase-locked control mechanism is introduced to gradually synchronize the speed of the internal combustion engine with that of the electric motor, with the phase difference continuously reduced, ensuring that the two are in stable synchronization before coupling. A throttle step limit strategy is used to limit the power increase rate of the internal combustion engine to avoid vibration and loss caused by rapid acceleration. When switching from hybrid fuel-electric mode to pure electric mode, the ship's operating stability is adjusted as follows: Gradually reduce the power of the internal combustion engine and control the electric motor to gradually increase the power at the same level until the power limit of the electric motor is reached, and then stop the internal combustion engine to make the power transfer process smooth and avoid system disturbances caused by sudden load changes.

[0013] Optionally, the operating status and navigation condition data after the stability adjustment are used to form a state space of the ship, including: The operating conditions after the smoothness adjustment include the voltage and operating power of the dual-shaft motor, the speed and operating power of the dual-shaft internal combustion engine, the speed of the twin propellers, and the standard energy consumption corresponding to the navigation mode of the ship, wherein the dual-shaft motor is an electric motor that drives the left propulsion shaft and the right propulsion shaft respectively, the dual-shaft internal combustion engine is an internal combustion engine that drives the left propulsion shaft and the right propulsion shaft respectively, and the dual-shaft twin propellers are propellers associated with the left propulsion shaft and the right propulsion shaft respectively.

[0014] Taking the state space as input, a reinforcement learning model is used to generate the drive power distribution results for the dual shafts in the ship, dynamically adjusting the power output of the electric motor and internal combustion engine, including: The reinforcement learning model uses the state space as input and extracts the standard energy consumption corresponding to the navigation mode of the ship as a constraint to generate the driving power of the motor and internal combustion engine associated with the dual shafts in the ship. The motor voltage and internal combustion engine speed are dynamically adjusted based on the driving power so that the motor and internal combustion engine associated with the dual shafts reach the driving power. The driving power of the motor and internal combustion engine associated with the dual shafts is: ; in, They represent the driving power of the electric motor and the internal combustion engine associated with the left propulsion shaft, respectively. They represent the driving power of the electric motor and the internal combustion engine associated with the right propulsion shaft respectively.

[0015] Optionally, during the dynamic adjustment process, a reverse torque feedback control algorithm is used to monitor the torque fluctuation of the transmission system in the ship, and the power output of the electric motor and the internal combustion engine is adjusted using the torque fluctuation feedback, including: The transmission system consists of an electric motor, an internal combustion engine, and two shafts. Torque sensors are deployed in the electric motor and the internal combustion engine to collect the torque of the electric motor and the internal combustion engine in real time during the dynamic adjustment of the electric motor voltage and the internal combustion engine speed, and calculate the torque fluctuation, where the torque fluctuation is the difference between the real-time torque and the moving average of the torque within a certain time window; A PID control strategy is adopted, and torque fluctuation is used as an error term to construct adjustment instructions for the electric motor and internal combustion engine in real time, and to fine-tune the driving power of the electric motor and internal combustion engine associated with the dual axes.

[0016] The present invention also provides an electric shaft dual-thrust ship power intelligent switching system, which includes a data acquisition device, a fuzzy reasoning module and a power switching module: The data acquisition device is used to periodically collect navigation data of various navigation conditions of the ship and energy consumption indicators during the navigation process of the ship; The fuzzy reasoning module is used to dynamically adjust the membership function adjustment factor of the ship's different navigation conditions based on the ship's energy consumption index, dynamically adjust the membership function of the navigation condition index using the membership function adjustment factor, receive navigation condition data using the dynamically adjusted membership function, output fuzzy language values ​​of the ship's different navigation conditions, convert the fuzzy language values ​​using fuzzy rules, and obtain a fuzzy reasoning result on whether the ship should perform power switching; The power switching module is used to adjust the smoothness of the ship's operating status based on the results of fuzzy reasoning, and the operating status after smoothness adjustment and the navigation condition data constitute the state space of the ship. The state space is used as input, and a reinforcement learning model is used to generate the driving power distribution results of the dual shafts in the ship, dynamically adjust the power output of the electric motor and the internal combustion engine, and use the reverse torque feedback control algorithm to monitor the torque fluctuation of the transmission system in the ship during the dynamic adjustment process, and use the torque fluctuation feedback to adjust the power output of the electric motor and the internal combustion engine.

[0017] Compared with the existing technology, the present invention proposes a method for intelligent power switching of electric shaft dual-thrust ships, which has the following beneficial effects: First, traditional fuzzy control systems often use membership functions with fixed shapes and positions, making it difficult to dynamically adjust according to the energy consumption pattern, motor response characteristics, and switching behavior during actual navigation. They are unable to adapt to changing operating conditions, switching too early in some scenarios and not triggering switching in other scenarios, resulting in a rigid control strategy with poor flexibility. The present invention, based on energy consumption data and standard energy consumption, generates membership function adjustment factors in real time for adjusting the fuzzy membership function, thereby dynamically changing the shape of the membership function, including upper and lower limit coefficients. This allows for dynamic reconstruction of the membership function based on real-time energy consumption or other operating conditions, improving the ability to perceive nonlinearity and uncertainty. Furthermore, by appropriately adjusting the function boundaries under critical energy consumption conditions, the disturbance caused by frequent switching can be reduced, making the fuzzy inference system more relevant to the current operating environment. For example, when energy consumption deviates from the standard energy consumption, the interval of the membership function is automatically adjusted, and the low-battery definition boundary is dynamically expanded during the rapid growth stage of energy consumption, thereby triggering the switching preparation mechanism in advance. This mechanism can effectively avoid delayed response, improve the switching success rate, and reduce the energy consumption and fluctuation amplitude of the entire ship system. It has good real-time, adaptability and generalization capabilities, providing key support for the refinement and dynamicization of ship intelligent switching strategies.

[0018] By setting fuzzy rules for multiple conditional combinations (including IF, AND, OR, and THEN logical statements), the combined influence of multiple operating parameters such as speed, battery power, motor voltage, and internal combustion engine speed can be fully considered, enabling the system to have stronger adaptability and intelligent judgment capabilities when facing changes in complex navigation environments, and accurately identify whether power mode switching is currently required. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A flow chart of an intelligent power switching method for an electric shaft dual-thrust ship provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0020] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0021] Embodiment 1 of the present invention is: This application provides a method for intelligent switching of electric shaft dual-thrust ship power, referring to Figure 1 , the method comprising: S1: Periodically collect the ship's navigation condition data for various navigation condition indicators and the ship's energy consumption indicators during navigation, dynamically adjust the ship's membership function adjustment factors for different navigation condition indicators based on the ship's energy consumption indicators, and dynamically adjust the membership function of the navigation condition indicators using the membership function adjustment factors.

[0022] Said navigation condition index includes navigation speed, battery power, dual-shaft motor voltage, dual-shaft internal combustion engine speed and navigation mode. Sailed ship energy consumption index is a sequence of energy consumption data of the ship power system, including: The ship is an electric-shaft twin-propeller ship, comprising two shafts, namely a left propeller shaft and a right propeller shaft. The propeller shafts transmit the power output from the ship's power system to the propellers. The ship's power system consists of an internal combustion engine and an electric motor. The energy consumption data of the ship's power system consists of the energy consumption data of the electric motor and the energy consumption data of the internal combustion engine. By deploying sensors in the electric motor and the internal combustion engine, the three-phase data of the electric motor and the speed and torque of the internal combustion engine are collected respectively, and the energy consumption data of the electric motor and the internal combustion engine are calculated: ; in, Indicates the nth energy consumption data in the energy consumption data sequence The motor energy consumption data in The energy consumption data of the motor are The power of the left and right propeller shafts, The motor voltages of the motors associated with the left propulsion shaft and the right propulsion shaft at the nth energy consumption data collection moment are respectively, The motor currents of the motors associated with the left propulsion shaft and the right propulsion shaft at the nth energy consumption data collection moment are respectively, are the motor power factors of the motors associated with the left propulsion shaft and the right propulsion shaft at the nth energy consumption data collection moment, respectively, and cos is the cosine function; Represents the internal combustion engine energy consumption data in the nth energy consumption data in the energy consumption data sequence, The energy consumption data of internal combustion engines are The power of the left and right propeller shafts, are the internal combustion engine speeds of the internal combustion engines associated with the left propulsion shaft and the right propulsion shaft at the nth energy consumption data collection moment, are the internal combustion engine torques of the internal combustion engines associated with the left propulsion shaft and the right propulsion shaft at the nth energy consumption data collection moment, is pi; N represents the number of energy consumption data in the energy consumption data sequence.

[0023] It should be noted that the navigation condition data of various navigation condition indicators are instantaneous data at the start of data collection, and the energy consumption indicator is the energy consumption data sequence of the ship power system during the data collection process; Specifically, the dual-shaft motor voltage is the maximum motor voltage of the two propulsion shafts in the ship, the dual-shaft internal combustion engine speed is the maximum internal combustion engine speed of the two propulsion shafts in the ship, and the navigation mode is the operating type of the ship, where the operating type includes standby mode, low-speed navigation mode, cruising mode and high-speed navigation mode.

[0024] Specifically, the driving mode of the propulsion shaft includes internal combustion engine drive, electric motor drive or internal combustion engine and electric motor coordinated drive mode. The electric motor is connected to the energy storage battery and the generator. The generator is used to generate electricity and store the generated electricity in the energy storage battery. The electric motor obtains electricity from the energy storage battery to realize the driving function and drive the propulsion shaft to work. Through the above structure, the ship can flexibly select the driving mode under different working conditions to achieve efficient and environmentally friendly propulsion effect, where the motor voltage is the output voltage provided by the energy storage battery.

[0025] Specifically, a power transmitter and a power quality analyzer are used to collect the three-phase data of the electric motor, and a speed sensor and a torque sensor are used to collect the speed and torque of the internal combustion engine.

[0026] It should be noted that the collected power data can be used to identify the ship's operating conditions, assist in the adaptive adjustment of the membership function adjustment factor, and improve the coordination efficiency of the ship's power system.

[0027] Based on the ship's energy consumption index, the membership function adjustment factor of the ship under different navigation conditions is dynamically calculated. The calculation method of the membership function adjustment factor is: The navigation mode of the ship is obtained, and the standard energy consumption corresponding to the navigation mode is extracted, where the mode categories of the navigation mode include standby mode, low-speed navigation mode, cruising mode and high-speed navigation mode.

[0028] It should be noted that in the waiting mode, the ship is at anchor, docked or waiting, and only the basic equipment is maintained in operation; in the low-speed navigation mode, the ship is mainly in the stage of entering and exiting the port, navigating in narrow waterways or passing through locks, and needs to frequently adjust the direction and speed; in the cruising mode, the ship is in the normal sea or river navigation stage, with stable speed and continuous thrust output; in the high-speed navigation mode, the power system runs at full load and the fuel / electricity consumption reaches the maximum value.

[0029] Standard energy consumption is the total energy consumed by a ship in sailing mode for one hour divided by one hour. The unit of standard energy consumption and power is kilowatt. Calculate the mean energy consumption data of the energy consumption data sequence. If the mean energy consumption data is higher than the standard energy consumption, the generation adjustment rule of the membership function adjustment factor is triggered, and the membership function adjustment factors of different navigation conditions of the ship are calculated. Otherwise, the membership function adjustment factor remains at the default value of 0. The generation formula of the membership function adjustment factor is: ; in, Indicates the The membership function adjustment factor of the navigation condition index is , where the 1st to 4th navigation condition indicators are speed, battery power, dual-axis motor voltage, and dual-axis internal combustion engine speed. represents a symbolic function, if Greater than 0, then , Less than 0, then , is equal to 0, then 0; Indicates selection The minimum value in ; represents the mean value of energy consumption data in the energy consumption data series, Indicates standard energy consumption, Indicates the The adjustment coefficient of the navigation condition index is in the range of 0.1 to 0.3. Adjust the factor for the preset maximum membership function, set is 0.25; specifically, the adjustment coefficients of the 1st to 4th navigation conditions are set as follows: .

[0030] Dynamically adjusting the membership function of the navigation condition index using the membership function adjustment factor includes: The membership function of the navigation condition index is expressed as: ; in, Indicates the The membership function of the navigation condition index in the language value r, Represents the input membership function No. The normalized navigation condition data of the navigation condition indicators are They represent the membership function respectively The preset lower limit coefficient and upper limit coefficient, ,and ; The membership function adjustment factor is used to adjust the lower limit coefficient and the upper limit coefficient of the membership function to form a dynamically adjusted membership function, wherein the adjustment method of the lower limit coefficient and the upper limit coefficient is: ; ; in, for The adjustment results.

[0031] S2: Use the dynamically adjusted membership function to receive navigation condition data, output the fuzzy language values ​​of the ship in different navigation condition indicators, use fuzzy rules to convert the fuzzy language values, and obtain the fuzzy reasoning result of whether the ship should switch power.

[0032] The dynamically adjusted membership function is used to receive navigation condition data and output the fuzzy language values ​​of the ship under different navigation condition indicators, including: The navigation condition data are normalized and used as the input value of the dynamically adjusted membership function to obtain the fuzzy language values ​​of the ship under different navigation condition indicators. The language value set of the fuzzy language value consists of three language values: "low", "medium" and "high".

[0033] Specifically, for the The normalized sailing condition data of the sailing condition index ,Will Input into the membership function respectively , get the membership function value

[0034] , extract the language value with the largest membership function value as the first The fuzzy language value of the navigation condition index.

[0035] Fuzzy rules are used to convert fuzzy language values ​​to obtain fuzzy reasoning results on whether the ship should switch power, including: The fuzzy rules are based on IF, AND, THEN and OR to perform fuzzy reasoning under multiple conditions, where IF, AND, THEN and OR represent "if", "and", "then" and "or" respectively; The fuzzy rules include: IF the speed is low AND the battery level is high AND the dual-axis motor voltage is high THEN the fuzzy reasoning result = switch to pure electric mode; IF the speed is medium AND the battery level is medium AND the dual-shaft internal combustion engine speed is low THEN the fuzzy reasoning result = switch to hybrid mode; IF the battery level is low OR the dual-axis motor voltage is low THEN the fuzzy reasoning result = switch to hybrid mode; IF the ship speed is high AND the dual-shaft internal combustion engine speed is high AND the battery power is low THEN the fuzzy reasoning result = do not perform power switching; IF the battery level is high AND the speed is medium AND the dual-axis motor voltage is high THEN the fuzzy reasoning result = switch to pure electric mode; The pure electric mode is when the internal combustion engine in the ship power system is not working and the electric motor is working; the fuel-electric hybrid mode is when both the internal combustion engine and the electric motor are working in the ship power system.

[0036] It should be noted that by setting fuzzy rules for multiple condition combinations (including IF, AND, OR, THEN logical statements), the combined influence of multiple operating parameters such as speed, battery power, motor voltage, and internal combustion engine speed can be fully considered, enabling the system to have stronger adaptability and intelligent judgment capabilities when facing changes in complex navigation environments, and accurately identify whether power mode switching is currently required.

[0037] S3: If the ship switches power, the ship's operating status is adjusted for stability, and the operating status after stability adjustment and navigation condition data constitute the ship's state space.

[0038] Make smooth adjustments to the ship's operating conditions, including: The ship's power switching mode includes switching from pure electric mode to fuel-electric hybrid mode, and vice versa; When the power switching mode is switched from pure electric mode to fuel-electric hybrid mode, the ship's operating stability is adjusted as follows: Gradually reduce the power of the electric motor and control the internal combustion engine to gradually increase the power at the same rate, so that the power handover process is smooth and the system disturbance caused by sudden load changes is avoided; A synchronous phase-locked control mechanism is introduced to gradually synchronize the speed of the internal combustion engine with that of the electric motor, with the phase difference continuously reduced, ensuring that the two are in stable synchronization before coupling. A throttle step limit strategy is used to limit the power increase rate of the internal combustion engine to avoid vibration and loss caused by rapid acceleration. When switching from hybrid fuel-electric mode to pure electric mode, the ship's operating stability is adjusted as follows: Gradually reduce the power of the internal combustion engine and control the electric motor to gradually increase the power at the same level until the power limit of the electric motor is reached, and then stop the internal combustion engine to make the power transfer process smooth and avoid system disturbances caused by sudden load changes.

[0039] The ship's state space is constructed by combining the operating status and navigation condition data after stability adjustment, including: The operating conditions after the smoothness adjustment include the voltage and operating power of the dual-shaft motor, the speed and operating power of the dual-shaft internal combustion engine, the speed of the twin propellers, and the standard energy consumption corresponding to the navigation mode of the ship, wherein the dual-shaft motor is an electric motor that drives the left propulsion shaft and the right propulsion shaft respectively, the dual-shaft internal combustion engine is an internal combustion engine that drives the left propulsion shaft and the right propulsion shaft respectively, and the dual-shaft twin propellers are propellers associated with the left propulsion shaft and the right propulsion shaft respectively.

[0040] It should be noted that differentiated smooth adjustment strategies are designed for the switching directions between pure electric mode and hybrid electric mode, effectively alleviating the common problems of power mutation, torque shock, and phase misalignment in traditional power switching. When switching from pure electric to hybrid mode, the system controls the internal combustion engine power increase process through a synchronous phase-locked mechanism and a throttle step limit strategy, achieving a smooth power handover between the electric motor and the internal combustion engine, ensuring power continuity and system stability during the switching period. When switching from hybrid to pure electric, the internal combustion engine power is orderly reduced and the electric motor output is simultaneously increased to ensure a balanced transition during the power takeover process of the ship, avoiding system disturbances caused by internal combustion engine shutdown. In addition, this smooth control method is also compatible with different ship types and different power levels of motor and main engine combinations. It has good engineering versatility and scalability, and can significantly improve the operating economy, reliability, and automation level of electric shaft dual-thrust ships under multiple working conditions.

[0041] S4: Taking the state space as input, a reinforcement learning model is used to generate the driving power distribution results of the dual shafts in the ship, dynamically adjust the power output of the electric motor and the internal combustion engine, and use the reverse torque feedback control algorithm to monitor the torque fluctuation of the transmission system in the ship during the dynamic adjustment process. The torque fluctuation feedback is used to adjust the power output of the electric motor and the internal combustion engine.

[0042] Taking the state space as input, a reinforcement learning model is used to generate the drive power distribution results for the dual shafts in the ship, dynamically adjusting the power output of the electric motor and internal combustion engine, including: The reinforcement learning model uses the state space as input and extracts the standard energy consumption corresponding to the navigation mode of the ship as a constraint to generate the driving power of the motor and internal combustion engine associated with the dual shafts in the ship. The motor voltage and internal combustion engine speed are dynamically adjusted based on the driving power so that the motor and internal combustion engine associated with the dual shafts reach the driving power. The driving power of the motor and internal combustion engine associated with the dual shafts is: ; in, They represent the driving power of the electric motor and the internal combustion engine associated with the left propulsion shaft, respectively. They represent the driving power of the electric motor and the internal combustion engine associated with the right propulsion shaft respectively.

[0043] As an embodiment of the present application, the reward function of the reinforcement learning model is: ; ; ; in, represents the reward function, Indicates the driving power distribution result of the two axes, Indicates the driving power distribution result of the two axes The reward function value of Indicates the driving power distribution result of dual-axis The difference ratio constraint between the final and standard energy consumption is set. The lower the difference ratio constraint, the closer it is to the standard energy consumption. It represents the sum of the driving powers in the dual-axis driving power distribution result. represents the standard energy consumption corresponding to the navigation mode of the ship extracted from the state space; Indicates the driving power distribution result of the two axes The fluctuation of Represents the vector consisting of the operating power of the electric motor and internal combustion engine associated with the dual axes in the state space, represents the L2 norm, The smaller it is, the smaller the adjustment range of the motor voltage and internal combustion engine speed of the electric motor and internal combustion engine associated with the dual shafts, which encourages smooth operation of the power system and reduces drive-side oscillations.

[0044] Specifically, the reward function comprehensively evaluates the rationality and stability of the power coordination between the dual-axis electric motor and the internal combustion engine by introducing an error term representing the difference between the dual-axis drive power distribution result and the standard energy consumption, as well as a state adjustment term. On the one hand, by comparing with the standard energy consumption, the reinforcement learning model is dynamically guided to approach the standard energy consumption output under different navigation modes. On the other hand, the introduction of the state adjustment term can suppress the drastic fluctuations in the voltage and speed of the dual-axis system, ensuring the stability and safety of the system's transmission side. This reward mechanism balances energy minimization with system stability, effectively avoiding structural impact or response delays caused by unstable power switching during energy efficiency optimization. It is suitable for demanding ship power coordination scenarios and helps to improve the intelligent level and reliability of energy management in hybrid power systems.

[0045] It should be noted that the parameters to be optimized of the reinforcement learning model are solved based on the maximization reward function, and the scores of the driving power of the electric motor and the internal combustion engine associated with the dual axes in different state spaces are obtained as the policy network in the reinforcement learning model. After each state space is received, the driving power of the electric motor and the internal combustion engine associated with the dual axes with the highest score is selected as the output.

[0046] During the dynamic adjustment process, a reverse torque feedback control algorithm is used to monitor the torque fluctuation of the ship's transmission system and use the torque fluctuation feedback to adjust the power output of the electric motor and internal combustion engine, including: The transmission system comprises an electric motor, an internal combustion engine, and two shafts (i.e., a left propulsion shaft and a right propulsion shaft in this embodiment). Torque sensors are deployed on the electric motor and the internal combustion engine to collect the torque of the electric motor and the internal combustion engine in real time during the dynamic adjustment of the electric motor voltage and the internal combustion engine speed, and to calculate the torque fluctuation, where the torque fluctuation is the difference between the real-time torque and the moving average of the torque within a certain time window; A PID control strategy is employed, treating torque fluctuation as an error term. Adjustment commands for the electric motor and internal combustion engine are generated in real time, further fine-tuning the drive power of the electric motor and internal combustion engine associated with each shaft. Specifically, for any propulsion shaft, if the torque fluctuation is greater than a preset positive threshold (e.g., 0.8 Nm), it indicates excessive torque, reducing the internal combustion engine power and improving the motor's flexible regulation. If the torque fluctuation is less than a preset negative threshold (e.g., -0.8 Nm), the system will automatically adjust the torque.

[0047] Example 2: An electric shaft dual-thrust ship power intelligent switching system includes a data acquisition device, a fuzzy reasoning module and a power switching module: The data acquisition device is used to periodically collect navigation data of various navigation conditions of the ship and energy consumption indicators during the navigation process of the ship; The fuzzy reasoning module is used to dynamically adjust the membership function adjustment factor of the ship's different navigation conditions based on the ship's energy consumption index, dynamically adjust the membership function of the navigation condition index using the membership function adjustment factor, receive navigation condition data using the dynamically adjusted membership function, output fuzzy language values ​​of the ship's different navigation conditions, convert the fuzzy language values ​​using fuzzy rules, and obtain a fuzzy reasoning result on whether the ship should perform power switching; The power switching module is used to adjust the smoothness of the ship's operating status based on the results of fuzzy reasoning, and the operating status after smoothness adjustment and the navigation condition data constitute the state space of the ship. The state space is used as input, and a reinforcement learning model is used to generate the driving power distribution results of the dual shafts in the ship, dynamically adjust the power output of the electric motor and the internal combustion engine, and use the reverse torque feedback control algorithm to monitor the torque fluctuation of the transmission system in the ship during the dynamic adjustment process, and use the torque fluctuation feedback to adjust the power output of the electric motor and the internal combustion engine.

[0048] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0049] It should be noted that the serial numbers of the above-mentioned embodiments of the present invention are for descriptive purposes only and do not represent the advantages or disadvantages of the embodiments. In addition, the terms "including", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "including a ..." does not exclude the presence of other identical elements in the process, device, article or method comprising the element.

[0050] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0051] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for intelligent power switching of electric shaft dual-thrust ships, characterized in that: The method comprises: S1: Periodically collect the ship's navigation condition data for various navigation condition indicators and the ship's energy consumption indicators during navigation, dynamically adjust the ship's membership function adjustment factors for different navigation condition indicators based on the ship's energy consumption indicators, and dynamically adjust the membership functions of the navigation condition indicators; S2: Using the dynamically adjusted membership function to receive navigation condition data, output fuzzy language values ​​of the ship at different navigation condition indicators, and convert the fuzzy language values ​​using fuzzy rules to obtain the fuzzy reasoning result of whether the ship should perform power switching; S3: If the ship switches power, the ship's operating status is adjusted for stability, and the operating status after stability adjustment and navigation condition data constitute the ship's state space; S4: Taking the state space as input, a reinforcement learning model is used to generate the driving power distribution results of the dual shafts in the ship, dynamically adjust the power output of the electric motor and the internal combustion engine, and use the reverse torque feedback control algorithm to monitor the torque fluctuation of the transmission system in the ship during the dynamic adjustment process. The torque fluctuation feedback is used to adjust the power output of the electric motor and the internal combustion engine.

2. The method for intelligent power switching of an electric shaft dual-thrust ship according to claim 1, characterized in that: Said navigation condition indicators include navigation speed, battery charge, dual-axis motor voltage, dual-axis internal combustion engine speed and navigation mode; The energy consumption index of the ship is a sequence of energy consumption data of the ship's power system, specifically: the ship is an electric-shaft dual-propulsion ship, including two shafts, namely a left propulsion shaft and a right propulsion shaft; the two shafts transmit power output by the ship's power system to the propellers, the ship's power system is composed of an internal combustion engine and an electric motor, and the energy consumption data of the ship's power system is composed of the electric motor energy consumption data and the internal combustion engine energy consumption data. By deploying sensors in the electric motor and the internal combustion engine, the three-phase data of the electric motor and the speed and torque of the internal combustion engine are respectively collected to calculate the electric motor energy consumption data and the internal combustion engine energy consumption data; Based on the ship's energy consumption index, the ship's membership function adjustment factor under different navigation conditions is dynamically calculated, specifically: Obtain the navigation mode of the ship and extract the standard energy consumption corresponding to the navigation mode, where the navigation mode categories include standby mode, low-speed navigation mode, cruising mode and high-speed navigation mode; Calculate the mean energy consumption data of the energy consumption data sequence. If the mean energy consumption data is higher than the standard energy consumption, the generation adjustment rule of the membership function adjustment factor is triggered, and the membership function adjustment factor of different navigation conditions of the ship is calculated. Otherwise, the membership function adjustment factor remains at the default value of 0. The generation formula of the membership function adjustment factor is: ； in, Indicates the The membership function adjustment factor of the navigation condition index is , where the 1st to 4th navigation condition indicators are speed, battery power, dual-axis motor voltage, and dual-axis internal combustion engine speed. represents a symbolic function, if Greater than 0, then , Less than 0, then , is equal to 0, then 0; Indicates selection The minimum value in ; represents the mean value of energy consumption data in the energy consumption data series, Indicates standard energy consumption, Indicates the The adjustment coefficient of the navigation condition index is in the range of 0.1 to 0.

3. Adjust the factor for the preset maximum membership function, set is 0.

25.

3. The method for intelligent power switching of an electric shaft dual-thrust ship according to claim 2, characterized in that: The membership function adjustment factor is used to dynamically adjust the membership function of the navigation condition index, including: The membership function of the navigation condition index is expressed as: ； in, Indicates the The membership function of the navigation condition index in the language value r, Represents the input membership function No. The normalized navigation condition data of the navigation condition indicators are They represent the membership function respectively The preset lower limit coefficient and upper limit coefficient, ,and ; The membership function adjustment factor is used to adjust the lower limit coefficient and the upper limit coefficient of the membership function to form a dynamically adjusted membership function, wherein the adjustment method of the lower limit coefficient and the upper limit coefficient is: ； ； in, for The adjustment results.

4. The method for intelligent power switching of an electric shaft dual-thrust ship according to claim 3, characterized in that: The dynamically adjusted membership function is used to receive navigation condition data and output the fuzzy language values ​​of the ship under different navigation condition indicators, including: The navigation condition data are normalized and used as the input value of the dynamically adjusted membership function to obtain the fuzzy linguistic values ​​of the ship under different navigation condition indicators. The fuzzy linguistic value set consists of three linguistic values: "low", "medium" and "high".

5. The method for intelligent power switching of an electric shaft dual-thrust ship according to claim 4, characterized in that: Fuzzy rules are used to convert fuzzy language values ​​to obtain fuzzy reasoning results on whether the ship should switch power, including: The fuzzy rules are based on IF, AND, THEN and OR to perform fuzzy reasoning under multiple conditions, where IF, AND, THEN and OR represent "if", "and", "then" and "or" respectively; The fuzzy rules include: IF the speed is low AND the battery level is high AND the dual-axis motor voltage is high THEN the fuzzy reasoning result = switch to pure electric mode; IF the speed is medium AND the battery level is medium AND the dual-shaft internal combustion engine speed is low THEN the fuzzy reasoning result = switch to hybrid mode; IF the battery level is low OR the dual-axis motor voltage is low THEN the fuzzy reasoning result = switch to hybrid mode; IF the ship speed is high AND the dual-shaft internal combustion engine speed is high AND the battery power is low THEN the fuzzy reasoning result = do not perform power switching; IF the battery level is high AND the speed is medium AND the dual-axis motor voltage is high THEN the fuzzy reasoning result = switch to pure electric mode; The pure electric mode is when the internal combustion engine in the ship power system is not working and the electric motor is working; the fuel-electric hybrid mode is when both the internal combustion engine and the electric motor are working in the ship power system.

6. The method for intelligent power switching of an electric shaft dual-thrust ship according to claim 5, characterized in that: Make smooth adjustments to the ship's operating conditions, including: The ship's power switching mode includes switching from pure electric mode to fuel-electric hybrid mode, and vice versa; When the power switching mode is switched from pure electric mode to fuel-electric hybrid mode, the ship's operating stability is adjusted as follows: Gradually reduce the power of the electric motor and control the internal combustion engine to gradually increase the power at the same rate, so that the power handover process is smooth and the system disturbance caused by sudden load changes is avoided; A synchronous phase-locked control mechanism is introduced to gradually synchronize the speed of the internal combustion engine with that of the electric motor, with the phase difference continuously reduced, ensuring that the two are in a stable synchronous state before coupling. A throttle step limit strategy is used to limit the power increase rate of the internal combustion engine to avoid vibration and loss caused by rapid acceleration. When switching from hybrid fuel-electric mode to pure electric mode, the ship's operating stability is adjusted as follows: Gradually reduce the power of the internal combustion engine and control the electric motor to gradually increase the power at the same rate until the power limit of the electric motor is reached, and then stop the internal combustion engine to make the power transfer process smooth and avoid system disturbances caused by sudden load changes.

7. The method for intelligent power switching of an electric shaft dual-thrust ship according to claim 6, characterized in that: The ship's state space is constructed by combining the operating status and navigation condition data after stability adjustment, including: The operating conditions after the smoothness adjustment include the voltage and operating power of the dual-shaft motor, the speed and operating power of the dual-shaft internal combustion engine, the speed of the twin propellers, and the standard energy consumption corresponding to the navigation mode of the ship, wherein the dual-shaft motor is an electric motor that drives the left propulsion shaft and the right propulsion shaft respectively, the dual-shaft internal combustion engine is an internal combustion engine that drives the left propulsion shaft and the right propulsion shaft respectively, and the dual-shaft twin propellers are propellers associated with the left propulsion shaft and the right propulsion shaft respectively.

8. The method for intelligent power switching of an electric shaft dual-thrust ship according to claim 7, characterized in that: Taking the state space as input, a reinforcement learning model is used to generate the drive power distribution results for the dual shafts in the ship, dynamically adjusting the power output of the electric motor and internal combustion engine, including: The reinforcement learning model uses the state space as input and extracts the standard energy consumption corresponding to the navigation mode of the ship as a constraint to generate the driving power of the motor and internal combustion engine associated with the dual shafts in the ship. The motor voltage and internal combustion engine speed are dynamically adjusted based on the driving power so that the motor and internal combustion engine associated with the dual shafts reach the driving power. The driving power of the motor and internal combustion engine associated with the dual shafts is: ； in, They represent the driving power of the electric motor and the internal combustion engine associated with the left propulsion shaft, respectively. They represent the driving power of the electric motor and the internal combustion engine associated with the right propulsion shaft respectively.

9. The method for intelligent power switching of an electric shaft dual-thrust ship according to claim 8, characterized in that: During the dynamic adjustment process, a reverse torque feedback control algorithm is used to monitor the torque fluctuation of the ship's transmission system and use the torque fluctuation feedback to adjust the power output of the electric motor and internal combustion engine, including: The transmission system consists of an electric motor, an internal combustion engine, and two shafts. Torque sensors are deployed on the electric motor and the internal combustion engine to collect the torque of the electric motor and the internal combustion engine in real time during the dynamic adjustment of the electric motor voltage and the internal combustion engine speed, and calculate the torque fluctuation, where the torque fluctuation is the difference between the real-time torque and the moving average of the torque within a certain time window; A PID control strategy is adopted, and torque fluctuation is used as an error term to construct adjustment instructions for the electric motor and internal combustion engine in real time, and to fine-tune the driving power of the electric motor and internal combustion engine associated with the dual axes.

10. An electric shaft dual-thrust ship power intelligent switching system, characterized in that: The system includes a data acquisition device, a fuzzy reasoning module and a power switching module: The data acquisition device is used to periodically collect navigation data of various navigation conditions of the ship and energy consumption indicators during the navigation process of the ship; The fuzzy reasoning module is used to dynamically adjust the membership function adjustment factor of the ship's different navigation conditions based on the ship's energy consumption index, dynamically adjust the membership function of the navigation condition index using the membership function adjustment factor, receive navigation condition data using the dynamically adjusted membership function, output fuzzy language values ​​of the ship's different navigation conditions, convert the fuzzy language values ​​using fuzzy rules, and obtain a fuzzy reasoning result on whether the ship should perform power switching; The power switching module is used to adjust the stability of the ship's operating status based on the fuzzy inference results, and the operating status after the stability adjustment and the navigation condition data constitute the ship's state space. Using the state space as input, a reinforcement learning model is used to generate the driving power distribution results of the dual shafts in the ship, dynamically adjust the power output of the electric motor and the internal combustion engine, and use the reverse torque feedback control algorithm to monitor the torque fluctuation of the ship's transmission system during the dynamic adjustment process, and use the torque fluctuation feedback to adjust the power output of the electric motor and the internal combustion engine; To realize the intelligent switching method of electric shaft dual-thrust ship power as described in any one of claims 1-9.

Images