Electrical shaft double-push ship power intelligent switching method and system

Abstract

The application relates to the technical field of power switching, and discloses an electric shaft double-push ship power intelligent switching method and system, which comprises the following steps: based on the energy consumption index of a ship, the membership degree function adjustment factor of the ship in different navigation working condition indexes is dynamically adjusted; whether the ship is switched in power is inferred by using the dynamically adjusted membership degree function, and the ship is adjusted in smoothness; a reinforcement learning model is used to generate the driving power distribution result of the double shafts in the ship, 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 feedback adjusted. The dynamic membership degree function adjustment mechanism is used to improve the fuzzy inference accuracy, the reverse torque feedback control algorithm is introduced, the power impact problem in the switching process of the electric motor and the internal combustion engine is effectively relieved, the stability and the power response capability of the ship power system are improved, and the continuous and efficient operation of the ship power system is ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of power switching, in particular to an intelligent power switching method and system for an electric shaft twin-drive ship. BACKGROUND

[0002] With the widespread promotion of green shipping concepts and the increasingly stringent control standards of the International Maritime Organization (IMO) on greenhouse gas emissions, traditional ships relying on internal combustion engines as a single propulsion power source have gradually failed to meet the current comprehensive requirements for high energy efficiency, low carbon emissions, and intelligent control. In complex navigation environments such as long navigation, high load operation, or frequent speed changes, single internal combustion engine power systems have problems such as response lag, high energy consumption, and inflexible adjustment, making it difficult to meet the multiple demands of modern ships for energy saving, reliability, and operational flexibility.

[0003] To address this trend, modern ship power systems are accelerating towards the direction of multi-energy collaboration and intelligent scheduling. In particular, under the background of the widespread application of hybrid propulsion systems, the dual-power mode of electric motors and internal combustion engines working together has become a key development path for new green ships due to its strong flexibility, good adjustability, and environmental friendliness. Among them, the electric shaft twin-drive system (Shaft Line Twin-Drive System) is a typical multi-energy integrated propulsion structure, which connects electric motors and internal combustion engines to the left and right propulsion shafts, respectively, allowing efficient switching between various propulsion conditions such as all-electric propulsion, all-diesel propulsion, and electric-diesel hybrid propulsion without significantly modifying the propulsion shaft structure.

[0004] Current research has focused on the control methods of ship propulsion systems under multi-energy collaboration. For example, CN118683722A discloses a propulsion motor speed control method for a ship power switching system, which includes the following technical features: integrating solar, wind, and water energy to form a clean energy supply unit, using stepless speed regulation to adjust the working state of the propulsion motor, forming a closed-loop control system with current and speed feedback, and introducing regenerative braking and energy consumption braking technology to realize braking energy recovery. This method has certain engineering value in terms of one-way speed regulation of the propulsion motor, energy recovery, and system protection. However, this method does not respond promptly to torque abnormalities such as load mutations and coupling vibrations in the transmission system (such as gearboxes and shafting), making it difficult to ensure smooth overall system operation. The system mainly relies on electric propulsion and passively cooperates with diesel engines, lacks bidirectional adjustment logic, and has significant power output fluctuations and transmission shocks in frequent variable working conditions (such as berthing and unberthing, and sharp turning).

[0005] To address this problem, the present application proposes an intelligent power switching method for an electric shaft twin-drive ship, which realizes dynamic coordination and switching of power output between electric motors and internal combustion engines. SUMMARY

[0006] The application provides an electric shaft double-push ship power intelligent switching method and system, since a traditional fuzzy control system usually adopts a fixed membership function, cannot make dynamic adaptation according to different navigation environments and energy consumption conditions, by introducing a membership function adjustment factor, dynamically adjusting the position and shape of the membership function, the response of the fuzzy reasoning system to the speed and other indicators is more sensitive and more robust, the accuracy and self-adaptive ability of the power switching judgment are improved, the smoothness adjustment method is adopted to ensure that the power switching process is continuous and smooth, and the mechanical impact and equipment loss of the system are reduced, in the double-shaft driving system, since the power responses of the electric motor and the internal combustion engine are not synchronized, the torque phase difference may be caused, and periodic load fluctuation is caused, therefore, the application collects torque fluctuation in real time, executes a reverse torque feedback adjustment algorithm, dynamically adjusts the double-source power output, and makes the torque output keep synchronization and smoothness.

[0007] To achieve the above object, the application provides an electric shaft double-push ship power intelligent switching method, which comprises the following steps:

[0008] S1: periodically collecting navigation working condition data of the ship under various navigation working condition indicators and energy consumption indicators of the ship in the navigation process, dynamically adjusting the membership function adjustment factor of the ship under different navigation working condition indicators based on the energy consumption indicators of the ship, and dynamically adjusting the membership function of the navigation working condition indicators;

[0009] S2: receiving the navigation working condition data by using the dynamically adjusted membership function, outputting fuzzy language values of the ship under different navigation working condition indicators, converting the fuzzy language values by using fuzzy rules, and obtaining a fuzzy reasoning result of whether the ship is switched in power;

[0010] S3: if the ship is switched in power, adjusting the running state of the ship in smoothness, and constructing a state space of the ship by using the running state adjusted in smoothness and the navigation working condition data;

[0011] S4: taking the state space as input, generating a driving power distribution result of the double shaft in the ship by using a reinforcement learning model, dynamically adjusting the power output of the electric motor and the internal combustion engine, and monitoring torque fluctuation of a transmission system in the ship by using a reverse torque feedback control algorithm in the dynamic adjustment process, and adjusting the power output of the electric motor and the internal combustion engine by using torque fluctuation feedback.

[0012] As a further improved method of the application:

[0013] Optionally, the navigation working condition indicators include speed, battery capacity, double-shaft electric motor voltage, double-shaft internal combustion engine speed and navigation mode, the energy consumption indicators of the ship are an energy consumption data sequence of a ship power system in the ship, and the energy consumption data sequence comprises:

[0014] The ship is an electric shaft double-push ship, comprising a double shaft, a left propulsion shaft and a right propulsion shaft respectively, the double shaft transmits the power output by a ship power system to a propeller, the ship power system is composed of an internal combustion engine and an electric motor, the energy consumption data of the ship power system is composed 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, 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 energy consumption data of the internal combustion engine are calculated;

[0015] The ship's energy consumption index is used to dynamically calculate the membership function adjustment factor of the ship under different navigation condition indexes, specifically:

[0016] The navigation mode of the ship is obtained, and the standard energy consumption corresponding to the navigation mode is extracted, wherein the mode category of the navigation mode includes standby mode, low-speed navigation mode, cruise mode and high-speed navigation mode;

[0017] The energy consumption data mean of the energy consumption data sequence is calculated, if the energy consumption data mean is higher than the standard energy consumption, the generation adjustment rule of the membership function adjustment factor is triggered, the membership function adjustment factor of the ship under different navigation condition indexes is calculated, otherwise the membership function adjustment factor remains as the default value 0, the generation formula of the membership function adjustment factor is:

[0018] ;

[0019] Wherein, represents the membership function adjustment factor of the first navigation condition index, , wherein the first to fourth navigation condition indexes are speed, battery power, double shaft motor voltage and double shaft internal combustion engine speed in turn, represents the sign function, if is greater than 0, , is less than 0, , is equal to 0, 0;

[0020] represents the minimum value in ;

[0021] represents the energy consumption data mean of the energy consumption data sequence, represents the standard energy consumption, represents the adjustment coefficient of the first navigation condition index, wherein the range of the adjustment coefficient is 0.1 to 0.3, is the preset maximum membership function adjustment factor, and is set to 0.25.

[0022] Optionally, the membership function of the navigation condition index can be dynamically adjusted using a membership function adjustment factor, including:

[0023] The membership function of the navigation condition index is expressed as follows:

[0024] ;

[0025] in, Indicates the first The membership function of various navigation condition indicators in the linguistic value r. Indicates the input membership function The Normalized navigation condition data for various navigation condition indicators. These represent the membership functions respectively. The preset lower limit coefficient and upper limit coefficient, ,and ;

[0026] The lower and upper bound coefficients of the membership function are adjusted using a membership function adjustment factor to form a dynamically adjusted membership function. The adjustment method for the lower and upper bound coefficients is as follows:

[0027] ;

[0028] ;

[0029] in, for The results of the adjustment.

[0030] Optionally, the navigation condition data is received using a dynamically adjusted membership function, and fuzzy linguistic values ​​of the ship's indicators under different navigation conditions are output, including:

[0031] The navigation condition data is 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 conditions. The linguistic value set of the fuzzy linguistic values ​​consists of three types of linguistic values: "low", "medium", and "high".

[0032] Optionally, fuzzy rules are used to transform the fuzzy linguistic values ​​to obtain fuzzy inference results regarding whether the ship is switching power, including:

[0033] The fuzzy rules are based on IF, AND, THEN, and OR for multi-condition fuzzy reasoning, where IF, AND, THEN, and OR represent "if", "and", "then", and "or" respectively.

[0034] The fuzzy rules comprise:

[0035] IF speed is low AND battery power is high AND dual-shaft motor voltage is high THEN fuzzy inference result = switch to pure electric mode;

[0036] IF speed is medium AND battery power is medium AND dual-shaft diesel engine speed is low THEN fuzzy inference result = switch to fuel-electric hybrid mode;

[0037] IF battery power is low OR dual-shaft motor voltage is low THEN fuzzy inference result = switch to fuel-electric hybrid mode;

[0038] IF speed is high AND dual-shaft diesel engine speed is high AND battery power is low THEN fuzzy inference result = do not switch power;

[0039] IF battery power is high AND speed is medium AND dual-shaft motor voltage is high THEN fuzzy inference result = switch to pure electric mode;

[0040] The pure electric mode is that the diesel engine does not work and the motor works in the ship power system; and the fuel-electric hybrid mode is that the diesel engine and the motor both work in the ship power system.

[0041] Optionally, the smoothness adjustment of the ship's operating conditions comprises:

[0042] The power switching mode of the ship comprises switching from pure electric mode to fuel-electric hybrid mode and switching from fuel-electric hybrid mode to pure electric mode;

[0043] In the power switching mode of switching from pure electric mode to fuel-electric hybrid mode, the smoothness adjustment mode of the ship's operating conditions is:

[0044] Gradually reduce the power of the motor, and control the diesel engine to gradually rise with equal power, so that the power transfer process is smoothly transitioned, and system disturbance caused by sudden load is avoided;

[0045] A synchronous phase-locked control mechanism is introduced, so that the speed of the diesel engine gradually synchronizes with the motor, the phase difference is continuously reduced, and it is ensured that the two are in a stable synchronization state before coupling; a throttle step limitation strategy is adopted to limit the power rising rate of the diesel engine, so as to avoid vibration and loss caused by sharp acceleration;

[0046] In the power switching mode of switching from fuel-electric hybrid mode to pure electric mode, the smoothness adjustment mode of the ship's operating conditions is:

[0047] Gradually reduce the power of the internal combustion engine, and control the electric motor to gradually rise at equal power until the limit power of the electric motor is reached and the internal combustion engine stops working, so that the power transfer process is smoothly transitioned, avoiding system disturbance caused by sudden load.

[0048] Optionally, the smoothness-adjusted operating conditions and the navigation condition data constitute a state space of the ship, including:

[0049] The smoothness-adjusted operating conditions include the voltage and operating power of the dual-shaft electric motor, the speed and operating power of the dual-shaft internal combustion engine, the speed of the dual-screw propeller, and the standard energy consumption corresponding to the navigation mode in which the ship is located, wherein the dual-shaft electric motor is an electric motor that drives the left and right propulsion shafts, the dual-shaft internal combustion engine is an internal combustion engine that drives the left and right propulsion shafts, and the dual-shaft dual-screw propeller is a propeller associated with the left and right propulsion shafts.

[0050] The state space is used as input to generate a driving power distribution result of the dual shafts in the ship using a reinforcement learning model to dynamically adjust the power output of the electric motor and the internal combustion engine, including:

[0051] The reinforcement learning model takes the state space as input, extracts the standard energy consumption corresponding to the navigation mode in which the ship is located as a constraint, generates the driving power of the electric motor and the internal combustion engine associated with the dual shafts in the ship, and dynamically adjusts the voltage of the electric motor and the speed of the internal combustion engine to achieve the driving power of the electric motor and the internal combustion engine associated with the dual shafts, wherein the driving power of the electric motor and the internal combustion engine associated with the dual shafts is:

[0052] ;

[0053] wherein, the driving power of the electric motor and the internal combustion engine associated with the left propulsion shaft in sequence respectively, the driving power of the electric motor and the internal combustion engine associated with the right propulsion shaft in sequence respectively.

[0054] Optionally, a reverse torque feedback control algorithm is used to monitor the torque fluctuation of the transmission system in the ship during the dynamic adjustment process, and the power output of the electric motor and the internal combustion engine is adjusted using torque fluctuation feedback, including:

[0055] The transmission system is composed of the electric motor, the internal combustion engine, and the dual shafts. Torque sensors are deployed on the electric motor and the internal combustion engine. The torque of the electric motor and the internal combustion engine is collected in real time during the dynamic adjustment of the voltage of the electric motor and the speed of the internal combustion engine, and the torque fluctuation is calculated, wherein the torque fluctuation is the difference between the real-time torque and the moving average of the torque within a certain time window.

[0056] Adopt PID control strategy, take torque fluctuation as error term, real-time construct motor and internal combustion engine's regulation instruction, carry out fine adjustment to the driving power of the motor and internal combustion engine associated with double shaft.

[0057] The application also provides an electric shaft double-push ship power intelligent switching system, which comprises a data acquisition device, a fuzzy reasoning module and a power switching module.

[0058] The data acquisition device is used for periodically acquiring ship navigation working condition data of various navigation working condition indexes and energy consumption indexes of the ship during navigation.

[0059] The fuzzy reasoning module is used for dynamically adjusting membership function adjustment factors of the ship under different navigation working condition indexes based on the energy consumption indexes of the ship, dynamically adjusting membership functions of the navigation working condition indexes by using the membership function adjustment factors, receiving the navigation working condition data by using the dynamically adjusted membership functions, outputting fuzzy language values of the ship under different navigation working condition indexes, converting the fuzzy language values by using fuzzy rules, and obtaining fuzzy reasoning results of whether the ship needs to switch power.

[0060] The power switching module is used for adjusting smoothness of the running state of the ship based on the fuzzy reasoning results, constructing a state space of the ship by using the smoothness-adjusted running state and the navigation working condition data, taking the state space as input, generating a driving power distribution result of the double shaft in the ship by using a reinforcement learning model, dynamically adjusting power outputs of the motor and the internal combustion engine, and monitoring torque fluctuation of a transmission system in the ship by using a reverse torque feedback control algorithm during the dynamic adjustment process, and adjusting the power outputs of the motor and the internal combustion engine by using the torque fluctuation feedback.

[0061] Compared with the prior art, the application provides an electric shaft double-push ship power intelligent switching method, and the method has the following beneficial effects:

[0062] Firstly, the conventional fuzzy control system often uses a membership function with fixed shape and position, which is difficult to adjust dynamically according to the energy consumption mode, motor response characteristics and switching behavior in the actual navigation process, and cannot adapt to changing working conditions. In some scenarios, it switches too early, and in other scenarios, it delays triggering the switch, resulting in a rigid control strategy and poor flexibility. Based on the energy consumption data and the standard energy consumption, the application generates a membership function adjustment factor for adjusting the fuzzy membership function in real time, and dynamically changes the shape of the membership function, including the upper limit coefficient and the lower limit coefficient. The membership function can be dynamically reconstructed according to real-time energy consumption or other working conditions, improving the perception of nonlinearity and uncertainty, and adjusting the function boundary moderately in the critical state of energy consumption. This can reduce the disturbance caused by frequent switching, making the fuzzy reasoning system closer to the current operating environment. For example, when the energy consumption deviates from the standard energy consumption, the interval of the membership function is automatically adjusted, and the low power definition boundary is dynamically expanded in the rapid growth stage of energy consumption, thereby triggering the switching preparation mechanism in advance. This mechanism can effectively avoid delayed response, improve switching success rate, and reduce the energy consumption and fluctuation amplitude of the whole ship system, with good real-time performance, adaptability and generalization ability, providing key support for the refinement and dynamic of the intelligent switching strategy of the ship.

[0063] By setting the fuzzy rules (including IF, AND, OR, THEN logical statements) combined with multiple conditions, the joint influence of multiple source working condition parameters such as speed, battery power, motor voltage, and diesel engine speed can be fully considered, so that the system has stronger adaptability and intelligent judgment ability when facing complex changes in navigation environment, and can accurately identify whether power mode switching is needed. BRIEF DESCRIPTION OF DRAWINGS

[0064] Figure 1 A flowchart of an intelligent switching method for the power of an electric shaft double-propeller ship according to an embodiment of the application is provided. DETAILED DESCRIPTION

[0065] It should be understood that the specific embodiments described herein are only used to explain the application and do not limit the application.

[0066] Embodiment 1 of the application is:

[0067] The application provides an intelligent switching method for the power of an electric shaft double-propeller ship, which is described with reference to Figure 1 The method comprises:

[0068] S1: periodically collecting navigation working condition data of the ship under multiple navigation working condition indicators and energy consumption indicators of the ship during navigation, dynamically adjusting the membership function adjustment factor of the ship under different navigation working condition indicators based on the energy consumption indicators of the ship, and dynamically adjusting the membership function of the navigation working condition indicators using the membership function adjustment factor.

[0069] The navigation working condition indicators include a navigation speed, a battery power, a double-shaft motor voltage, a double-shaft internal combustion engine rotating speed, and a navigation mode, and the energy consumption indicator of the ship is an energy consumption data sequence of a ship power system in the ship, including:

[0070] The ship is an electric shaft double-propeller ship, including double shafts, i.e., two propeller shafts, which are a left propeller shaft and a right propeller shaft, respectively, and the propeller shafts transmit power output by the ship power system to propellers, the ship power system is composed of an internal combustion engine and an electric motor, and energy consumption data of the ship power system is composed of electric motor energy consumption data and internal combustion engine energy consumption data, and the electric motor energy consumption data and the internal combustion engine energy consumption data are calculated by deploying sensors in the electric motor and the internal combustion engine to collect three-phase data of the electric motor and rotating speed and torque of the internal combustion engine, respectively:

[0071] ;

[0072] wherein, represents the nth energy consumption data in the energy consumption data sequence the electric motor energy consumption data in the electric motor energy consumption data the powers of the left propeller shaft and the right propeller shaft in the electric motor energy consumption data the electric motor voltages of the left propeller shaft and the right propeller shaft associated electric motor at the nth energy consumption data collection time point in the electric motor energy consumption data the electric motor currents of the left propeller shaft and the right propeller shaft associated electric motor at the nth energy consumption data collection time point in the electric motor energy consumption data the electric motor power factors of the left propeller shaft and the right propeller shaft associated electric motor at the nth energy consumption data collection time point in the electric motor energy consumption data, and cos is a cosine function;

[0073] represents the nth energy consumption data in the energy consumption data sequence the internal combustion engine energy consumption data in the internal combustion engine energy consumption data the powers of the left propeller shaft and the right propeller shaft in the internal combustion engine energy consumption data the internal combustion engine rotating speeds of the left propeller shaft and the right propeller shaft associated internal combustion engine at the nth energy consumption data collection time point in the internal combustion engine energy consumption data the internal combustion engine torques of the left propeller shaft and the right propeller shaft associated internal combustion engine at the nth energy consumption data collection time point in the internal combustion engine energy consumption data is a circular constant;

[0074] N represents the number of energy consumption data in the energy consumption data sequence.

[0075] It should be noted that the navigation working condition data of the plurality of navigation working condition indicators are instantaneous data at the beginning of data collection, and the energy consumption indicator is an energy consumption data sequence of the ship power system in the ship during data collection.​

[0076] Specifically, the dual-shaft motor voltage is a maximum motor voltage of two propulsion shafts in the ship, the dual-shaft internal combustion engine speed is a maximum internal combustion engine speed of two propulsion shafts in the ship, and the navigation mode is a work type of the ship, wherein the work type includes an anchoring mode, a low-speed navigation mode, a cruising mode, and a high-speed navigation mode.

[0077] Specifically, the driving mode of the propulsion shaft includes an internal combustion engine driving mode, an electric motor driving mode, or an internal combustion engine and electric motor cooperative driving mode, the electric motor is connected with an energy storage battery and a generator, the generator is used to generate electric energy and store the generated electric energy into the energy storage battery, the electric motor obtains electric energy from the energy storage battery to realize a driving function, and the propulsion shaft is driven to work. Through the above structure, the ship can flexibly select a driving mode under different working conditions to realize efficient and environmentally friendly propulsion effect, and the electric motor voltage is an output voltage provided by the energy storage battery.

[0078] Specifically, the three-phase data of the electric motor are collected by using a power transmitter and an electric energy quality analyzer, and the internal combustion engine speed and torque are collected by using a speed sensor and a torque sensor.

[0079] It should be noted that the collected power data can be used for ship working condition recognition, auxiliary adaptive adjustment of the membership function adjustment factor, and improvement of the coordination efficiency of the ship power system.

[0080] The membership function adjustment factor of the ship under different navigation working condition indexes is dynamically calculated based on the energy consumption index of the ship, and the calculation method of the membership function adjustment factor is as follows:

[0081] The navigation mode of the ship is obtained, and the standard energy consumption corresponding to the navigation mode is extracted, wherein the mode category of the navigation mode includes an anchoring mode, a low-speed navigation mode, a cruising mode, and a high-speed navigation mode.

[0082] It should be noted that in the anchoring mode, the ship is in an anchoring, berthing, or waiting state, and only basic equipment is maintained to operate; in the low-speed navigation mode, the ship mainly enters and exits the port, navigates in a narrow waterway, or passes through a ship lock stage, and needs to frequently adjust the direction and speed; in the cruising mode, the ship is in a normal sea or river navigation stage, the speed is stable, and the thrust is continuously output; and in the high-speed navigation mode, the power system is full-load operated, and the fuel / electric energy consumption reaches a maximum value.

[0083] The standard energy consumption is the total amount of energy consumed by the ship after driving for 1 hour divided by 1 hour, and the unit of the standard energy consumption and the power is kilowatt;

[0084] 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 and adjustment rules of the membership function adjustment factor are triggered, and the membership function adjustment factors for 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 as follows:

[0085] ;

[0086] in, Indicates the first Membership function adjustment factor for various navigation condition indicators The navigation conditions indicators for the first four categories are, in order, speed, battery charge, dual-shaft electric motor voltage, and dual-shaft internal combustion engine speed. Represents a sign function, if If it is greater than 0, then , If less than 0, then , If it equals 0, then 0;

[0087] Indicates selection The minimum value in;

[0088] This represents the mean of energy consumption data in a series of energy consumption data. Indicates standard energy consumption. Indicates the first The adjustment factors for various navigation condition indicators range from 0.1 to 0.3. Set the preset maximum membership function adjustment factor. The value is 0.25; specifically, the adjustment coefficients for the navigation conditions 1-4 are set as follows: .

[0089] The membership function of the navigation condition index is dynamically adjusted using a membership function adjustment factor, including:

[0090] The membership function representation of the navigation condition index is as follows:

[0091] ;

[0092] in, Indicates the first The membership function of various navigation condition indicators in the linguistic value r. Indicates the input membership function The Normalized navigation condition data for various navigation condition indicators. The membership functions are sequentially represented as The preset lower limit coefficient and upper limit coefficient, , and ;

[0093] The lower limit coefficient and upper limit coefficient of the membership function are adjusted by the membership function adjustment factor to form a dynamically adjusted membership function, wherein the adjustment manner of the lower limit coefficient and upper limit coefficient is:

[0094] ;

[0095] ;

[0096] Wherein, is the adjustment result.

[0097] S2: receiving the navigation working condition data by using the dynamically adjusted membership function, outputting the fuzzy language values of the ship under different navigation working condition indexes, and converting the fuzzy language values by using the fuzzy rules to obtain the fuzzy inference result of whether the ship performs power switching.

[0098] Receiving the navigation working condition data by using the dynamically adjusted membership function, outputting the fuzzy language values of the ship under different navigation working condition indexes, including:

[0099] The navigation working condition data is normalized, and the normalized navigation working condition data is taken as the input value of the dynamically adjusted membership function to obtain the fuzzy language values of the ship under different navigation working condition indexes, wherein the language value set of the fuzzy language values is composed of three language values of “low”, “medium” and “high”.

[0100] Specifically, for the normalized navigation working condition data of the first navigation working condition index , the membership function is sequentially input to obtain the membership function value

[0101] , and the language value with the maximum membership function value is extracted as the fuzzy language value of the first navigation working condition index.

[0102] Converting the fuzzy language values by using the fuzzy rules to obtain the fuzzy inference result of whether the ship performs power switching, including:

[0103] The fuzzy rules are multi-condition fuzzy reasoning by IF, AND, THEN and OR, wherein IF, AND, THEN and OR represent "if", "and", "then" and "or" respectively;

[0104] The fuzzy rules include:

[0105] IF the sailing speed is low AND the battery power is high AND the dual-shaft motor voltage is high, THEN the fuzzy reasoning result = switch to the pure electric mode;

[0106] IF the sailing speed is medium AND the battery power is medium AND the dual-shaft internal combustion engine speed is low, THEN the fuzzy reasoning result = switch to the fuel-electric hybrid mode;

[0107] IF the battery power is low OR the dual-shaft motor voltage is low, THEN the fuzzy reasoning result = switch to the fuel-electric hybrid mode;

[0108] IF the sailing 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 switch the power;

[0109] IF the battery power is high AND the sailing speed is medium AND the dual-shaft motor voltage is high, THEN the fuzzy reasoning result = switch to the pure electric mode;

[0110] The pure electric mode is that the internal combustion engine does not work and the motor works in the ship power system; and the fuel-electric hybrid mode is that the internal combustion engine and the motor work in the ship power system.

[0111] It should be noted that by setting the fuzzy rules (containing IF, AND, OR, THEN logical statements) of multi-condition combination, the joint influence of multiple source working condition parameters such as sailing speed, battery power, motor voltage and internal combustion engine speed can be fully considered, so that the system has stronger adaptability and intelligent judgment ability when facing complex changes in sailing environment, and accurately identifies whether power mode switching is needed.

[0112] S3: If the ship switches the power, adjust the running state of the ship for smoothness, and construct the state space of the ship by the running state adjusted for smoothness and the sailing working condition data.

[0113] The adjustment of the running state of the ship for smoothness includes:

[0114] The power switching mode of the ship includes switching from the pure electric mode to the fuel-electric hybrid mode, and switching from the fuel-electric hybrid mode to the pure electric mode;

[0115] In the power switching mode from the pure electric mode to the hybrid mode, the smoothness adjustment mode of the ship running state is as follows:

[0116] The power of the electric motor is gradually reduced, and the internal combustion engine is controlled to gradually increase the power at an equal power, so that the power transfer process is smoothly transitioned, and system disturbance caused by sudden load is avoided.

[0117] The synchronous phase-locked control mechanism is introduced, so that the speed of the internal combustion engine gradually synchronizes with the electric motor, and the phase difference is continuously reduced, so that stable synchronization state is ensured before coupling; the throttle step limit strategy is adopted to limit the power increasing rate of the internal combustion engine, so as to avoid vibration and loss caused by sharp acceleration.

[0118] In the power switching mode from the hybrid mode to the pure electric mode, the smoothness adjustment mode of the ship running state is as follows:

[0119] The power of the internal combustion engine is gradually reduced, and the electric motor is controlled to gradually increase the power at an equal power until the limit power of the electric motor is reached, and the internal combustion engine is stopped, so that the power transfer process is smoothly transitioned, and system disturbance caused by sudden load is avoided.

[0120] The running state after smoothness adjustment and the sailing condition data constitute the state space of the ship, including:

[0121] The running state after smoothness adjustment includes the voltage and running power of the double-shaft electric motor, the speed and running power of the double-shaft internal combustion engine, the speed of the double-screw propeller, and the standard energy consumption corresponding to the sailing mode of the ship, wherein the double-shaft electric motor is an electric motor driving the left and right propulsion shafts respectively, the double-shaft internal combustion engine is an internal combustion engine driving the left and right propulsion shafts respectively, and the double-shaft double-screw propeller is a propeller associated with the left and right propulsion shafts respectively.

[0122] It should be noted that differentiated smooth adjustment strategies are designed for the switching direction of the pure electric mode and the hybrid mode, which effectively alleviates the problems of power mutation, torque impact and phase misalignment commonly seen in traditional power switching. In the switching from pure electric mode to hybrid mode, the system controls the power increasing process of the internal combustion engine through the synchronous phase-locked mechanism and the throttle step limit strategy, realizes the smooth power transfer of the electric motor and the internal combustion engine, and guarantees the power continuity and system stability during switching. In the switching from hybrid mode to pure electric mode, the power of the internal combustion engine is sequentially reduced, and the output of the electric motor is simultaneously increased, so as to ensure the balanced transition of the ship during power takeover and avoid system disturbance caused by the shutdown of the internal combustion engine. In addition, the smooth control method is also compatible with different ship types, different power levels of electric motors and main engine combinations, has good engineering universality and expansibility, and can significantly improve the running economy, reliability and automation level of the electric shaft double-propeller ship in multiple conditions.

[0123] S4: taking the state space as input, generating the driving power distribution result of the twin shaft in the ship by using the reinforcement learning model, dynamically adjusting the power output of the electric motor and the internal combustion engine, and monitoring the torque fluctuation of the transmission system in the ship by using the reverse torque feedback control algorithm in the dynamic adjustment process, and adjusting the power output of the electric motor and the internal combustion engine by using the torque fluctuation feedback.

[0124] taking the state space as input, generating the driving power distribution result of the twin shaft in the ship by using the reinforcement learning model, dynamically adjusting the power output of the electric motor and the internal combustion engine, including:

[0125] The reinforcement learning model takes the state space as input, extracts the standard energy consumption corresponding to the sailing mode of the ship as a constraint, generates the driving power of the electric motor and the internal combustion engine associated with the twin shaft in the ship, and dynamically adjusts the motor voltage and the internal combustion engine speed to achieve the driving power of the electric motor and the internal combustion engine associated with the twin shaft, and the driving power of the electric motor and the internal combustion engine associated with the twin shaft is:

[0126] ;

[0127] wherein, the driving power of the electric motor and the internal combustion engine associated with the left propulsion shaft in sequence respectively, the driving power of the electric motor and the internal combustion engine associated with the right propulsion shaft in sequence respectively.

[0128] As an embodiment of the present application, the reward function of the reinforcement learning model is:

[0129] ;

[0130] ;

[0131] ;

[0132] wherein, represents the reward function, represents the driving power distribution result of the twin shaft, represents the reward function value of the driving power distribution result of the twin shaft ;

[0133] represents the difference ratio constraint between the driving power distribution result of the twin shaft and the standard energy consumption, the lower the difference ratio constraint, the closer to the standard energy consumption, represents the sum of the driving power in the driving power distribution result of the twin shaft, represents the standard energy consumption corresponding to the sailing mode of the ship extracted from the state space;

[0134] represents the driving power distribution result of the dual shaft represents the fluctuation of the dual shaft, represents a vector composed of the operating power of the electric motor and the internal combustion engine associated with the dual shaft in the state space, represents the L2 norm, is smaller, the adjustment range of the motor voltage and the internal combustion engine speed of the electric motor and the internal combustion engine associated with the dual shaft is smaller, encouraging the smooth operation of the power system and reducing the oscillation on the driving side.

[0135] Specifically, the reward function comprehensively evaluates the rationality and stability of the power coordination of the dual shaft electric motor and the internal combustion engine by introducing a proportional error term of the difference between the driving power distribution result of the dual shaft and the standard energy consumption, and 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 inhibit the violent fluctuation of the dual shaft system in voltage and speed change, and ensure the smoothness and safety of the transmission side of the system. This reward mechanism takes into account the minimization of energy consumption and system stability, and can effectively avoid structural impact or response delay caused by unstable power switching in the process of optimizing energy efficiency, and is suitable for high-demand ship power coordination scenarios, which helps to improve the intelligent level and reliability of energy management under hybrid power system.

[0136] It should be noted that the reinforcement learning model is solved based on maximizing the reward function to obtain the scores of the driving power of the electric motor and the internal combustion engine associated with the dual shaft under different state spaces as the policy network in the reinforcement learning model, and the driving power of the electric motor and the internal combustion engine associated with the dual shaft with the highest score is selected as the output after receiving the state space each time.

[0137] In 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 by using torque fluctuation feedback, including:

[0138] The transmission system is composed of an electric motor, an internal combustion engine, and a dual shaft (i.e. left and right propulsion shafts in the embodiment). Torque sensors are deployed at the electric motor and the internal combustion engine, and the torque of the electric motor and the internal combustion engine is collected in real time during the dynamic adjustment of the electric motor voltage and the internal combustion engine speed, and the torque fluctuation is calculated, wherein the torque fluctuation is the difference between the real-time torque and the moving average value of the torque within a certain time window.

[0139] Adopting PID control strategy, taking torque fluctuation as error term, real-time constructing motor and internal combustion engine adjustment instruction, further fine-tuning driving power of dual-shaft associated motor and internal combustion engine. Specifically, for any propulsion shaft, if torque fluctuation is greater than preset positive threshold (for example, 0.8 Nm), it indicates that torque is too large, reduce internal combustion engine power, and improve motor flexible adjustment, if torque fluctuation is less than preset negative threshold (for example, -0.8 Nm).

[0140] Embodiment 2:

[0141] An electric shaft dual-propulsion ship power intelligent switching system, comprising a data acquisition device, a fuzzy reasoning module and a power switching module:

[0142] The data acquisition device is used to periodically acquire ship navigation working condition data of various navigation working condition indicators and energy consumption indicators during ship navigation;

[0143] The fuzzy reasoning module is used to dynamically adjust the membership function adjustment factor of the ship under different navigation working condition indicators based on the energy consumption indicators of the ship, dynamically adjust the membership function of the navigation working condition indicators using the membership function adjustment factor, receive the navigation working condition data using the dynamically adjusted membership function, output fuzzy language values of the ship under different navigation working condition indicators, convert the fuzzy language values using fuzzy rules, and obtain fuzzy reasoning results of whether the ship performs power switching;

[0144] The power switching module is used to adjust the smoothness of the running state of the ship based on the fuzzy reasoning results, construct a state space of the ship using the smoothness adjusted running state and the navigation working condition data, use the state space as input, generate driving power distribution results of dual shafts in the ship using a reinforcement learning model, dynamically adjust power output of the motor and the internal combustion engine, and monitor torque fluctuation of the transmission system in the ship using a reverse torque feedback control algorithm during the dynamic adjustment process, and adjust power output of the motor and the internal combustion engine using torque fluctuation feedback.

[0145] It should be understood that the embodiments are only for illustration, and the scope of the patent application is not limited by the structure.

[0146] It should be noted that the above-mentioned embodiment serial numbers of the present application are only for description, not representing the advantages and disadvantages of the embodiments. Also, the terms "comprising", "containing" or any other variants thereof in this document are intended to cover the non-exclusive inclusion, so that the process, device, article or method including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, device, article or method. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0147] Through the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be realized by means of software and necessary general hardware platforms, of course, they can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application 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 plurality of instructions for making a terminal device (which can be a mobile phone, computer, server, or network device, etc.) execute the methods described in various embodiments of the present application.

[0148] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent flow transformation made by using the content of the specification and drawings, or directly or indirectly applied to other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for intelligent switching of power in a twin-screw marine vessel with electric shafts, characterized by, The method comprises: S1: periodically collecting ship navigation working condition data of various navigation working condition indicators and energy consumption indicators of the ship during navigation, dynamically adjusting a membership function adjustment factor of the ship under different navigation working condition indicators based on the energy consumption indicators of the ship, and dynamically adjusting the membership function of the navigation working condition indicators; S2: receiving the navigation working condition data using the dynamically adjusted membership function, outputting fuzzy language values of the ship under different navigation working condition indicators, converting the fuzzy language values using fuzzy rules, and obtaining a fuzzy reasoning result of whether the ship performs power switching; S3: if the ship performs power switching, adjusting the running state for smoothness, and constructing a state space of the ship by using the running state after the smoothness adjustment and the navigation working condition data; S4: taking the state space as input, generating a driving power distribution result of the dual shaft of the ship using a reinforcement learning model, dynamically adjusting the power output of the electric motor and the internal combustion engine, and monitoring the torque fluctuation of the transmission system of the ship during the dynamic adjustment process using a reverse torque feedback control algorithm, and adjusting the power output of the electric motor and the internal combustion engine using the torque fluctuation feedback; The navigation working condition indicators include speed, battery power, dual shaft motor voltage, dual shaft internal combustion engine speed, and navigation mode; The energy consumption indicators of the ship are energy consumption data sequences of the ship power system, specifically: the ship is an electric shaft dual propulsion ship, including a dual shaft, which is a left propulsion shaft and a right propulsion shaft; the dual shaft transmits power output by the ship power system to the propeller; the ship power system is composed of an internal combustion engine and an electric motor; the energy consumption data of the ship power system is composed of electric motor energy consumption data and internal combustion engine energy consumption data; by deploying sensors in the electric motor and the internal combustion engine, three-phase data of the electric motor and speed and torque of the internal combustion engine are collected respectively, and the electric motor energy consumption data and the internal combustion engine energy consumption data are calculated; The membership function adjustment factor of the ship under different navigation working condition indicators is dynamically calculated based on the energy consumption indicators of the ship, specifically: The navigation mode of the ship is obtained, and the standard energy consumption corresponding to the navigation mode is extracted, wherein the mode category of the navigation mode includes standby mode, low-speed navigation mode, cruise mode, and high-speed navigation mode; The energy consumption data mean of the energy consumption data sequence is calculated, if the energy consumption data mean is higher than the standard energy consumption, the generation rule of the membership function adjustment factor is adjusted, the membership function adjustment factor of the ship under different navigation working condition indicators is calculated, otherwise the membership function adjustment factor remains as the default value 0, and the generation formula of the membership function adjustment factor is: ； wherein, represents a membership function adjustment factor of a 1st kind of navigation working condition index, wherein the 1st-4th kind of navigation working condition index are in turn a speed, a battery power, a double-shaft motor voltage, and a double-shaft internal combustion engine speed, represents a sign function, if is greater than 0, then , is less than 0, then , is equal to 0, then 0; denotes the minimum value among a mean value of energy consumption data representing the energy consumption data sequence, a standard energy consumption, an adjustment coefficient of the first navigational condition index, wherein the adjustment coefficient ranges from 0.1 to 0.3, a preset maximum membership function adjustment factor, set to 0.

25.

2. An electric shaft twin push vessel power intelligent switching method according to claim 1, characterized in that, The membership function of the navigation working condition indicator is dynamically adjusted using the membership function adjustment factor, including: The membership function of the navigation working condition indicator is expressed as: ； wherein, represents the membership function of the th sailing condition index at the language value r, represents the sailing condition data of the th sailing condition index after normalization processing of the input membership function, , and ;​​​ The lower limit coefficient and the upper limit coefficient of the membership function are adjusted using the membership function adjustment factor to form the dynamically adjusted membership function, wherein the adjustment method of the lower limit coefficient and the upper limit coefficient is: ； ； wherein is the result of the adjustment.

3. An electric shaft twin push vessel power intelligent switching method according to claim 2, characterized in that, The navigation working condition data is received using the dynamically adjusted membership function, and fuzzy language values of the ship under different navigation working condition indicators are output, including: The navigation working condition data is normalized, and the normalized navigation working condition data is taken as an input value of the dynamically adjusted membership function, so as to obtain fuzzy language values of the ship under different navigation working condition indexes, wherein a language value set of the fuzzy language values is composed of three language values of "low", "medium" and "high".

4. An electric shaft twin push vessel power intelligent switching method according to claim 3, characterized in that, The fuzzy rules are used to convert the fuzzy language values, so as to obtain fuzzy reasoning results of whether the ship performs power switching, including: The fuzzy rules are fuzzy reasoning under multiple conditions by IF, AND, THEN and OR, wherein IF, AND, THEN and OR represent "if", "and", "then" and "or" respectively; The fuzzy rules include: IF the speed is low AND the battery power is high AND the dual-shaft motor voltage is high, THEN the fuzzy reasoning result = switching to the pure electric mode; IF the speed is medium AND the battery power is medium AND the dual-shaft internal combustion engine speed is low, THEN the fuzzy reasoning result = switching to the fuel-electric hybrid mode; IF the battery power is low OR the dual-shaft motor voltage is low, THEN the fuzzy reasoning result = switching to the fuel-electric hybrid mode; IF the speed is high AND the dual-shaft internal combustion engine speed is high AND the battery power is low, THEN the fuzzy reasoning result = not performing power switching; IF the battery power is high AND the speed is medium AND the dual-shaft motor voltage is high, THEN the fuzzy reasoning result = switching to the pure electric mode; The pure electric mode is that the internal combustion engine does not work in the ship power system, and the motor works; and the fuel-electric hybrid mode is that the internal combustion engine and the motor both work in the ship power system.

5. An electric shaft twin push vessel power intelligent switching method as claimed in claim 4, characterized in that, The running state of the ship is adjusted for smoothness, including: The power switching mode of the ship includes switching from the pure electric mode to the fuel-electric hybrid mode, and switching from the fuel-electric hybrid mode to the pure electric mode; Under the power switching mode of switching from the pure electric mode to the fuel-electric hybrid mode, the smoothness adjustment mode of the running state of the ship is: The power of the motor is gradually reduced, and the internal combustion engine is controlled to gradually increase at an equal power, so that the power transfer process is smoothly transitioned, and system disturbance caused by sudden load is avoided; A synchronous phase-locked control mechanism is introduced, so that the speed of the internal combustion engine gradually synchronizes with the motor, the phase difference is continuously reduced, and stable synchronization state of the two is ensured before coupling; a throttle step limitation strategy is used to limit the power increasing rate of the internal combustion engine, so as to avoid vibration and loss caused by sharp acceleration; Under the power switching mode of switching from the fuel-electric hybrid mode to the pure electric mode, the smoothness adjustment mode of the running state of the ship is: The power of the internal combustion engine is gradually reduced, and the motor is controlled to gradually increase at an equal power until the limit power of the motor is reached, and the internal combustion engine is stopped, so that the power transfer process is smoothly transitioned, and system disturbance caused by sudden load is avoided.

6. An electric shaft twin push vessel power intelligent switching method as claimed in claim 5, characterized in that, The running state after the smoothness adjustment and the navigation working condition data constitute a state space of the ship, including: The smoothness-adjusted operating condition includes voltage and operating power of a double-shaft electric motor, rotating speed and operating power of a double-shaft internal combustion engine, rotating speed of a double-screw propeller, and standard energy consumption corresponding to a sailing mode in which the ship is located, wherein the double-shaft electric motor is an electric motor for driving a left propeller shaft and a right propeller shaft respectively, the double-shaft internal combustion engine is an internal combustion engine for driving the left propeller shaft and the right propeller shaft respectively, and the double-shaft double-screw propeller is a propeller associated with the left propeller shaft and the right propeller shaft respectively.

7. An electric shaft twin push vessel power intelligent switching method as claimed in claim 6, characterized in that, The state space is taken as input, and a reinforcement learning model is used to generate a driving power distribution result of the double shaft in the ship, so as to dynamically adjust power output of the electric motor and the internal combustion engine, including: The reinforcement learning model takes the state space as input, extracts standard energy consumption corresponding to a sailing mode in which the ship is located as a constraint, generates driving power of an electric motor and an internal combustion engine associated with the double shaft in the ship, and dynamically adjusts voltage of the electric motor and rotating speed of the internal combustion engine with the driving power as a target, so that the electric motor and the internal combustion engine associated with the double shaft reach the driving power, and the driving power of the electric motor and the internal combustion engine associated with the double shaft is: ； wherein, successively represent the driving power of the electric motor and the internal combustion engine associated with the left propulsion shaft, respectively, successively represent the driving power of the electric motor and the internal combustion engine associated with the right propulsion shaft, respectively.

8. An electric shaft twin push vessel power intelligent switching method as claimed in claim 7, characterized in that, A reverse torque feedback control algorithm is used to monitor torque fluctuation of a transmission system in the ship during the dynamic adjustment, and torque fluctuation is used to feedback adjust power output of the electric motor and the internal combustion engine, including: The transmission system includes the electric motor, the internal combustion engine, and the double shaft, torque sensors are arranged at the electric motor and the internal combustion engine, torque of the electric motor and the internal combustion engine is collected in real time during dynamic adjustment of voltage of the electric motor and rotating speed of the internal combustion engine, and torque fluctuation is calculated, wherein the torque fluctuation is a difference between real-time torque and a moving average value of torque within a certain time window; A PID control strategy is used, torque fluctuation is taken as an error term, and adjustment instructions of the electric motor and the internal combustion engine are constructed in real time, so as to finely adjust driving power of the electric motor and the internal combustion engine associated with the double shaft.

9. An electric shaft twin push vessel power intelligent switching system, characterized by, The system includes a data acquisition device, a fuzzy reasoning module, and a power switching module: The data acquisition device is used to periodically acquire sailing condition data of the ship in multiple sailing condition indicators and energy consumption indicators of the ship during sailing; The fuzzy reasoning module is used to dynamically adjust an adjustment factor of a membership function of the ship in different sailing condition indicators based on the energy consumption indicators of the ship, dynamically adjust the membership function of the sailing condition indicator by using the adjustment factor of the membership function, receive the sailing condition data by using the dynamically adjusted membership function, output fuzzy language values of the ship in different sailing condition indicators, convert the fuzzy language values by using fuzzy rules, and obtain a fuzzy reasoning result of whether the ship needs to switch power; The power switching module is used to adjust smoothness of an operating condition of the ship based on the fuzzy reasoning result, form a state space of the ship by using the smoothness-adjusted operating condition and the sailing condition data, take the state space as input, generate a driving power distribution result of the double shaft in the ship by using a reinforcement learning model, dynamically adjust power output of the electric motor and the internal combustion engine, and monitor torque fluctuation of a transmission system in the ship during the dynamic adjustment by using a reverse torque feedback control algorithm, and feedback adjust power output of the electric motor and the internal combustion engine by using the torque fluctuation. To realize an electric shaft double-push ship power intelligent switching method as claimed in any one of claims 1-8.

Images