CN114655412A - Hybrid ship torque distribution method, system, device and storage medium - Google Patents
Hybrid ship torque distribution method, system, device and storage medium Download PDFInfo
- Publication number
- CN114655412A CN114655412A CN202210259422.5A CN202210259422A CN114655412A CN 114655412 A CN114655412 A CN 114655412A CN 202210259422 A CN202210259422 A CN 202210259422A CN 114655412 A CN114655412 A CN 114655412A
- Authority
- CN
- China
- Prior art keywords
- ship
- working
- torque distribution
- torque
- hybrid
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 68
- 230000002787 reinforcement Effects 0.000 claims abstract description 33
- 238000013210 evaluation model Methods 0.000 claims abstract description 32
- 238000011156 evaluation Methods 0.000 claims abstract description 18
- 238000004146 energy storage Methods 0.000 claims description 27
- 239000003990 capacitor Substances 0.000 claims description 23
- 230000008569 process Effects 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 8
- 238000010248 power generation Methods 0.000 claims description 8
- 230000001133 acceleration Effects 0.000 claims description 4
- 239000003921 oil Substances 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000011217 control strategy Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 239000010705 motor oil Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63H—MARINE PROPULSION OR STEERING
- B63H21/00—Use of propulsion power plant or units on vessels
- B63H21/20—Use of propulsion power plant or units on vessels the vessels being powered by combinations of different types of propulsion units
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63H—MARINE PROPULSION OR STEERING
- B63H21/00—Use of propulsion power plant or units on vessels
- B63H21/20—Use of propulsion power plant or units on vessels the vessels being powered by combinations of different types of propulsion units
- B63H2021/202—Use of propulsion power plant or units on vessels the vessels being powered by combinations of different types of propulsion units of hybrid electric type
Landscapes
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Ocean & Marine Engineering (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The invention discloses a torque distribution method, a system, a device and a storage medium for a hybrid power ship, and relates to the technical field of hybrid power ship control. The torque distribution method of the hybrid power ship comprises the following steps: determining a current working mode of the hybrid power ship; determining a ship working component according to the working mode; predicting the required torque of the ship according to the working mode; acquiring the current working state parameters of the ship working component; determining a first torque distribution result according to the working state parameter and the ship required torque by a dynamic linear programming method; inputting the working state parameters into a reinforcement learning evaluation model to evaluate the running state of the ship; and correcting the first torque distribution result according to the evaluation result of the ship running state to obtain a second torque distribution result. This application can improve the performance of boats and ships navigation in-process to different grade type boats and ships dynamic allocation moment of torsion.
Description
Technical Field
The invention relates to the technical field of hybrid ship control, in particular to a method, a system, a device and a storage medium for torque distribution of a hybrid ship.
Background
At present, a torque distribution method adopted by a hybrid ship is mainly an energy management method based on rules, such as an energy management control strategy based on a static logic gate, an energy management control strategy based on fuzzy control and the like, that is, a corresponding rule is set for a specific type of hybrid ship to perform torque distribution, and the method is too dependent on experience and is rigid, and has poor adaptability to other types of hybrid ships, and a series of problems such as low efficiency, high oil consumption, overload of a motor and the like may be caused when the method is applied to other types of hybrid ships.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art. Therefore, the invention provides a torque distribution method, a system, a device and a storage medium for a hybrid power ship, which can dynamically distribute torques for different types of ships and improve the performance of the ships in the sailing process.
In one aspect, an embodiment of the present invention provides a torque distribution method for a hybrid ship, including the following steps:
determining a current working mode of the hybrid power ship;
determining a ship working component according to the working mode;
predicting the required torque of the ship according to the working mode;
acquiring the current working state parameters of the ship working component;
determining a first torque distribution result according to the working state parameter and the ship required torque by a dynamic linear programming method;
inputting the working state parameters into a reinforcement learning evaluation model to evaluate the running state of the ship;
and correcting the first torque distribution result according to the evaluation result of the ship running state to obtain a second torque distribution result.
According to some embodiments of the invention, the reinforcement learning evaluation model is obtained by:
establishing a digital twin model and initializing model parameters of the digital twin model;
inputting actual navigation data in the navigation process of a ship into the digital twin model to determine a loss value of the digital twin model, and correcting the model parameters according to the loss value to optimize the digital twin model;
and repeating the step of inputting the actual navigation data in the ship navigation process into the digital twin model to determine the loss value of the digital twin model, and correcting the model parameters according to the loss value to optimize the digital twin model until the loss value of the digital twin model is less than the loss preset value, thereby obtaining the reinforcement learning evaluation model.
According to some embodiments of the invention, the step of inputting actual navigation data during the navigation of the ship into the digital twin model to determine the loss value of the digital twin model comprises the following steps:
inputting the working state of the ship working component in the actual navigation data into the digital twin model to obtain a ship running state virtual evaluation value of the ship running state;
and determining the loss value according to the ship running state feedback value and the ship running state evaluation value in the actual navigation data.
According to some embodiments of the invention, the determining the current operating mode of the hybrid vessel comprises:
collecting load information and channel information of a ship;
determining a working scene according to the load information and the channel information;
and determining a working mode according to the working scene.
According to some embodiments of the invention, the determining the operation mode according to the operation scenario comprises:
when the working scene is in-port attitude adjustment, the working mode is a motor propulsion mode;
when the working scene is a medium-speed channel cruise, the working mode is an engine propulsion mode;
when the working scene is emergency acceleration, the working mode is a hybrid power propulsion and super capacitor power auxiliary mode;
when the working scene is high-speed channel cruising, the working mode is a hybrid power propulsion mode;
and when the working scene is low-speed channel cruising, the working mode is a hybrid power generation propulsion mode.
According to some embodiments of the invention, the hybrid powertrain system torque distribution method further comprises the steps of:
acquiring a torque limit interval of the ship working component and the residual electric quantity of the energy storage system;
and when the second torque distribution result meets the torque limit interval and the residual capacity of the energy storage system is enough to provide electric energy for the motor, feeding the second torque distribution result back to a ship control system, and otherwise, taking the second torque distribution result as the first torque distribution result and correcting according to the reinforcement learning evaluation model.
According to some embodiments of the invention, the determining a first torque distribution result according to the operating state parameter and the ship required torque by the method of dynamic linear programming comprises the following steps:
constructing a dynamic decision model consisting of a plurality of single-stage decision functions according to the MAP of the ship working part;
and inputting the working state parameters and the ship required torque into the dynamic decision model to obtain a first torque distribution result, wherein the working state parameters comprise the current rotating speed of a ship working component.
In another aspect, an embodiment of the present invention further provides a hybrid ship torque distribution system, including:
the system comprises a first module, a second module and a third module, wherein the first module is used for determining the current working mode of the hybrid power ship;
the second module is used for determining a ship working component according to the working mode;
a third module for predicting a ship demand torque according to the working mode;
the fourth module is used for acquiring the current working state parameters of the ship working component;
a fifth module, configured to determine a first torque distribution result according to the operating state parameter and the ship demand torque by a dynamic linear programming method;
the sixth module is used for inputting the working state parameters into a reinforcement learning evaluation model to evaluate the running state of the ship;
and the seventh module is used for correcting the first torque distribution result according to the evaluation result of the running state of the ship to obtain a second torque distribution result.
In another aspect, an embodiment of the present invention further provides a hybrid ship torque distribution device, including:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the hybrid marine torque distribution method as previously described.
In another aspect, embodiments of the present invention also provide a computer-readable storage medium having stored thereon computer-executable instructions for causing a computer to perform a hybrid marine torque distribution method as described above.
The technical scheme of the invention at least has one of the following advantages or beneficial effects: after the current working mode of the hybrid power ship is determined, the ship working part is determined according to the working mode, the ship required torque is predicted according to the working mode, the working state parameters of the current ship working part are collected, then a first torque distribution result is determined according to the working state parameters and the ship required torque through a dynamic linear programming method, and the torque distribution is performed through the dynamic linear programming method after the ship required torque is predicted, so that the first torque distribution result is high in instantaneity and flexibility, and can be adapted to the change of the ship required torque in time. And then, inputting the working state parameters into a reinforcement learning evaluation model to evaluate the running state of the ship, correcting the first torque distribution result according to the evaluation result of the running state of the ship to obtain a second torque distribution result, evaluating the running state of the ship through the reinforcement learning model evaluation model, and correcting the first torque distribution result based on the evaluation result, so that the final second torque distribution result can be adapted to the ship, and the performance of the ship in the sailing process can be optimized by using the second torque distribution result.
Drawings
FIG. 1 is a flow chart of a hybrid marine torque distribution method provided by an embodiment of the present invention;
fig. 2 is a schematic diagram of a hybrid ship torque distribution device provided by the embodiment of the invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or components having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, if there are first, second, etc. described, they are only used for distinguishing technical features, but they are not interpreted as indicating or implying relative importance or implicitly indicating the number of indicated technical features or implicitly indicating the precedence of the indicated technical features.
Referring to fig. 1, the hybrid ship torque distribution method according to the embodiment of the present invention includes, but is not limited to, step S110, step S120, step S130, step S140, step S150, step S160, and step S170.
Step S110, determining the current working mode of the hybrid power ship;
step S120, determining a ship working component according to the working mode;
step S130, predicting the required torque of the ship according to the working mode;
step S140, collecting working state parameters of the current ship working component;
step S150, determining a first torque distribution result according to the working state parameters and the ship required torque by a dynamic linear programming method;
step S160, inputting the working state parameters into a reinforcement learning evaluation model to evaluate the running state of the ship;
and S170, correcting the first torque distribution result according to the evaluation result of the ship running state to obtain a second torque distribution result.
In the present embodiment, the operation modes of the ship include, but are not limited to, five operation modes of motor propulsion, engine propulsion, hybrid propulsion plus super capacitor power assist, hybrid propulsion, and hybrid power generation propulsion. According to the working mode, the corresponding ship working component can be determined, for example, in the working mode of motor propulsion, the ship working component is a motor; under the working mode of engine propulsion, the ship working part is an engine, and under the working mode of hybrid propulsion and super capacitor power assistance, the ship working part is a motor and an engine, wherein the motor is driven by the super capacitor assistance; in a hybrid propulsion working mode, the ship working components are a motor and an engine; in the hybrid power generation and propulsion mode of operation, the marine vessel's working components are the engine and the electric machine, wherein the electric machine is in the power generation mode. It should be noted that the motor in this embodiment includes an energy storage unit for supplying electric energy and a driving motor.
After the working mode is determined, the required torque of the ship can be predicted according to the working mode, specifically, the target navigational speed in different working modes can be simulated in advance to predict the power, and then the required power is determined by utilizing a torque, rotating speed and power calculation formula according to the predicted power. And then acquiring working state parameters of the current ship working part, determining a first torque distribution result according to the working state parameters and the ship required torque by a dynamic linear programming method, and performing torque distribution by a dynamic linear programming method after the ship required torque is predicted, so that the first torque distribution result has high real-time performance and flexibility, and can adapt to the change of the ship required torque in time.
After the first torque distribution result is obtained, the working state parameters are input into a reinforcement learning evaluation model to evaluate the running state of the ship, the first torque distribution result is corrected according to the evaluation result of the running state of the ship to obtain a second torque distribution result, the running state of the ship, including the states of motor power, engine oil consumption, exhaust emission and the like, is evaluated through the reinforcement learning model evaluation model, the first torque distribution result is corrected based on the evaluation result, the final second torque distribution result can be adapted to the ship, and the performance of the ship in the sailing process can be optimized by using the second torque distribution result. Therefore, the dynamic real-time distribution process of the advance torque of the hybrid power ship is realized, and the distribution result is strong in adaptability.
According to some embodiments of the present invention, the reinforcement learning evaluation model is obtained by:
step S210, establishing a digital twin model and initializing model parameters of the digital twin model;
step S220, inputting actual navigation data in the navigation process of the ship into a digital twin model to determine a loss value of the digital twin model, and correcting model parameters according to the loss value to optimize the digital twin model;
and S230, repeatedly inputting actual navigation data in the navigation process of the ship into the digital twin model to determine the loss value of the digital twin model, and correcting the model parameters according to the loss value to optimize the digital twin model until the loss value of the digital twin model is smaller than a loss preset value, so as to obtain the reinforcement learning evaluation model.
In the embodiment, the actual navigation data of the ship is generated and input into the digital twin model for reinforcement learning in the driving process, the ship can distribute torque mainly by dynamic linear programming before the loss value of the digital twin model is smaller than the preset loss value, and in the process, the digital twin model can autonomously learn the navigation condition, decision and other relevant actual navigation data of the ship for model optimization. And transferring the digital twin model to the environment for use until the loss value of the digital twin model is smaller than a preset loss value so as to optimize the torque distribution result of the dynamic linear programming.
According to some embodiments of the present invention, the step S220 of inputting the actual navigation data of the ship during the navigation process into the digital twin model to determine the loss value of the digital twin model comprises the following steps:
step S310, inputting the working state of the ship working component in the actual navigation data into a digital twin model to obtain a ship running state virtual evaluation value of the ship running state;
and step S320, determining a loss value according to the ship running state feedback value and the ship running state evaluation value in the actual navigation data.
In the embodiment, the loss value is calculated through a loss function, the loss function is used for measuring the degree of inconsistency between the predicted value and the true value of the model, and the smaller the loss function is, the better the robustness of the model is.
According to some embodiments of the invention, the hybrid system torque distribution method further comprises the steps of:
step S410, acquiring a torque limit interval of a ship working component and the residual electric quantity of an energy storage system;
step S420, when the second torque distribution result satisfies the torque limit interval and the remaining capacity of the energy storage system is sufficient to provide electric energy for the motor, feeding the second torque distribution result back to the ship control system, otherwise, using the second torque distribution result as the first torque distribution result, and performing correction according to the reinforcement learning evaluation model.
In this embodiment, if the ship working component includes the motor, when the distribution result respectively satisfies the torque limit intervals of the motor and the engine and the remaining capacity of the energy storage system is sufficient to provide electric energy for the motor, the distribution result is fed back to the ship control system for execution, otherwise, the correction is continued according to the reinforcement learning evaluation model. If the ship working component is only the engine, when the torque distribution result of the engine meets the torque limit interval of the engine and the residual electric quantity of the energy storage system is enough to provide electric energy for the motor (at the moment, the electric energy required by the motor is zero), the torque distribution result of the engine is fed back to the ship control system to be executed, otherwise, the correction is continued according to the reinforcement learning evaluation model.
According to some embodiments of the invention, step S150 comprises the steps of:
step S510, constructing a dynamic decision model composed of a plurality of single-stage decision functions according to the MAP of the ship working part;
step S520, inputting the working state parameters and the ship required torque into the dynamic decision model to obtain a first torque distribution result, wherein the working state parameters comprise the current rotating speed of the ship working component.
In this embodiment, a dynamic linear programming method is adopted to convert a multi-stage problem into a plurality of single-stage problems to solve the multi-stage problems to obtain a first torque distribution result, so that the computational complexity can be reduced.
According to some embodiments of the invention, determining the current operating mode of the hybrid vessel comprises the steps of:
step S610, collecting load information and channel information of a ship;
step S620, determining a working scene according to the load information and the channel information;
step S630, determining the working mode according to the working scene.
In this embodiment, the load information includes, but is not limited to, information such as engine speed, engine torque, motor speed, motor torque, propeller speed, propeller torque, and energy storage system power supply load.
In the present embodiment, the working scenarios include, but are not limited to, in-port attitude adjustment, medium-speed channel cruising, emergency acceleration, high-speed channel cruising, and low-speed channel cruising. Illustratively, when the channel information indicates that a dense obstacle exists around the channel, the water flow is continuous and smooth, the load information indicates the frequent small increment change speed of the power system, and the working scene can be determined to be the posture adjustment in the harbor.
According to some embodiments of the invention, step S430 comprises the steps of:
when the working scene is the posture adjustment in the harbor, the working mode is a motor propulsion mode;
when the working scene is a medium-speed channel cruise, the working mode is an engine propulsion mode;
when the working scene is emergency acceleration, the working mode is a hybrid power propulsion and super capacitor power auxiliary mode;
when the working scene is high-speed channel cruising, the working mode is a hybrid power propulsion mode;
when the working scene is low-speed channel cruising, the working mode is a hybrid power generation propulsion mode or a motor propulsion mode with sufficient electric quantity.
The first embodiment is as follows: the ship working component in the motor propelling mode is a motor, and energy storage units such as a battery pack, a super capacitor and the like are used for providing energy for the motor. And primarily distributing energy output among different energy storage units by adopting a dynamic linear programming method according to the current rotating speed of the motor, the MAP (MAP) of the motor and the predicted required torque so as to obtain a first torque distribution result of the motor. The method comprises the steps of collecting the rotating speed of a current motor and residual energy values and efficiency values of different energy storage units, inputting the residual energy values and the efficiency values into a reinforcement learning evaluation model to evaluate the running state of a ship comprising the working states of a driving motor and the energy storage units, automatically modifying energy output among the different energy storage units according to the evaluation values to further obtain a distribution result of motor torque, if the motor torque is within a motor torque limit range and each energy storage unit has enough electric energy to provide required power for the motor, sending the motor torque to a corresponding control system, and if not, returning to the reinforcement learning evaluation model to evaluate and distribute again.
Example two: the working part of the ship cruising on the medium-speed channel is an engine, and a first distribution result is obtained by adopting a dynamic linear programming method according to the rotating speed of the current engine, an MAP (MAP) diagram of the engine and the predicted required torque. The current working state of the engine including rotating speed, emission, oil consumption and efficiency value is input into a reinforcement learning evaluation model to evaluate the ship running state including engine economy, emission and working state, and the energy output of the engine is automatically modified according to the evaluation value so as to obtain the engine torque distribution result. And if the engine torque is within the engine torque limit range, sending the engine torque to a corresponding control system, and otherwise, returning to the reinforcement learning evaluation model for reevaluation and distribution.
Example three: the hybrid propulsion plus super capacitor power assist mode of operation requires both the engine and the electric machine to be involved in operation. And according to the current rotating speed of the engine/motor, the MAP (MAP of the engine/motor) and the predicted required torque, carrying out initial distribution on the torque of the engine/motor and the energy output among different energy storage units (comprising super capacitors) by adopting a dynamic linear programming method. The collected working states of current engine emission, oil consumption and efficiency values, the rotating speed of a driving motor, the residual energy value and the efficiency value among different energy storage units (including super capacitors) of the motor and the like are input into a reinforcement learning evaluation model to evaluate the working states of the engine such as the economy, the emission performance and the rotating speed, the rotating speed of the driving motor, the ship running state of the working states of the motors such as the energy storage units (including super capacitors) and the like, and the energy output among the engine and the different energy storage units (including super capacitors) is automatically modified according to the evaluation values. And if the engine torque and the motor torque are respectively in the corresponding torque limit ranges and each energy storage unit (comprising a super capacitor) has enough electric energy to provide the required power for the motor, the torque distribution results of the engine and the motor are sent to the corresponding control system, and if not, the torque distribution results are returned to the reinforcement learning evaluation model for reevaluation and distribution.
Example four: and performing initial distribution on the torque of the engine/motor and the energy output between different energy storage units (without super capacitors) by adopting a dynamic linear programming method according to the current rotating speed of the engine/motor, the MAP (MAP of the engine/motor) and the predicted required torque. The collected working states of current engine emission, oil consumption and efficiency values, residual energy values and efficiency values among the rotating speed of a driving motor and different energy storage units (without super capacitors) of the motor are input into a reinforcement learning evaluation model to evaluate the working states of the engine such as economy, emission, rotating speed and the like, the rotating speed of the driving motor and the ship running state of the working states of the motors such as the energy storage units (without super capacitors) are driven, and energy output among the engine and the different energy storage units (without super capacitors) is automatically modified according to the evaluation values. And if the engine torque and the motor torque are respectively in the corresponding torque limit ranges and each energy storage unit (without a super capacitor) has enough electric energy to provide the required power for the motor, the torque distribution results of the engine and the motor are sent to the corresponding control system, and if not, the torque distribution results are returned to the reinforcement learning evaluation model for reevaluation and distribution.
Example five: the hybrid power generation propulsion working mode requires the engine and the motor to both work, and the motor is in a generator mode due to the fact that the SOC value of the battery pack in the energy storage system is too low. And primarily distributing the torque of the engine/motor by adopting a dynamic linear programming method according to the current rotating speed of the engine/motor, the engine MAP, the power generation MAP of the motor and the predicted required torque. And inputting the collected working states of the current engine emission, oil consumption and efficiency values, the rotating speed of the driving motor, the residual energy value of the battery pack/super capacitor and the like into a reinforcement learning evaluation model to evaluate the economic performance, the emission performance, the working state of the rotating speed, the rotating speed of the driving motor, the charging efficiency of the battery pack/super capacitor and other ship running states of the engine, the battery pack and the super capacitor, and automatically modifying the energy input among the engine, the battery pack and the super capacitor according to the evaluation values. And if the engine torque and the motor torque are respectively in the corresponding torque limit ranges and the electric energy of the battery pack or the super capacitor does not exceed the maximum value of the high-efficiency interval, transmitting the torque distribution results of the engine and the motor to a corresponding control system, and otherwise, returning to the reinforcement learning evaluation model for reevaluation and distribution.
In another aspect, an embodiment of the present invention further provides a hybrid ship torque distribution system, including:
the system comprises a first module, a second module and a third module, wherein the first module is used for determining the current working mode of the hybrid power ship;
the second module is used for determining a ship working component according to the working mode;
the third module is used for predicting the required torque of the ship according to the working mode;
the fourth module is used for acquiring the working state parameters of the current ship working component;
the fifth module is used for determining a first torque distribution result according to the working state parameters and the ship required torque by a dynamic linear programming method;
the sixth module is used for inputting the working state parameters into the reinforcement learning evaluation model to evaluate the running state of the ship;
and the seventh module is used for correcting the first torque distribution result according to the evaluation result of the running state of the ship to obtain a second torque distribution result.
It can be understood that the contents in the above-mentioned embodiment of the method for distributing torque of a hybrid vessel are all applicable to the embodiment of the present system, the functions specifically implemented by the embodiment of the present system are the same as those in the above-mentioned embodiment of the method for distributing torque of a hybrid vessel, and the advantages achieved by the embodiment of the present system are also the same as those achieved by the above-mentioned embodiment of the method for distributing torque of a hybrid vessel.
Referring to fig. 2, fig. 2 is a schematic diagram of a hybrid marine torque distribution apparatus according to an embodiment of the present invention. The hybrid vessel torque distribution device according to the embodiment of the present invention includes one or more control processors and a memory, and fig. 2 illustrates one control processor and one memory as an example.
The control processor and the memory may be connected by a bus or other means, as exemplified by the bus connection in fig. 2.
The memory, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs as well as non-transitory computer executable programs. Further, the memory may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory remotely located from the control processor, and the remote memory may be connected to the hybrid marine torque distribution device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Those skilled in the art will appreciate that the configuration of the apparatus shown in fig. 2 does not constitute a limitation of the hybrid marine torque distribution apparatus and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.
The non-transitory software programs and instructions required to implement the hybrid vessel torque distribution method applied to the hybrid vessel torque distribution device in the above-described embodiment are stored in a memory and, when executed by a control processor, perform the hybrid vessel torque distribution method applied to the hybrid vessel torque distribution device in the above-described embodiment.
Furthermore, an embodiment of the present invention also provides a computer-readable storage medium storing computer-executable instructions that, when executed by one or more control processors, cause the one or more control processors to perform the hybrid marine torque distribution method of the above method embodiment.
One of ordinary skill in the art will appreciate that all or some of the steps, systems, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (10)
1. A hybrid marine torque distribution method, comprising the steps of:
determining a current working mode of the hybrid power ship;
determining a ship working component according to the working mode;
predicting the required torque of the ship according to the working mode;
acquiring the current working state parameters of the ship working component;
determining a first torque distribution result according to the working state parameters and the ship required torque by a dynamic linear programming method;
inputting the working state parameters into a reinforcement learning evaluation model to evaluate the running state of the ship;
and correcting the first torque distribution result according to the evaluation result of the ship running state to obtain a second torque distribution result.
2. The hybrid marine torque distribution method according to claim 1, wherein the reinforcement learning evaluation model is obtained by:
establishing a digital twin model and initializing model parameters of the digital twin model;
inputting actual navigation data in the navigation process of a ship into the digital twin model to determine a loss value of the digital twin model, and correcting the model parameters according to the loss value to optimize the digital twin model;
and repeating the step of inputting the actual navigation data in the navigation process of the ship into the digital twin model to determine the loss value of the digital twin model and correcting the model parameters according to the loss value to optimize the digital twin model until the loss value of the digital twin model is less than the loss preset value, thereby obtaining the reinforcement learning evaluation model.
3. The hybrid ship torque distribution method according to claim 1, wherein the inputting of actual sailing data during the sailing of the ship into the digital twin model to determine the loss value of the digital twin model comprises the steps of:
inputting the working state of the ship working component in the actual navigation data into the digital twin model to obtain a ship running state virtual evaluation value of the ship running state;
and determining the loss value according to the ship running state feedback value and the ship running state virtual evaluation value in the actual navigation data.
4. The hybrid marine vessel torque distribution method of claim 1, wherein said determining the current operating mode of the hybrid marine vessel comprises the steps of:
collecting load information and channel information of a ship;
determining a working scene according to the load information and the channel information;
and determining a working mode according to the working scene.
5. The hybrid marine vessel torque distribution method according to claim 4, wherein the determining an operation mode according to the operation scenario includes the steps of:
when the working scene is the posture adjustment in the harbor, the working mode is a motor propulsion mode;
when the working scene is a medium-speed channel cruise, the working mode is an engine propulsion mode;
when the working scene is emergency acceleration, the working mode is a hybrid propulsion and super capacitor power auxiliary mode;
when the working scene is high-speed channel cruising, the working mode is a hybrid power propulsion mode;
and when the working scene is low-speed channel cruising, the working mode is a hybrid power generation propulsion mode.
6. The hybrid marine torque splitting method of claim 1, further comprising the steps of:
acquiring a torque limit interval of the ship working component and the residual electric quantity of the energy storage system;
and when the second torque distribution result meets the torque limit interval and the residual capacity of the energy storage system is enough to provide electric energy for the motor, feeding the second torque distribution result back to a ship control system, and otherwise, taking the second torque distribution result as the first torque distribution result and correcting according to the reinforcement learning evaluation model.
7. The hybrid marine torque distribution method of claim 1, wherein said determining a first torque distribution result from said operating state parameters and said marine demanded torque by a method of dynamic linear programming comprises the steps of:
constructing a dynamic decision model consisting of a plurality of single-stage decision functions according to the MAP of the ship working part;
and inputting the working state parameters and the ship required torque into the dynamic decision model to obtain a first torque distribution result, wherein the working state parameters comprise the current rotating speed of a ship working component.
8. A hybrid marine torque distribution system, comprising:
the system comprises a first module, a second module and a third module, wherein the first module is used for determining the current working mode of the hybrid power ship;
the second module is used for determining a ship working component according to the working mode;
a third module for predicting a ship demand torque according to the working mode;
the fourth module is used for acquiring the current working state parameters of the ship working component;
a fifth module, configured to determine a first torque distribution result according to the operating state parameter and the ship demand torque by a dynamic linear programming method;
the sixth module is used for inputting the working state parameters into a reinforcement learning evaluation model to evaluate the running state of the ship;
and the seventh module is used for correcting the first torque distribution result according to the evaluation result of the running state of the ship to obtain a second torque distribution result.
9. A hybrid marine torque distribution device, comprising:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the hybrid marine torque distribution method of any one of claims 1 to 7.
10. A computer readable storage medium in which a processor-executable program is stored, wherein the processor-executable program, when executed by the processor, is for implementing the hybrid marine torque distribution method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210259422.5A CN114655412A (en) | 2022-03-16 | 2022-03-16 | Hybrid ship torque distribution method, system, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210259422.5A CN114655412A (en) | 2022-03-16 | 2022-03-16 | Hybrid ship torque distribution method, system, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114655412A true CN114655412A (en) | 2022-06-24 |
Family
ID=82029576
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210259422.5A Pending CN114655412A (en) | 2022-03-16 | 2022-03-16 | Hybrid ship torque distribution method, system, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114655412A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010123636A2 (en) * | 2009-04-24 | 2010-10-28 | General Electric Company | Method and system for controlling propulsion systems |
| CN105035296A (en) * | 2015-08-11 | 2015-11-11 | 上海海事大学 | Automatic energy system working mode switching device and method for hybrid electric propulsion ship |
| CN108100202A (en) * | 2017-12-25 | 2018-06-01 | 武汉理工大学 | LNG- battery hybrid marine propuision system power distribution methods |
| CN111409623A (en) * | 2020-03-10 | 2020-07-14 | 科力远混合动力技术有限公司 | Torque control method in mode switching process of hybrid electric vehicle |
| CN113619558A (en) * | 2020-05-06 | 2021-11-09 | 上海汽车集团股份有限公司 | Torque distribution method and system for hybrid system vehicle |
| CN113886973A (en) * | 2021-10-25 | 2022-01-04 | 江苏远望仪器集团有限公司 | Ship navigational speed processing method, device and processing equipment based on virtual-real mapping |
-
2022
- 2022-03-16 CN CN202210259422.5A patent/CN114655412A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010123636A2 (en) * | 2009-04-24 | 2010-10-28 | General Electric Company | Method and system for controlling propulsion systems |
| CN105035296A (en) * | 2015-08-11 | 2015-11-11 | 上海海事大学 | Automatic energy system working mode switching device and method for hybrid electric propulsion ship |
| CN108100202A (en) * | 2017-12-25 | 2018-06-01 | 武汉理工大学 | LNG- battery hybrid marine propuision system power distribution methods |
| CN111409623A (en) * | 2020-03-10 | 2020-07-14 | 科力远混合动力技术有限公司 | Torque control method in mode switching process of hybrid electric vehicle |
| CN113619558A (en) * | 2020-05-06 | 2021-11-09 | 上海汽车集团股份有限公司 | Torque distribution method and system for hybrid system vehicle |
| CN113886973A (en) * | 2021-10-25 | 2022-01-04 | 江苏远望仪器集团有限公司 | Ship navigational speed processing method, device and processing equipment based on virtual-real mapping |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110834621B (en) | Torque distribution control method for light hybrid vehicle, storage medium and vehicle | |
| CN110450641B (en) | Automobile braking energy recovery method and device and electric automobile | |
| CN110696810B (en) | Energy management method and device for hybrid electric vehicle, vehicle and storage medium | |
| CN104508937B (en) | Charge-discharge controller, charge-discharge control system, charge/discharge control method and program | |
| CN110718940B (en) | Multi-energy ship intelligent power distribution method and device based on load prediction | |
| JP2018083574A (en) | Travel control device for vehicle | |
| CN113715798B (en) | ISG motor compensation control method and device | |
| CN110979335A (en) | Hybrid power system energy efficiency calculation method, calculation system and vehicle | |
| CN114655412A (en) | Hybrid ship torque distribution method, system, device and storage medium | |
| Ali et al. | Observer-based power management for multi-source electric vehicles using optimized splitting ratios | |
| CN115071670A (en) | Hybrid power system control method and device and vehicle | |
| CN215097538U (en) | Range extender control device, range extender and vehicle | |
| CN114722489A (en) | Ship power system model selection method and device and storage medium | |
| Diju et al. | Control strategy of hybrid electric ship based on improved fuzzy logic threshold | |
| US20170282896A1 (en) | Motive power system, transportation apparatus, and power transmission method | |
| CN114919565A (en) | Vehicle and torque control method and system thereof | |
| CN114312742A (en) | Driving power generation control method and device, storage medium and vehicle control unit | |
| JP6471599B2 (en) | Vehicle power generation control device | |
| JP2021195043A (en) | Hybrid vehicle control system and control method | |
| US11563330B2 (en) | Electric vehicle control device and electric vehicle | |
| Radrizzani et al. | An efficiency based approach for the energy management in hevs | |
| Papalambrou et al. | Transient and disturbed propeller load compensation in hybrid propulsion using propeller estimator and predictive control | |
| WO2014112309A1 (en) | Drive system for unmanned transport vehicle | |
| Zhu | Modelling, design and energy management of a hybrid electric ship–a case study | |
| CN112356821B (en) | Vehicle torque maximum limit value calculation method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220624 |
|
| RJ01 | Rejection of invention patent application after publication |