CN113525657B - Ship hybrid power hybrid model prediction control method based on hybrid logic dynamic theory - Google Patents
Ship hybrid power hybrid model prediction control method based on hybrid logic dynamic theory Download PDFInfo
- Publication number
- CN113525657B CN113525657B CN202110772092.5A CN202110772092A CN113525657B CN 113525657 B CN113525657 B CN 113525657B CN 202110772092 A CN202110772092 A CN 202110772092A CN 113525657 B CN113525657 B CN 113525657B
- Authority
- CN
- China
- Prior art keywords
- hybrid
- ship
- model
- control
- power
- 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.)
- Active
Links
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
- B63H21/21—Control means for engine or transmission, specially adapted for use on marine vessels
-
- 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
-
- 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
- B63H21/21—Control means for engine or transmission, specially adapted for use on marine vessels
- B63H2021/216—Control means for engine or transmission, specially adapted for use on marine vessels using electric control means
Abstract
The invention aims to provide a ship hybrid power hybrid model predictive control method based on a hybrid logic dynamic theory, wherein a ship hybrid power hybrid system model is established according to a system physical law, logic rules and operation constraints under a hybrid logic dynamic modeling frame; establishing hybrid model predictive optimization control based on a hybrid system, keeping an error weight matrix and a control weight matrix in a conventional performance index unchanged in a control process, and providing a neural network learning variable weight matrix hybrid model predictive control method based on working condition prediction in order to meet different control requirements such as rapidity, robustness and the like in different periods; determining the optimal power distribution combination of the hybrid power ship according to the energy optimization target so as to accurately manage the distributed power; the invention can effectively solve the problem of oscillation caused by mode switching, effectively improve the control effect of an energy management strategy and further improve the fuel economy of the ship.
Description
Technical Field
The invention relates to a ship energy management method, in particular to a ship power prediction control method.
Background
The hybrid power ship is a multi-power source system, and the performance of the whole system can be improved through the characteristic complementation of various power sources; the energy management control strategy is a key technology for realizing optimal performance, and is a core component of an energy management system, and the perfection of the strategy design directly determines the economy, the dynamic property and the emission property of the whole system; the main objective of energy management is to reasonably distribute and coordinate and control various power sources according to the operating characteristics and real-time working condition distribution of the system on the premise of meeting the dynamic performance of the ship, so that the efficient operation of each device can achieve the best performance.
At present, an energy management strategy actually applied to ship hybrid power is mainly based on a logic threshold and fuzzy reasoning energy management strategy; the rule-based energy management control strategy of the hybrid power system mainly focuses on the optimal power distribution of each power source and the classification of working modes, fuzzy rules have better robustness than logic thresholds, but threshold values and membership function settings related in the two modes are too dependent on expert experience, so that the optimal control effect is difficult to obtain in real time and the problem of oscillation is caused during mode switching.
Disclosure of Invention
The invention aims to provide a ship hybrid power hybrid model predictive control method based on a hybrid logic dynamic theory, which can improve the adaptability of working conditions, optimally distribute power sources and enable an engine and a motor to work in a high-efficiency interval.
The purpose of the invention is realized as follows:
the invention relates to a ship hybrid power hybrid model predictive control method based on a hybrid logic dynamic theory, which is characterized by comprising the following steps:
(1) building a ship hybrid power hybrid system model based on hybrid logic dynamics;
(2) further establishing hybrid system prediction control based on a hybrid ship model;
(3) a neural network learning variable weight matrix hybrid model prediction control method based on working condition prediction;
(4) and solving the hybrid model predictive control to obtain the optimal ship power distribution.
The present invention may further comprise:
1. the building of the ship hybrid power hybrid model system model in the step (1) specifically comprises the following steps:
(a) establishing a system state equation of a ship hybrid power system;
for a hybrid power system of a ship, the dynamic equation is as follows:
in the formula
Is a system state variable, y (t) cx (t) is a system output variable,
is a system control variable; omega is the output rotating speed, and SOC is the state of charge of the battery; p e (t)、P m (t) engine and motor target powers, respectively;
(b) introducing an auxiliary variable, and logically integrating the working mode and the switching condition;
the working mode specifically includes: a mechanical propulsion mode MP, a motor propulsion mode PTH, a host propulsion charging mode PTO and a hybrid propulsion mode Boost; the relationship of the auxiliary variables to the operating mode and the switching conditions is as follows:
in the formula
(equivalents) of the total amount of the components,
(XOR) is a logical operator;
the corresponding state equations of the power system in different modes are as follows:
(c) establishing a ship hybrid power system model by using a HYSDEL compiler in a hybrid system description language, and introducing the ship hybrid power system model into a hybrid logic dynamic framework through dynamic characteristics, operation constraints and logic rules of the ship hybrid power system;
the established MLD model is as follows:
in the formula
2. The hybrid system predictive control based on the hybrid ship model established in the step (2) is specifically as follows:
according to the requirements of the ship hybrid power control, a regulator type performance index function is designed as shown in the following formula, the system is returned to a design state by designing a control quantity u (k), and the index of the following formula is minimized:
3. the neural network learning variable weight matrix hybrid model prediction control method based on the working condition prediction in the step (3) specifically comprises the following steps:
(a) establishing a neural network variable weight matrix model based on working condition prediction;
firstly, initializing an action neural network, and inputting a training working condition, a control matrix weight matrix and an error weight matrix to carry out data training with a mentor; then, performing weight optimization on the output signal of the hybrid system based on the working condition prediction to obtain a neural network variable weight matrix model based on the working condition prediction;
(b) and in a prediction time domain, replacing control and error weight matrix coefficients in a performance index function in real time according to the neural network variable weight matrix model, and constructing the hybrid model prediction controller of the ship hybrid power.
4. Solving of the hybrid model predictive control in the step (4) to obtain the optimal distribution of the ship power specifically comprises:
generating a mixed integer quadratic programming problem for the corresponding controller as follows
s.t.Aq≤b+Cθ
Wherein q is ═ u 0 ,…u n-1 ,δ 0 ,…δ n-1 ,z 0 ,…z n-1 ]，θ＝[x,r x ,r y ,r u ,r z ]；
And solving by using a Gurobi solver, and taking the first element of the optimal control sequence as the control input of the current moment.
The invention has the advantages that: the invention can effectively solve the problem of oscillation caused by mode switching, effectively improve the control effect of an energy management strategy and further improve the fuel economy of the ship.
Drawings
FIG. 1 is a topology of the present invention suitable for use in a marine hybrid power system;
fig. 2 is a relationship between an auxiliary variable and a switching condition in the present invention.
Detailed Description
The invention will now be described in more detail by way of example with reference to the accompanying drawings in which:
with reference to fig. 1-2, the invention provides a ship hybrid model predictive control method based on hybrid logic dynamic theory, which establishes a ship hybrid system model according to the physical law, logic rules and operation constraints of the system under the framework of hybrid logic dynamic modeling; further establishing hybrid model predictive optimization control based on a hybrid system, and providing a neural network learning variable weight matrix hybrid model predictive control method based on working condition prediction in order to meet different control requirements such as rapidity, robustness and the like in different periods; determining the optimal power distribution combination of the hybrid power ship according to the energy optimization target so as to accurately manage the distributed power; the method comprises the following steps:
step 1: building a ship hybrid power hybrid system model based on hybrid logic dynamics;
step 2: further establishing hybrid system prediction control based on a hybrid ship model;
and step 3: a neural network learning variable weight matrix hybrid model prediction control method based on working condition prediction;
and 4, step 4: and solving the hybrid model predictive control to obtain the optimal distribution of the ship power.
The building of the ship hybrid model system model in the step 1 specifically comprises the following steps:
(a) establishing a system state equation of a ship hybrid power system;
for a hybrid power system of a ship, the dynamic equation is as follows:
in the formula
Is a system state variable, y (t) cx (t) is a system output variable,
is a system control variable; omega is the output rotating speed, and SOC is the state of charge of the battery; p e (t)、P m (t) engine and motor target powers, respectively.
(b) Introducing an auxiliary variable, and logically integrating the working mode and the switching condition;
the working mode specifically includes: a mechanical propulsion Mode (MP), a motor propulsion mode (PTH), a host propulsion charging mode (PTO), a hybrid propulsion mode (Boost); the relationship between the auxiliary variable and the working mode and the switching condition is shown in fig. 2, and the state equation of the power system corresponding to different modes is shown in the formula (2).
The logical relationship between the working mode and the switching condition is as follows:
in the formula
(equivalents) of the total amount of the components,
(XOR) is a logical operator;
(c) and establishing a ship hybrid power system model by using a HYSDEL compiler in the hybrid system description language.
The dynamic characteristics, operation constraints and logic rules of the ship hybrid power system are introduced into a hybrid logic dynamic framework.
The established MLD model is as follows:
in the formula
Establishing hybrid system predictive control based on a hybrid ship model in the step 2;
according to the requirements of ship hybrid power control, a regulator type performance index function is designed as shown in a formula (4), a system is returned to a design state through designing a control quantity u (k), and the index of the formula (4) is minimized.
The neural network learning variable weight matrix hybrid model predictive control method based on the working condition prediction in the step 3; the method specifically comprises the following steps:
(a) establishing a neural network variable weight matrix model based on working condition prediction;
firstly, initializing an action neural network, and inputting a training working condition, a control matrix weight matrix and an error weight matrix to carry out data training with a mentor; and then, carrying out weight optimization on the output signals of the hybrid system based on the working condition prediction to obtain a neural network variable weight matrix model based on the working condition prediction.
(b) And in a prediction time domain, replacing control and error weight matrix coefficients in a performance index function in real time according to the neural network variable weight matrix model, and constructing the hybrid model prediction controller of the ship hybrid power.
Solving hybrid model predictive control in the step 4 to obtain optimal distribution of ship power; the method specifically comprises the following steps:
generating the Mixed Integer Quadratic Program (MIQP) problem for the controller from equation (5) as follows
Wherein q is ═ u 0 ,…u n-1 ,δ 0 ,…δ n-1 ,z 0 ,…z n-1 ]，θ＝[x,r x ,r y ,r u ,r z ]
And solving by using a Gurobi solver, and taking the first element of the optimal control sequence as the control input of the current moment.
Claims (4)
1. The ship hybrid power hybrid model predictive control method based on the hybrid logic dynamic theory is characterized by comprising the following steps:
(1) building a ship hybrid power hybrid system model based on hybrid logic dynamics;
(2) further establishing hybrid system prediction control based on a hybrid ship model;
(3) performing variable weight matrix hybrid model predictive control based on a neural network predicted by working conditions;
(4) solving hybrid model predictive control to obtain optimal distribution of ship power;
the building of the ship hybrid power hybrid model system model in the step (1) specifically comprises the following steps:
(a) establishing a system state equation of a ship hybrid power system;
for a hybrid power system of a ship, the dynamic equation is as follows:
in the formula
Is a system state variable, y (t) cx (t) is a system output variable,
is a system control variable; omega is the output rotating speed, and SOC is the state of charge of the battery; p e (t)、P m (t) target power for engine and motor, P R Is the required power; j is the total moment of inertia of the hybrid power system; eta bat The working efficiency of the battery; eta m The propulsion efficiency of the motor; q is the capacity of the battery; v oc Is the open circuit voltage of the battery; c is the propulsion coefficient of the propeller; k is a charge and discharge conversion coefficient;
(b) introducing an auxiliary variable, and logically integrating the working mode and the switching condition;
the working mode specifically includes: a mechanical propulsion mode MP, a motor propulsion mode PTH, a host propulsion charging mode PTO and a hybrid propulsion mode Boost; the relationship of the auxiliary variables to the operating mode and the switching conditions is as follows:
in the formula
In the equivalent way, the first and second groups,
XOR is a logical operator; 1, (k) is work mode MP, PTH, PTO, Boost respectively; omega i,min ,ω i,max Maximum and minimum limit values of the output rotating speed under the corresponding working mode are respectively set; SOC i,min ,SOC i,max Maximum and minimum limit values of the state of charge in the corresponding working mode respectively;
the corresponding state equations of the power system in different modes are as follows:
(c) establishing a ship hybrid power system model by using a HYSDEL compiler in a hybrid system description language, and introducing the ship hybrid power system model into a hybrid logic dynamic framework through dynamic characteristics, operation constraints and logic rules of the ship hybrid power system;
the established MLD model is as follows:
in the formula
A、B j 、C、D j And E n Representing a real constant matrix, j 1,2,3, n 1,2, L, 5.
2. The hybrid logic dynamic theory-based ship hybrid model predictive control method according to claim 1, characterized in that: the hybrid system predictive control based on the hybrid ship model established in the step (2) is specifically as follows:
according to the requirements of the ship hybrid power control, a regulator type performance index function is designed as shown in the following formula, the system is returned to a design state by designing a control quantity u (k), and the index of the following formula is minimized:
in the formula, N is an optimal control interval; u. of min 、u max 、y min 、y max And x min 、x max Boundary minimum and maximum values for input, output and state variables, respectively; x is the number of N Is a terminal state value; x is the number of f Is the final target polyhedron subset of the state space; epsilon is a soft constraint adjusting threshold value; q x Is the state variable weight; q xN Weight for terminal state; q u Is a control variable weight; q z Is the weight of the auxiliary variable; q y Is the output variable weight; q ρ Is a soft constraint weight; x is the number of r ,u r ,z r ,y r Tracking targets for state, control, auxiliary, and output variables; p is a norm.
3. The hybrid logic dynamic theory-based ship hybrid model predictive control method according to claim 1, characterized in that: the neural network learning variable weight matrix hybrid model prediction control method based on the working condition prediction in the step (3) specifically comprises the following steps:
(a) establishing a neural network variable weight matrix model based on working condition prediction;
firstly, initializing an action neural network, and inputting a training working condition, a control matrix weight matrix and an error weight matrix to carry out data training with a mentor; then, performing weight optimization on the output signal of the hybrid system based on the working condition prediction to obtain a neural network variable weight matrix model based on the working condition prediction;
(b) and in a prediction time domain, replacing control and error weight matrix coefficients in a performance index function in real time according to the neural network variable weight matrix model, and constructing the hybrid model prediction controller of the ship hybrid power.
4. The hybrid logic dynamic theory-based ship hybrid model predictive control method according to claim 1, characterized in that: solving of the hybrid model predictive control in the step (4) to obtain the optimal distribution of the ship power specifically comprises:
generating a mixed integer quadratic programming problem for the corresponding controller as follows
Wherein q is ═ u 0 ,L u n-1 ,δ 0 ,Lδ n-1 ,z 0 ,L z n-1 ]，θ＝[x,r x ,r y ,r u ,r z ](ii) a H is a black plug matrix; d is a linear cost parameter matrix; y is a quadratic term matrix; f is a cost matrix; a is a constraint matrix; b is a constraint constant vector; c is a constraint matrix of theta;
and solving by using a Gurobi solver, and taking the first element of the optimal control sequence as the control input of the current moment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110772092.5A CN113525657B (en) | 2021-07-08 | 2021-07-08 | Ship hybrid power hybrid model prediction control method based on hybrid logic dynamic theory |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110772092.5A CN113525657B (en) | 2021-07-08 | 2021-07-08 | Ship hybrid power hybrid model prediction control method based on hybrid logic dynamic theory |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113525657A CN113525657A (en) | 2021-10-22 |
| CN113525657B true CN113525657B (en) | 2022-08-02 |
Family
ID=78127132
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110772092.5A Active CN113525657B (en) | 2021-07-08 | 2021-07-08 | Ship hybrid power hybrid model prediction control method based on hybrid logic dynamic theory |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113525657B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115395863B (en) * | 2022-10-28 | 2023-01-31 | 南京工程学院 | Active magnetic bearing control method based on hybrid system theory |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012092503A2 (en) * | 2010-12-29 | 2012-07-05 | Pierre Caouette | Electronic system and method of automating, controlling, and optimizing the operation of one or more energy storage units and a combined serial and parallel hybrid marine propulsion system |
| CN103770779A (en) * | 2014-01-25 | 2014-05-07 | 江苏大学 | Method for controlling energy management hybrid model of dual planetary hybrid electric automobile |
| CN107140168A (en) * | 2017-04-26 | 2017-09-08 | 武汉理工大学 | A kind of hybrid power ship EMS and control method based on WAVELET FUZZY logic |
| CN108100202A (en) * | 2017-12-25 | 2018-06-01 | 武汉理工大学 | LNG- battery hybrid marine propuision system power distribution methods |
| CN108622362A (en) * | 2018-01-25 | 2018-10-09 | 上海海事大学 | A kind of hybrid power ship energy management method based on switching system theory |
| CN110690730A (en) * | 2019-10-15 | 2020-01-14 | 哈尔滨工程大学 | Power and energy control method of hybrid power ship |
| CN111439249A (en) * | 2019-01-16 | 2020-07-24 | 通用汽车环球科技运作有限责任公司 | Model predictive control of a powertrain system using preview information |
| CN111907680A (en) * | 2020-09-07 | 2020-11-10 | 锡瑞迪船用动力系统(上海)有限公司 | Energy efficiency control system and method for hybrid power ship |
| CN112561169A (en) * | 2020-12-17 | 2021-03-26 | 西安理工大学 | Hybrid MPC energy management method for parallel hybrid electric vehicle |
| CN113071649A (en) * | 2021-04-22 | 2021-07-06 | 哈尔滨工程大学 | Ship gas-electric hybrid power mode switching coordination control strategy |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2643878A1 (en) * | 2008-11-14 | 2010-05-14 | Pierre Caouette | An electronic method of controlling propulsion & regeneration for electric, hybrid-electric and diesel-electric marine crafts |
| US9564757B2 (en) * | 2013-07-08 | 2017-02-07 | Eaton Corporation | Method and apparatus for optimizing a hybrid power system with respect to long-term characteristics by online optimization, and real-time forecasts, prediction or processing |
| TWI592335B (en) * | 2015-09-24 | 2017-07-21 | 財團法人船舶暨海洋產業研發中心 | Energy management method for boats and ships |
-
2021
- 2021-07-08 CN CN202110772092.5A patent/CN113525657B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012092503A2 (en) * | 2010-12-29 | 2012-07-05 | Pierre Caouette | Electronic system and method of automating, controlling, and optimizing the operation of one or more energy storage units and a combined serial and parallel hybrid marine propulsion system |
| CN103770779A (en) * | 2014-01-25 | 2014-05-07 | 江苏大学 | Method for controlling energy management hybrid model of dual planetary hybrid electric automobile |
| CN107140168A (en) * | 2017-04-26 | 2017-09-08 | 武汉理工大学 | A kind of hybrid power ship EMS and control method based on WAVELET FUZZY logic |
| CN108100202A (en) * | 2017-12-25 | 2018-06-01 | 武汉理工大学 | LNG- battery hybrid marine propuision system power distribution methods |
| CN108622362A (en) * | 2018-01-25 | 2018-10-09 | 上海海事大学 | A kind of hybrid power ship energy management method based on switching system theory |
| CN111439249A (en) * | 2019-01-16 | 2020-07-24 | 通用汽车环球科技运作有限责任公司 | Model predictive control of a powertrain system using preview information |
| CN110690730A (en) * | 2019-10-15 | 2020-01-14 | 哈尔滨工程大学 | Power and energy control method of hybrid power ship |
| CN111907680A (en) * | 2020-09-07 | 2020-11-10 | 锡瑞迪船用动力系统(上海)有限公司 | Energy efficiency control system and method for hybrid power ship |
| CN112561169A (en) * | 2020-12-17 | 2021-03-26 | 西安理工大学 | Hybrid MPC energy management method for parallel hybrid electric vehicle |
| CN113071649A (en) * | 2021-04-22 | 2021-07-06 | 哈尔滨工程大学 | Ship gas-electric hybrid power mode switching coordination control strategy |
Non-Patent Citations (3)
| Title |
|---|
| 孙晓军 姚崇 宋恩哲 张风林 白慧泉.船舶并联气电混合动力系统动态特性研究与能量效率分析.《推进技术》.2021, * |
| 朱琬璐.船舶综合电力推进系统数字化设计技术研究.《哈尔滨工程大学博士学位论文》.2016, * |
| 魏纳新.水面舰艇在高海情下的横摇运动姿态控制技术研究.《哈尔滨工程大学博士学位论文》.2006, * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113525657A (en) | 2021-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tian et al. | An ANFIS-based ECMS for energy optimization of parallel hybrid electric bus | |
| WO2022252559A1 (en) | Rule and double depth q-network-based hybrid vehicle energy management method | |
| CN110929920A (en) | Hybrid power train energy management method based on working condition identification | |
| Zhao et al. | A deep reinforcement learning framework for optimizing fuel economy of hybrid electric vehicles | |
| US7954579B2 (en) | Adaptive control strategy and method for optimizing hybrid electric vehicles | |
| CN107579518A (en) | Power system environment economic load dispatching method and apparatus based on MHBA | |
| Zhang et al. | Real-time optimization of energy management strategy for fuel cell vehicles using inflated 3D inception long short-term memory network-based speed prediction | |
| CN113525657B (en) | Ship hybrid power hybrid model prediction control method based on hybrid logic dynamic theory | |
| CN115241885B (en) | Power grid real-time scheduling optimization method and system, computer equipment and storage medium | |
| CN112491094B (en) | Hybrid-driven micro-grid energy management method, system and device | |
| Wu et al. | A logical network approximation to optimal control on a continuous domain and its application to HEV control | |
| CN112561169A (en) | Hybrid MPC energy management method for parallel hybrid electric vehicle | |
| Takahashi et al. | Model predictive control for hybrid electric vehicles with linear parameter-varying model | |
| CN111891111A (en) | Hybrid electric vehicle interval II type fuzzy logic self-adaptive control method based on MCPSO | |
| Gao et al. | Adaptive equivalent consumption minimization strategy for hybrid electric ship | |
| Mosayebi et al. | Smart extreme fast portable charger for electric vehicles-based artificial intelligence | |
| Yin et al. | Hybrid multi-agent emotional deep Q network for generation control of multi-area integrated energy systems | |
| CN116050461A (en) | Improved method for determining membership function of fuzzy control theory by using convolutional neural network | |
| CN115257697B (en) | Hybrid vehicle energy management and cooperative control method, system and application | |
| Yu | Fuzzy logic energy management strategy based on genetic algorithm for plug-in hybrid electric vehicles | |
| Feldkamp et al. | Recurrent neural network training for energy management of a mild hybrid electric vehicle with an ultra-capacitor | |
| CN113277095B (en) | Tandem type oil-electricity hybrid unmanned aerial vehicle energy management system and method | |
| CN115360768A (en) | Power scheduling method and device based on muzero and deep reinforcement learning and storage medium | |
| CN112350316B (en) | Variable-discourse-domain cloud PI load frequency control method based on cloud scaling factor | |
| CN114583696A (en) | Power distribution network reactive power optimization method and system based on BP neural network and scene matching |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |