CN108177648A - A kind of energy management method of the plug-in hybrid vehicle based on intelligent predicting - Google Patents
A kind of energy management method of the plug-in hybrid vehicle based on intelligent predicting Download PDFInfo
- Publication number
- CN108177648A CN108177648A CN201810003711.2A CN201810003711A CN108177648A CN 108177648 A CN108177648 A CN 108177648A CN 201810003711 A CN201810003711 A CN 201810003711A CN 108177648 A CN108177648 A CN 108177648A
- Authority
- CN
- China
- Prior art keywords
- model
- information
- power battery
- vehicle
- energy
- 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.)
- Granted
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W20/00—Control systems specially adapted for hybrid vehicles
- B60W20/10—Controlling the power contribution of each of the prime movers to meet required power demand
- B60W20/11—Controlling the power contribution of each of the prime movers to meet required power demand using model predictive control [MPC] strategies, i.e. control methods based on models predicting performance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02T90/10—Technologies relating to charging of electric vehicles
- Y02T90/14—Plug-in electric vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The present invention provides a kind of energy management methods of the plug-in hybrid vehicle based on intelligent predicting, and the driving cycle information for having the characteristics that multi-source, mixing is utilized, and on-line study optimization PHEV global energies distribute, and improve the intelligent level of hybrid power system;Real-time learning and prediction model are established, improves the operating mode precision of prediction of control time domain, realizes the multiple-objection optimization energy management in rolling time horizon, it is significant to the deep energy-saving potentiality for excavating PHEV, there is many advantageous effects.
Description
Technical field
The present invention relates to a kind of energy management technical fields of plug-in hybrid vehicle, and in particular, to Yi Zhongtong
Cross the method that the means of intelligent prediction realize plug-in hybrid vehicle energy management.
Background technology
The dynamical system of plug-in hybrid vehicle due to the polyphyly of energy input, operating mode diversity, with
And diversified forms energy stream it is strong coupling the features such as, Comprehensive Control and energy management are always more complicated in this field
Technological difficulties.Its energy management and vehicle road traffic environment, road pedestrian, weather, driver's driving style, vehicle itself shape
A variety of driving cycle factors such as state, road grade are closely related, however the traveling for how using these having the characteristics that multi-source, mixing
Work information realizes the global energy distribution of on-line study optimization plug-in hybrid vehicle, improves hybrid power system
Intelligent level is urgent problem to be solved in this field.
Invention content
For technical problem present in above-mentioned this field, the present invention provides a kind of energy of plug-in hybrid vehicle
Quantity management method specifically includes following steps:
Step 1, On-line testing correspond to the multidimensional driving cycle information of target travel route, based on deep learning algorithm pair
The target travel route establishes the reconstruction model of global driving cycle.So as to realize dynamic weight in advance to target travel route
Structure.
Step 2, based on the reconstruction model of global driving cycle established in the step 1, establish intensified learning network
Model obtains the power battery optimal energy track of the plug-in hybrid vehicle;
Step 3 builds driver style deep layer volume according to the oneself state information and traffic information of the vehicle respectively
The deep layer convolutional neural networks model of product neural network model and traffic information, extracts corresponding driver style feature and traffic
Information characteristics establish the future short-term operating mode real-time prediction model of the vehicle based on deep learning algorithm;
Step 4, the life model according to the power battery, with the power battery optimal energy in the step 2
Track, with reference to the following short-term operating mode real-time prediction model established in the step 3, is built as final value constraint when rolling
Found the control strategy of the power battery.
Further, in the step 1 On-line testing multidimensional driving cycle information, including extracting from Map Services of increasing income
Quotient, traffic monitoring platform, car flow information, signal information, pedestrian information and the Weather information of vehicle-mounted vision system.Pass through standard
Above-mentioned various information MAPs are standard driving cycle information by mapping mode.
Further, described in the step 2 establishes intensified learning network model, obtains the plug-in hybrid
The power battery optimal energy track of vehicle, specifically includes:It is consumed using global energy at least as the intensified learning network mould
The reinforcing reward of type.
Further, the oneself state information of the vehicle in the step 3 includes and steering, gas pedal, brake pedal
Etc. relevant information.Different drivers judge in the heart vehicle follow gallop, track variation behavior and the signal lamp in driving process
Difference is very big in reason, and which results in the differences of driving behavior.Still there are some to be difficult to the friendship measured except driver's driving style
Logical environmental information can have an impact following operating mode, thus the traffic information includes such as environment car speed, signal lamp and converts
And road pedestrian's random walk etc..Database is established respectively to the oneself state information and traffic information of the vehicle, is utilized
Sample in the database builds the deep layer convolutional neural networks model of the driver style deep layer and traffic information respectively.
Each network layer of the neural network is to be limited the depth that forms of Boltzmann machine superposition by multiple Gauss-Bernoulli Jacob
It spends belief network end and adds in neural network, the following temp work of the vehicle is carried out using the feature of depth belief network generation
Condition is predicted in real time.The training process of whole network is mainly made of two parts, and a part is that successively trained one uncle of multiple Gausses exerts
The limited Boltzmann machine of profit, each Gauss-Bernoulli Jacob are limited Boltzmann machine model and utilize the joint probability table based on energy
It reaches.Another part of model training process is the small parameter perturbations under Training, and concrete operations are that end introduces neural network
Layer is returned, deep layer convolutional neural networks structure is formed, the parameter of pre-training is finely adjusted using back-propagation algorithm, was finely tuned
Parameter more new formula in journey is as follows:
Wherein J (W, b;X, y) be model loss function, by parameter W, b and input x and output y are determined, δ is residual error, 1
Represent the number of plies, w(1)It is weighting parameter, b(1)It is offset parameter, a(1)It is activation value, m is sample value quantity, and α is learning rate, w(1)
It is regular terms, λ is regularization coefficient.
Be based ultimately upon deep layer convolutional neural networks model realization prediction operating mode process can be used to lower mapping relations and
Propagated forward formula represents:
F (traffic information, driving style information;W, b)=v
z(l+1)=W(l)a(l)+b(l)
a(l+1)=f (z(l+1))
Wherein v is Vehicle Speed, and 1 represents the number of plies, w(1)It is weighting parameter, b(1)It is offset parameter, a(1)It is activation
Value, z(1+1)Be unit weighted input and.
Further, the life model of the power battery in the step 4 is the cycle longevity of lithium-ion-power cell
Empirical model is ordered, power battery capacitance loss is introduced into realize multiple-objection optimization management in the object function of energy optimization,
The empirical model that power battery capacity changes with charging and discharging currents is:
Wherein QlossIt is that power battery loses capacity, BexpIt is pre-exponential factor, with CrateInversely, R is gas constant,
TbattIt is the average absolute temperature of battery, AhIt is power battery accumulation charge and discharge ampere-hour number.
Further, the step 4 further includes the cost function established about power battery service life, traveling energy expenditure.
According to the energy management method for the plug-in hybrid vehicle that the invention described above is provided, it is utilized with more
Source, the driving cycle information for mixing feature, on-line study optimization PHEV global energies distribute, and improve the intelligence of hybrid power system
Change horizontal;Real-time learning and prediction model are established, improves the operating mode precision of prediction of control time domain, realizes more mesh in rolling time horizon
Mark optimization energy management, it is significant to the deep energy-saving potentiality for excavating PHEV, there is many advantageous effects.
Description of the drawings
Fig. 1 is the schematic diagram for the multidimensional driving cycle information that On-line testing corresponds to target travel route
Fig. 2 is the schematic diagram for the future short-term operating mode real-time prediction model for establishing vehicle
Fig. 3 is the schematic diagram of the structure flow of deep layer convolutional neural networks
Fig. 4 is the overall flow schematic diagram of method provided by the present invention
Specific embodiment
Further explaination in detail is made to technical scheme of the present invention below in conjunction with the accompanying drawings.
The energy management method of a kind of plug-in hybrid vehicle provided by the present invention, as shown in figure 4, specifically including
Following steps:
Step 1, as shown in Figure 1, On-line testing correspond to target travel route multidimensional driving cycle information, based on depth
Learning algorithm establishes the target travel route reconstruction model of global driving cycle.It is pre- so as to be realized to target travel route
First dynamic reconstruct.
Step 2, based on the reconstruction model of global driving cycle established in the step 1, establish intensified learning network
Model obtains the power battery optimal energy track of the plug-in hybrid vehicle;
Step 3 builds driver style deep layer volume according to the oneself state information and traffic information of the vehicle respectively
The deep layer convolutional neural networks model of product neural network model and traffic information, extracts corresponding driver style feature and traffic
Information characteristics establish the future short-term operating mode real-time prediction model of the vehicle based on deep learning algorithm;
Step 4, the life model according to the power battery, with the power battery optimal energy in the step 2
Track, with reference to the following short-term operating mode real-time prediction model established in the step 3, is built as final value constraint when rolling
Found the control strategy of the power battery.
In the preferred embodiment of the application, the multidimensional driving cycle information of On-line testing in the step 1, including
Extract from the Map Services quotient that increases income, traffic monitoring platform, car flow information, signal information, the pedestrian information of vehicle-mounted vision system
And Weather information.
In the preferred embodiment of the application, described in the step 2 establishes intensified learning network model, obtains
The power battery optimal energy track of the plug-in hybrid vehicle, specifically includes:Using global energy consumption it is minimum as
The reinforcing reward of the intensified learning network model.
In the preferred embodiment of the application, as shown in Fig. 2, the oneself state information of the vehicle in the step 3
Including with the relevant information such as steering, gas pedal, brake pedal.Different drivers in driving process vehicle follow gallop,
Track changes behavior and signal lamp judges that psychologically very greatly, which results in the differences of driving behavior for difference.It is travelled in driver
Still there are some traffic environment information for being difficult to measure that can be had an impact to following operating mode except style, thus the traffic information packet
Include such as conversion of environment car speed, signal lamp and road pedestrian's random walk.To the oneself state information of the vehicle and
Traffic information establishes database respectively, and the driver style deep layer and traffic are built respectively using the sample in the database
The deep layer convolutional neural networks model of information.
In the preferred embodiment of the application, as shown in figure 3, each network layer of the neural network is by multiple
The depth belief network end that Gauss-Bernoulli Jacob is limited Boltzmann machine superposition composition adds in neural network, utilizes depth conviction
The future short-term operating mode that the feature of network generation carries out the vehicle is predicted in real time.The training process of whole network is mainly by two
It is grouped as, a part is that successively trained multiple Gauss-Bernoulli Jacob are limited Boltzmann machine, each Gauss-Bernoulli Jacob is limited glass
The graceful machine model of Wurz is expressed using the joint probability based on energy.Another part of model training process is under Training
Small parameter perturbations, concrete operations are that end introduces neural net regression layer, form deep layer convolutional neural networks structure, are passed using reversed
It broadcasts algorithm to be finely adjusted the parameter of pre-training, the more new formula of the parameter in trim process is as follows:
Wherein J (W, b;X, y) be model loss function, by parameter W, b and input x and output y are determined, δ is residual error, 1
Represent the number of plies, w(1)It is weighting parameter, b(1)It is offset parameter, a(1)It is activation value, m is sample value quantity, and a is learning rate, w(1)
It is regular terms, λ is regularization coefficient.
In the preferred embodiment of the application, based on deep layer convolutional neural networks model realization prediction operating mode
Process can be used to lower mapping relations and propagated forward formula represents:
F (traffic information, driving style information;W, b)=v
z(l+1)=W(l)a(l)+b(l)
a(l+1)=f (z(l+1))
Wherein v is Vehicle Speed, and 1 represents the number of plies, w(1)It is weighting parameter, b(1)It is offset parameter, a(1)It is activation
Value, z(1+1)Be unit weighted input and.
In the preferred embodiment of the application, the life model of the power battery in the step 4 for lithium from
The cycle life empirical model of sub- power battery, power battery capacitance loss is introduced into the object function of energy optimization with reality
Existing multiple-objection optimization management, the empirical model that power battery capacity changes with charging and discharging currents are:
Wherein QlossIt is that power battery loses capacity, DexpIt is pre-exponential factor, with CrateInversely, R is gas constant,
TbattIt is the average absolute temperature of battery, AhIt is power battery accumulation charge and discharge ampere-hour number.
In the preferred embodiment of the application, the step 4 further includes foundation about power battery service life, traveling energy
Measure the cost function of consumption.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
Understanding without departing from the principles and spirit of the present invention can carry out these embodiments a variety of variations, modification, replace
And modification, the scope of the present invention is defined by the appended.
Claims (9)
1. a kind of energy management method of the plug-in hybrid vehicle based on intelligent predicting, it is characterised in that:It specifically includes
Following steps:
Step 1, On-line testing correspond to the multidimensional driving cycle information of target travel route, based on deep learning algorithm to described
Target travel route establishes the reconstruction model of global driving cycle.
Step 2, the reconstruction model of global driving cycle established based in the step 1, establish intensified learning network model,
Obtain the power battery optimal energy track of the plug-in hybrid vehicle;
Step 3 builds driver style deep layer convolution god according to the oneself state information and traffic information of the vehicle respectively
Deep layer convolutional neural networks model through network model and traffic information, extracts corresponding driver style feature and traffic information
Feature establishes the future short-term operating mode real-time prediction model of the vehicle based on deep learning algorithm;
Step 4, the life model according to the power battery, with the power battery optimal energy track in the step 2
As final value constraint when rolling, with reference to the following short-term operating mode real-time prediction model established in the step 3, institute is established
State the control strategy of power battery.
2. the method as described in claim 1, it is characterised in that:The multidimensional driving cycle information of On-line testing in the step 1,
Including:Extract from the Map Services quotient that increases income, traffic monitoring platform, the car flow information of vehicle-mounted vision system, signal information, pedestrian
Information and Weather information.
3. the method as described in claim 1, it is characterised in that:Described in the step 2 establishes intensified learning network model,
The power battery optimal energy track of the plug-in hybrid vehicle is obtained, is specifically included:It is minimum with global energy consumption
Reinforcing as the intensified learning network model is rewarded.
4. the method as described in claim 1, it is characterised in that:The oneself state information of vehicle in the step 3 include with
Steering, gas pedal, the relevant information of brake pedal;The traffic information include with environment car speed, signal lamp convert with
And the relevant information of road pedestrian's random walk;Data are established respectively to the oneself state information and traffic information of the vehicle
Library builds the driver style deep layer convolutional neural networks model and traffic information respectively using the sample in the database
Deep layer convolutional neural networks model.
5. method as claimed in claim 4, it is characterised in that:Each network layer of the neural network be by multiple Gausses-
The depth belief network end that Bernoulli Jacob is limited Boltzmann machine superposition composition adds in neural network;Training process is mainly by two
It is grouped as, a part is that successively trained multiple Gauss-Bernoulli Jacob are limited Boltzmann machine;Another part is under Training
Small parameter perturbations.
6. method as claimed in claim 5, it is characterised in that:Gauss-the Bernoulli Jacob is limited in Boltzmann machine, each
One Bernoulli Jacob of Gauss is limited Boltzmann machine model and is expressed using the joint probability based on energy;Parameter in the trim process
More new formula is as follows:
Wherein J (W, b;X, y) be model loss function, by parameter W, b and input x and output y determine that δ is residual error, and I is represented
The number of plies, w(l)It is weighting parameter, b(l)It is offset parameter, a(l)It is activation value, m is sample value quantity, and a is learning rate, w(l)It is just
Then item, λ are regularization coefficients.
7. method as claimed in claim 6, it is characterised in that:Based on the deep layer convolutional neural networks model realization to described
The process that the future short-term operating mode of vehicle is predicted in real time can be used to lower mapping relations and propagated forward formula represents:
F (traffic information, driving style information;W, b)=v
z(l+1)=W(l)a(l)+b(l)
a(l+1)=f (Z(l+1))
Wherein v is Vehicle Speed, and l represents the number of plies, w(l)It is weighting parameter, b(l)It is offset parameter, a(l)It is activation value, z(l +1)Be unit weighted input and.
8. the method as described in claim 1, it is characterised in that:The life model of the power battery in the step 4 is adopted
With the cycle life empirical model of lithium-ion-power cell:
Wherein QlossIt is that power battery loses capacity, BexpIt is pre-exponential factor, with CrateInversely, R is gas constant, Tbatt
It is the average absolute temperature of battery, AhIt is power battery accumulation charge and discharge ampere-hour number.
9. the method as described in claim 1, it is characterised in that:The step 4 further includes foundation about power battery service life, row
Sail the cost function of energy expenditure.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810003711.2A CN108177648B (en) | 2018-01-02 | 2018-01-02 | A kind of energy management method of the plug-in hybrid vehicle based on intelligent predicting |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810003711.2A CN108177648B (en) | 2018-01-02 | 2018-01-02 | A kind of energy management method of the plug-in hybrid vehicle based on intelligent predicting |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108177648A true CN108177648A (en) | 2018-06-19 |
CN108177648B CN108177648B (en) | 2019-09-17 |
Family
ID=62549919
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810003711.2A Active CN108177648B (en) | 2018-01-02 | 2018-01-02 | A kind of energy management method of the plug-in hybrid vehicle based on intelligent predicting |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108177648B (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108674411A (en) * | 2018-07-03 | 2018-10-19 | 肖金保 | A kind of Energy Management System for Hybrid Electric Vehicle |
CN109034391A (en) * | 2018-08-17 | 2018-12-18 | 王玲 | The multi-source heterogeneous information RBM network integration framework and fusion method of automatic Pilot |
CN109143870A (en) * | 2018-10-23 | 2019-01-04 | 宁波溪棠信息科技有限公司 | A kind of control method of multiple target task |
CN110341690A (en) * | 2019-07-22 | 2019-10-18 | 北京理工大学 | A kind of PHEV energy management method based on deterministic policy Gradient learning |
CN110852482A (en) * | 2019-10-15 | 2020-02-28 | 江苏大学 | Real-time global optimization intelligent control system and method for fuel cell bus |
CN111267830A (en) * | 2020-02-10 | 2020-06-12 | 南京航空航天大学 | Hybrid power bus energy management method, device and storage medium |
CN111367172A (en) * | 2020-02-28 | 2020-07-03 | 华南理工大学 | Hybrid system energy management strategy based on reverse deep reinforcement learning |
CN111832881A (en) * | 2020-04-30 | 2020-10-27 | 北京嘀嘀无限科技发展有限公司 | Method, medium and electronic device for predicting electric vehicle energy consumption based on road condition information |
CN112035942A (en) * | 2019-06-03 | 2020-12-04 | 上海汽车集团股份有限公司 | Energy consumption simulation method and device based on driving behaviors |
CN112097783A (en) * | 2020-08-14 | 2020-12-18 | 广东工业大学 | Electric taxi charging navigation path planning method based on deep reinforcement learning |
WO2021036456A1 (en) * | 2019-08-29 | 2021-03-04 | 南京智慧光信息科技研究院有限公司 | Big data- and artificial intelligence-based hybrid propulsion method and robot system |
CN112937547A (en) * | 2021-01-28 | 2021-06-11 | 北京理工大学 | Plug-in hybrid power bus energy management method based on global working conditions |
CN112977402A (en) * | 2019-12-13 | 2021-06-18 | 现代自动车株式会社 | Hybrid vehicle and control method thereof |
CN113246797A (en) * | 2021-06-04 | 2021-08-13 | 广州小鹏汽车科技有限公司 | Method and device for predicting service life of battery |
CN113264031A (en) * | 2021-07-07 | 2021-08-17 | 重庆大学 | Hybrid power system control method based on road surface identification and deep reinforcement learning |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100088490A1 (en) * | 2008-10-02 | 2010-04-08 | Nec Laboratories America, Inc. | Methods and systems for managing computations on a hybrid computing platform including a parallel accelerator |
CN102765388A (en) * | 2012-07-03 | 2012-11-07 | 清华大学 | Vehicle control method based on multi-information integration |
CN103112450A (en) * | 2013-02-27 | 2013-05-22 | 清华大学 | Real-time optimized control method for plug-in parallel hybrid electric vehicle |
CN105416077A (en) * | 2015-12-01 | 2016-03-23 | 北京理工大学 | Energy management system and method for electric automobile |
US20170103307A1 (en) * | 2015-10-08 | 2017-04-13 | Via Alliance Semiconductor Co., Ltd. | Processor with hybrid coprocessor/execution unit neural network unit |
CN107187442A (en) * | 2017-05-18 | 2017-09-22 | 中国第汽车股份有限公司 | The plug-in hybrid electric automobile EMS predicted based on operating mode |
-
2018
- 2018-01-02 CN CN201810003711.2A patent/CN108177648B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100088490A1 (en) * | 2008-10-02 | 2010-04-08 | Nec Laboratories America, Inc. | Methods and systems for managing computations on a hybrid computing platform including a parallel accelerator |
CN102765388A (en) * | 2012-07-03 | 2012-11-07 | 清华大学 | Vehicle control method based on multi-information integration |
CN103112450A (en) * | 2013-02-27 | 2013-05-22 | 清华大学 | Real-time optimized control method for plug-in parallel hybrid electric vehicle |
US20170103307A1 (en) * | 2015-10-08 | 2017-04-13 | Via Alliance Semiconductor Co., Ltd. | Processor with hybrid coprocessor/execution unit neural network unit |
CN105416077A (en) * | 2015-12-01 | 2016-03-23 | 北京理工大学 | Energy management system and method for electric automobile |
CN107187442A (en) * | 2017-05-18 | 2017-09-22 | 中国第汽车股份有限公司 | The plug-in hybrid electric automobile EMS predicted based on operating mode |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108674411A (en) * | 2018-07-03 | 2018-10-19 | 肖金保 | A kind of Energy Management System for Hybrid Electric Vehicle |
CN109034391A (en) * | 2018-08-17 | 2018-12-18 | 王玲 | The multi-source heterogeneous information RBM network integration framework and fusion method of automatic Pilot |
CN109143870A (en) * | 2018-10-23 | 2019-01-04 | 宁波溪棠信息科技有限公司 | A kind of control method of multiple target task |
CN109143870B (en) * | 2018-10-23 | 2021-08-06 | 宁波溪棠信息科技有限公司 | Multi-target task control method |
CN112035942A (en) * | 2019-06-03 | 2020-12-04 | 上海汽车集团股份有限公司 | Energy consumption simulation method and device based on driving behaviors |
CN110341690A (en) * | 2019-07-22 | 2019-10-18 | 北京理工大学 | A kind of PHEV energy management method based on deterministic policy Gradient learning |
CN110341690B (en) * | 2019-07-22 | 2020-08-04 | 北京理工大学 | PHEV energy management method based on deterministic strategy gradient learning |
WO2021036456A1 (en) * | 2019-08-29 | 2021-03-04 | 南京智慧光信息科技研究院有限公司 | Big data- and artificial intelligence-based hybrid propulsion method and robot system |
CN110852482A (en) * | 2019-10-15 | 2020-02-28 | 江苏大学 | Real-time global optimization intelligent control system and method for fuel cell bus |
WO2021073036A1 (en) * | 2019-10-15 | 2021-04-22 | 江苏大学 | Real-time global optimization intelligent control system and method for fuel cell bus |
CN112977402A (en) * | 2019-12-13 | 2021-06-18 | 现代自动车株式会社 | Hybrid vehicle and control method thereof |
CN111267830A (en) * | 2020-02-10 | 2020-06-12 | 南京航空航天大学 | Hybrid power bus energy management method, device and storage medium |
CN111367172A (en) * | 2020-02-28 | 2020-07-03 | 华南理工大学 | Hybrid system energy management strategy based on reverse deep reinforcement learning |
CN111367172B (en) * | 2020-02-28 | 2021-09-21 | 华南理工大学 | Hybrid system energy management strategy based on reverse deep reinforcement learning |
CN111832881A (en) * | 2020-04-30 | 2020-10-27 | 北京嘀嘀无限科技发展有限公司 | Method, medium and electronic device for predicting electric vehicle energy consumption based on road condition information |
CN112097783A (en) * | 2020-08-14 | 2020-12-18 | 广东工业大学 | Electric taxi charging navigation path planning method based on deep reinforcement learning |
CN112097783B (en) * | 2020-08-14 | 2022-05-20 | 广东工业大学 | Electric taxi charging navigation path planning method based on deep reinforcement learning |
CN112937547A (en) * | 2021-01-28 | 2021-06-11 | 北京理工大学 | Plug-in hybrid power bus energy management method based on global working conditions |
CN113246797A (en) * | 2021-06-04 | 2021-08-13 | 广州小鹏汽车科技有限公司 | Method and device for predicting service life of battery |
CN113264031A (en) * | 2021-07-07 | 2021-08-17 | 重庆大学 | Hybrid power system control method based on road surface identification and deep reinforcement learning |
CN113264031B (en) * | 2021-07-07 | 2022-04-29 | 重庆大学 | Hybrid power system control method based on road surface identification and deep reinforcement learning |
Also Published As
Publication number | Publication date |
---|---|
CN108177648B (en) | 2019-09-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108177648B (en) | A kind of energy management method of the plug-in hybrid vehicle based on intelligent predicting | |
CN103914985B (en) | A kind of hybrid power passenger car following speed of a motor vehicle trajectory predictions method | |
CN106004865B (en) | Mileage ADAPTIVE MIXED power vehicle energy management method based on operating mode's switch | |
CN108761509B (en) | Automobile driving track and mileage prediction method based on historical data | |
CN109733248A (en) | Pure electric automobile remaining mileage model prediction method based on routing information | |
CN102052926B (en) | Reduce the method for fuel consumption and cost | |
CN109927709A (en) | A kind of route or travel by vehicle working condition determining method, energy management method and system | |
CN108909702A (en) | A kind of plug-in hybrid-power automobile energy management method and system | |
CN105865472A (en) | Vehicle-mounted navigation method based on least oil consumption | |
CN107330217A (en) | A kind of middle sight oil consumption Forecasting Methodology based on RBFNN | |
CN107346460A (en) | Following operating mode Forecasting Methodology based on the lower front truck operation information of intelligent network contact system | |
WO2023109720A1 (en) | Urban public transportation planning method | |
CN103745111A (en) | Method of predicting driving range of all-electric passenger vehicles | |
Zhou et al. | A quantitative analysis of model predictive control as energy management strategy for hybrid electric vehicles: A review | |
CN108009666A (en) | The preferential optimal path computation method of level based on dynamic road network | |
Bousonville et al. | Estimating truck fuel consumption with machine learning using telematics, topology and weather data | |
CN112734176A (en) | Charging station building method and device, terminal equipment and readable storage medium | |
CN108510130B (en) | Intelligent unmanned vehicle limit mileage intelligent multi-source evaluation method and device | |
CN113393690A (en) | Hybrid traffic balance distribution method considering automatic driving special lane | |
CN113642768A (en) | Vehicle running energy consumption prediction method based on working condition reconstruction | |
Zhang et al. | Energy management strategy of a novel parallel electric-hydraulic hybrid electric vehicle based on deep reinforcement learning and entropy evaluation | |
CN106297296A (en) | A kind of fine granularity distribution method hourage based on sparse tracing point data | |
Grubwinkler et al. | A modular and dynamic approach to predict the energy consumption of electric vehicles | |
Hu et al. | Optimal energy efficient control of pure electric vehicle power system based on dynamic traffic information flow | |
CN116092037B (en) | Vehicle type identification method integrating track space-semantic features |
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 |