CN110533262A - A kind of operating condition rolling recognition methods of various dimensions - Google Patents
A kind of operating condition rolling recognition methods of various dimensions Download PDFInfo
- Publication number
- CN110533262A CN110533262A CN201910857544.2A CN201910857544A CN110533262A CN 110533262 A CN110533262 A CN 110533262A CN 201910857544 A CN201910857544 A CN 201910857544A CN 110533262 A CN110533262 A CN 110533262A
- Authority
- CN
- China
- Prior art keywords
- operating condition
- various dimensions
- time
- dimension
- library
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2228—Indexing structures
- G06F16/2264—Multidimensional index structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- 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
- G06N3/043—Architecture, e.g. interconnection topology based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Abstract
The present invention provides a kind of driving cycles of various dimensions to roll recognition methods, the following steps are included: obtaining the vehicle operation data of magnanimity based on vehicle remote monitoring big data platform, aiming at the problem that driving cycle of different time and different zones has differences, it proposes the concept of time dimension and Spatial Dimension, extracts the characteristic parameter for including time dimension and Spatial Dimension in interior driving cycle；Using orthogonal Hilbert-Huang transform method, various dimensions driving cycle library is established；Constructed operating condition is clustered using the hierarchical clustering method of Euclid's approach degree, establishes various dimensions typical condition library, and updated once every D days to typical condition library；According to the floor data that vehicle remote monitoring big data platform obtains in real time, current working characteristic parameter is extracted, carries out operating mode's switch, so that it is determined that current working classification, it is primary to roll identification every time T.The present invention can effectively identify the real time running operating condition of various dimensions, provide basis for the control of new-energy automobile real-time power.
Description
Technical field
The present invention relates to the operating mode's switch field of new-energy automobile energy control, the operating condition of especially a kind of various dimensions is rolled
Recognition methods.
Background technique
With the successive appearance of new stage fuel economy regulation, to vehicle energy saving, more stringent requirements are proposed with emission-reduction technology.
In this context, new-energy automobile is just by more and more favors.Vehicle energy control be new-energy automobile core technology it
One, reasonable energy management strategies can be allocated the energy between each power source, so that vehicle is meeting dynamic property requirement
Under the premise of save as far as possible energy, reduce pollutant discharge.New-energy automobile Energy Management System is directed to certain mostly at present
One specific operation carries out energy distribution, however in vehicle actual moving process, driving cycle be it is complicated and changeable, when with design
There are great differences for set specific operation, so that automobile energy management in actual travel cannot be optimal.
In order to solve this problem, researchers at home and abroad successively develop a variety of energy management-control methods based on optimization,
And certain effect is obtained, and the representative are offline optimization, the optimization based on prediction, the optimization based on study, offline optimization
It is that global optimization is carried out according to history work information, does not consider the real-time of operating condition, the optimization based on prediction can only realize part
Energy consumption is minimum, and the optimization based on study is learnt according to a large amount of historical datas, to predict following a period of time
The accuracy of operating condition, this prediction is difficult to be protected.
It would therefore be highly desirable to need to provide a kind of precision height and the strong operating mode's switch method of timeliness.
Summary of the invention
In view of the above technical problems, the operating condition that the present invention provides a kind of various dimensions rolls recognition methods, and this method can be effective
The precision and imeliness problem of operating mode's switch are handled, while the period for rolling identification can be optimized, so that operating condition
Identification can adapt to the variation of environment, while meet the requirement of timeliness.
The technical solution adopted by the present invention are as follows:
A kind of operating condition rolling recognition methods of various dimensions, which comprises the following steps:
Step 1: on the basis of obtaining magnanimity vehicle operation data, propose the concept of time dimension and Spatial Dimension, it is right
Acquired floor data carries out data mining, establishes the operating mode feature parameter of various dimensions；
Step 2: according to the various dimensions operating mode feature parameter established, using general operating condition construction method to different dimensions
Operating condition constructed, to form the operating condition library of various dimensions；
Step 3: on the basis of establishing various dimensions operating condition library, constructed operating condition library being gathered using general clustering procedure
Class, to form the typical condition library of various dimensions；
Step 4: the typical condition library of various dimensions is updated；
Step 5: obtaining current working data in real time, current working characteristic parameter is extracted, using general operating mode's switch side
Method identifies that it is primary to roll identification every time T to current working type.
A kind of operating condition of various dimensions rolls recognition methods, which is characterized in that the various dimensions of foundation described in step 1
Operating mode feature parameter includes:
(1) road is divided into several segments P according to regional locationi, the position coordinates section for defining segment is space
The characteristic parameter of dimension；
(2) it is directed to the same road segment, was divided into seven period t for one dayi, i.e., morning peak (6:30~8:30), on
Noon (8:30~11:30), noon peak (11:30~14:30), afternoon (14:30~17:00), evening peak (17:00~19:00),
(19:00~23:00), midnight (23:00~6:30) at night, definition above seven periods are time dimension characteristic parameter；
(3) remaining characteristic parameter is the average speed v under time dimension or Spatial Dimensionm, average running speed vmr, most
High speed vmax, peak accelerationMinimum deceleration degreeDead time ratio pvi, at the uniform velocity time scale pvc, accelerate
Time scale pa, deceleration time ratio pd, accelerating sections average accelerationDeceleration average retardation rateOn this basis,
The building of various dimensions operating condition is carried out according to above 13 characteristic parameters.
A kind of operating condition of various dimensions rolls recognition methods, which is characterized in that general operating condition structure described in step 2
Construction method is orthogonal Hilbert-Huang transform method, combination clustering procedure or Markov method.
The operating conditions of various dimensions a kind of rolls recognition methods, which is characterized in that general clustering procedure described in step 3 is
The hierarchical clustering method or K-means clustering procedure of Euclid's approach degree.
A kind of operating condition of various dimensions rolls recognition methods, which is characterized in that various dimensions typical condition library in step 3
Specific construction method are as follows:
(1) using the operating mode feature parameter under the same space dimension different time dimension and different sky under same time dimension
Between dimension operating mode feature parameter, utilize the operating condition under extracted operating mode feature parameter settling time dimension and Spatial Dimension
Library；
(2) the operating condition block of different spaces dimension under same time dimension is divided by 4 classes using general clustering procedure, it can also basis
The complexity of operating condition increases or decreases classification quantity, to establish the typical condition library of various dimensions.
A kind of operating condition of various dimensions rolls recognition methods, which is characterized in that the allusion quotation of various dimensions described in step 4
Type operating condition library is updated, and for the imeliness problem in operating condition library, primary, parameter D and road were updated to the operating condition library every D days
Operating condition actual change frequency is inversely proportional, and the update cycle can be adjusted according to road actual change situation.
A kind of operating condition of various dimensions rolls recognition methods, which is characterized in that general operating condition described in step 5 is known
Other method is Adaptive Fuzzy Neural-network recognition methods.
A kind of operating condition of various dimensions rolls recognition methods, which is characterized in that current working class described in step 5
The specific steps that type is identified are as follows:
(1) according to the real-time acquisition time dimensional characteristics parameter of remote monitoring system platform, then the feature of Spatial Dimension is determined
Parameter, or first obtain the characteristic parameter of Spatial Dimension, then the characteristic parameter of acquisition time dimension；
(2) 11 characteristic parameters of residue in the Δ t time are then acquired, operating condition type is carried out according to current signature parameter
Identification, the period definition for rolling identification is T.
A kind of operating condition of various dimensions rolls recognition methods, which is characterized in that the size of the Δ t and T is to operating condition
The precision of identification has a major impact, and the initial value of parameter, Δ t and T can carry out analysis determination according to experimental data, in application process
In, Δ t and T can be inversely proportional according to its value of the change frequency appropriate adjustment of operating condition, Δ t and T with operating condition change frequency, even work
Condition variation frequently, can reduce value；If operating condition is relatively stable, value can suitably increase.
The beneficial effects of the present invention are:
Various dimensions operating condition of the invention rolls recognition methods, right first on the basis of obtaining magnanimity vehicle operation data
Time dimension and Spatial Dimension are divided, the operating mode feature parameter under extraction time dimension and Spatial Dimension；Then, using just
The method for handing over Hilbert-Huang transform handles acquired characteristic parameter, establishes various dimensions operating condition；Then, using Europe
The hierarchical clustering method that approach degree is obtained in several clusters constructed operating condition library, so that the typical condition library of various dimensions is formed,
The operating condition library established updated primary every D days；Finally, obtain current working characteristic parameter in real time according to remote monitoring system,
Operating condition is identified using Adaptive Fuzzy Neural-network, recognition cycle T.The week that typical condition library in this method updates
It phase D and rolls recognition cycle T and can be adjusted according to actual condition change frequency under time dimension and Spatial Dimension, D and T's takes
Value is inversely proportional with operating condition change frequency, i.e. the higher D and T value of change frequency is smaller, and the value of change frequency lower D and T is bigger.Cause
This, the method for the present invention can effectively deal with the precision problem of operating condition and the real time problems of identification, have preferable accuracy of identification and
Real-time provides basis for the control of new-energy automobile real-time power.
Detailed description of the invention
Fig. 1 is that various dimensions operating condition provided in an embodiment of the present invention rolls recognition methods flow chart；
Fig. 2 is Adaptive Fuzzy Neural-network operating mode's switch flow chart provided in an embodiment of the present invention；
Fig. 3 is that operating mode's switch provided in an embodiment of the present invention emulates schematic diagram.
Specific embodiment
To keep the technical problem to be solved in the present invention, technical solution and advantage clearer, below in conjunction with attached drawing and tool
Body embodiment is described in detail.
Fig. 1 is the flow diagram that various dimensions operating condition provided in an embodiment of the present invention rolls recognition methods.As shown in Figure 1,
Various dimensions operating condition provided in an embodiment of the present invention roll recognition methods the following steps are included:
S101, on the basis of obtaining magnanimity vehicle operation data, propose time dimension and Spatial Dimension concept, extract
Various dimensions operating mode feature parameter；
S102, by extracted various dimensions operating mode feature parameter, at the method using orthogonal Hilbert-Huang transform
Reason, establishes various dimensions operating condition；
S103, building various dimensions operating condition is clustered using the hierarchical clustering method of Euclid's approach degree, establishes multidimensional
Spend typical condition library；
S104, the typical condition library of various dimensions is regularly updated, was updated every D days primary；
S105, floor data is obtained according to remote monitoring system in real time, extracts the characteristic parameter of current working, use is adaptive
Fuzzy neural network is answered to carry out rolling identification to current working type, it is primary to roll identification every time T.
In the present invention, the various dimensions operating mode feature parameter extracted in step S101 is that step S102 establishes various dimensions operating condition
Basis；Step S103 is that the various dimensions operating condition established to step S102 carries out clustering, establishes various dimensions typical condition
Library is prepared for operating mode's switch；Step S104 is the floor data obtained in real time using remote monitoring system, extracts current working
Characteristic parameter is the basis that operating condition rolls identification in step S105；Step S105 is to roll to extract current working in step S104
Operating condition is carried out on the basis of characteristic parameter rolls identification.
The various dimensions operating mode feature parameter of foundation described in step 1 includes:
(1) road is divided into several segments P according to regional locationi, the position coordinates section for defining segment is space
The characteristic parameter of dimension；
(2) it is directed to the same road segment, was divided into seven period t for one dayi, i.e., morning peak (6:30~8:30), on
Noon (8:30~11:30), noon peak (11:30~14:30), afternoon (14:30~17:00), evening peak (17:00~19:00),
(19:00~23:00), midnight (23:00~6:30) at night, definition above seven periods are time dimension characteristic parameter；
(3) remaining characteristic parameter is the average speed v under time dimension or Spatial Dimensionm, average running speed vmr, most
High speed vmax, peak accelerationMinimum deceleration degreeDead time ratio pvi, at the uniform velocity time scale pvc, accelerate
Time scale pa, deceleration time ratio pd, accelerating sections average accelerationDeceleration average retardation rateOn this basis,
The building of various dimensions operating condition is carried out according to above 13 characteristic parameters.
Step 2, in 3 various dimensions typical condition library specific construction method are as follows:
(1) using the operating mode feature parameter under the same space dimension different time dimension and different sky under same time dimension
Between dimension operating mode feature parameter, utilize the operating condition under extracted operating mode feature parameter settling time dimension and Spatial Dimension
Library；
(2) the operating condition block of different spaces dimension under same time dimension is divided by 4 classes using general clustering procedure, it can also basis
The complexity of operating condition increases or decreases classification quantity, to establish the typical condition library of various dimensions.
The typical condition library of various dimensions is updated described in step 4, for the imeliness problem in operating condition library, every D
It updates once the operating condition library, and parameter D is inversely proportional with road condition actual change frequency, and the update cycle can be according to road reality
Situation of change is adjusted.
The specific steps that current working type is identified described in step 5 are as follows:
(1) according to the real-time acquisition time dimensional characteristics parameter of remote monitoring system platform, then the feature of Spatial Dimension is determined
Parameter, or first obtain the characteristic parameter of Spatial Dimension, then the characteristic parameter of acquisition time dimension；
(2) 11 characteristic parameters of residue in the Δ t time are then acquired, operating condition type is carried out according to current signature parameter
Identification, the period definition for rolling identification is T, and the size of the Δ t and T has a major impact the precision of operating mode's switch, parameter, Δ t
Analysis determination can be carried out according to experimental data with the initial value of T, can rule of thumb choose Δ t=5min, T=30min, apply
In the process, Δ t and T can be inversely proportional according to its value of the change frequency appropriate adjustment of operating condition, Δ t and T with operating condition change frequency, i.e.,
If operating condition variation is frequently, value can be reduced；If operating condition is relatively stable, value can suitably increase.
The process of Adaptive Fuzzy Neural-network operating mode's switch shown in Fig. 2 is operating mode's switch method employed in the present invention.
As shown in Fig. 2, this method is using the various dimensions operating mode feature parameter obtained in real time as the input of Adaptive Fuzzy Neural-network, mind
Through the current operating condition type of Network Recognition.
Fig. 3 show operating mode's switch simulation result of the invention.As shown in figure 3, firstly, according to current working characteristic parameter
Then the identification for carrying out operating condition type determines current working data according to the floor data in various dimensions typical condition library.
Embodiment described above, only a specific embodiment of the invention, to illustrate technical solution of the present invention, rather than
It is limited, scope of protection of the present invention is not limited thereto, although having carried out with reference to the foregoing embodiments to the present invention detailed
Illustrate, those skilled in the art should understand that: anyone skilled in the art the invention discloses
In technical scope, it can still modify to technical solution documented by previous embodiment or variation can be readily occurred in, or
Person's equivalent replacement of some of the technical features；And these modifications, variation or replacement, do not make corresponding technical solution
Essence is detached from the spirit and scope of technical solution of the embodiment of the present invention, should be covered by the protection scope of the present invention.Therefore,
The protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (9)
1. a kind of operating condition of various dimensions rolls recognition methods, which comprises the following steps:
Step 1: on the basis of obtaining magnanimity vehicle operation data, the concept of time dimension and Spatial Dimension is proposed, to being obtained
The floor data taken carries out data mining, establishes the operating mode feature parameter of various dimensions；
Step 2: according to the various dimensions operating mode feature parameter established, using general operating condition construction method to the work of different dimensions
Condition is constructed, to form the operating condition library of various dimensions；
Step 3: on the basis of establishing various dimensions operating condition library, constructed operating condition library is clustered using general clustering procedure,
To form the typical condition library of various dimensions；
Step 4: the typical condition library of various dimensions was updated once every D days；
Step 5: obtaining current working data in real time, current working characteristic parameter is extracted, using general operating mode's switch method pair
Current working type is identified that it is primary to roll identification every time T.
2. a kind of operating condition of various dimensions according to claim 1 rolls recognition methods, which is characterized in that described in step 1
The various dimensions operating mode feature parameter of foundation includes:
(1) road is divided into several segments P according to regional locationi, the position coordinates section for defining segment is Spatial Dimension
Characteristic parameter；
(2) it is directed to the same road segment, was divided into seven period t for one dayi, i.e., morning peak (6:30~8:30), the morning (8:
30~11:30), noon peak (11:30~14:30), afternoon (14:30~17:00), evening peak (17:00~19:00), at night
At (19:00~23:00), midnight (23:00~6:30), definition above seven periods are time dimension characteristic parameter；
(3) remaining characteristic parameter is the average speed v under time dimension or Spatial Dimensionm, average running speed vmr, most high speed
Spend vmax, peak accelerationMinimum deceleration degreeDead time ratio pvi, at the uniform velocity time scale pvc, the acceleration time
Ratio pa, deceleration time ratio pd, accelerating sections average accelerationDeceleration average retardation rateOn this basis, according to
Above 13 characteristic parameters carry out the building of various dimensions operating condition.
3. a kind of operating condition of various dimensions according to claim 1 rolls recognition methods, which is characterized in that described in step 2
General operating condition construction method is orthogonal Hilbert-Huang transform method, combination clustering procedure or Markov method.
4. a kind of operating condition of various dimensions according to claim 1 rolls recognition methods, which is characterized in that described in step 3
General clustering procedure is the hierarchical clustering method or K-means clustering procedure of Euclid's approach degree.
5. a kind of operating condition of various dimensions according to claim 4 rolls recognition methods, which is characterized in that multidimensional in step 3
Spend the specific construction method in typical condition library are as follows:
(1) different spaces under operating mode feature parameter and same time dimension under the same space dimension different time dimension is used to tie up
The operating mode feature parameter of degree utilizes the operating condition library under extracted operating mode feature parameter settling time dimension and Spatial Dimension；
(2) the operating condition block of different spaces dimension under same time dimension is divided by 4 classes using general clustering procedure, it can also be according to operating condition
Complexity increase or decrease classification quantity, to establish the typical condition library of various dimensions.
6. a kind of operating condition of various dimensions according to claim 1 rolls recognition methods, which is characterized in that described in step 4
The typical condition library of various dimensions is updated, for the imeliness problem in operating condition library, one is updated to the operating condition library every D days
Secondary, parameter D is inversely proportional with road condition actual change frequency.
7. a kind of operating condition of various dimensions according to claim 2 rolls recognition methods, which is characterized in that described in step 5
General operating mode's switch method is Adaptive Fuzzy Neural-network recognition methods.
8. a kind of operating condition of various dimensions according to claim 7 rolls recognition methods, which is characterized in that described in step 5
The specific steps that current working type is identified are as follows:
(1) according to the real-time acquisition time dimensional characteristics parameter of remote monitoring system platform, then the characteristic parameter of Spatial Dimension is determined,
Or first obtain the characteristic parameter of Spatial Dimension, then the characteristic parameter of acquisition time dimension；
(2) 11 characteristic parameters of residue in the Δ t time are then acquired, operating condition type is known according to current signature parameter
Not, the period definition for rolling identification is T.
9. a kind of operating condition of various dimensions according to claim 8 rolls recognition methods, which is characterized in that the Δ t's and T
Size has a major impact the precision of operating mode's switch, and the initial value of parameter, Δ t and T can carry out analysis determination according to experimental data,
In application process, Δ t and T can according to its value of the change frequency appropriate adjustment of operating condition, Δ t and T and operating condition change frequency at
The variation of inverse ratio, even operating condition frequently, can reduce value；If operating condition is relatively stable, value can suitably increase.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910857544.2A CN110533262A (en) | 2019-09-09 | 2019-09-09 | A kind of operating condition rolling recognition methods of various dimensions |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910857544.2A CN110533262A (en) | 2019-09-09 | 2019-09-09 | A kind of operating condition rolling recognition methods of various dimensions |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110533262A true CN110533262A (en) | 2019-12-03 |
Family
ID=68668310
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910857544.2A Pending CN110533262A (en) | 2019-09-09 | 2019-09-09 | A kind of operating condition rolling recognition methods of various dimensions |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110533262A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114248781A (en) * | 2020-09-21 | 2022-03-29 | 比亚迪股份有限公司 | Vehicle working condition prediction method and device and vehicle |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8442821B1 (en) * | 2012-07-27 | 2013-05-14 | Google Inc. | Multi-frame prediction for hybrid neural network/hidden Markov models |
| CN107516107A (en) * | 2017-08-01 | 2017-12-26 | 北京理工大学 | A kind of driving cycle classification Forecasting Methodology of motor vehicle driven by mixed power |
| CN107662503A (en) * | 2017-09-13 | 2018-02-06 | 浙江工业大学之江学院 | Discrimination method is intended to based on acceleration and the electric vehicle brake of brake pedal status |
| CN108596208A (en) * | 2018-03-21 | 2018-09-28 | 上海交通大学 | A kind of vehicle drive for full working scope road recycles construction method |
-
2019
- 2019-09-09 CN CN201910857544.2A patent/CN110533262A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8442821B1 (en) * | 2012-07-27 | 2013-05-14 | Google Inc. | Multi-frame prediction for hybrid neural network/hidden Markov models |
| CN107516107A (en) * | 2017-08-01 | 2017-12-26 | 北京理工大学 | A kind of driving cycle classification Forecasting Methodology of motor vehicle driven by mixed power |
| CN107662503A (en) * | 2017-09-13 | 2018-02-06 | 浙江工业大学之江学院 | Discrimination method is intended to based on acceleration and the electric vehicle brake of brake pedal status |
| CN108596208A (en) * | 2018-03-21 | 2018-09-28 | 上海交通大学 | A kind of vehicle drive for full working scope road recycles construction method |
Non-Patent Citations (8)
| Title |
|---|
| 姜涛: ""基于工况识别的插电式混合动力汽车控制策略研究"", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》 * |
| 李怀俊: "《基于核主元模糊聚类的旋转机械故障诊断技术研究》", 31 July 2016, 西南交通大学出版社 * |
| 石琴等: ""基于粒子群优化支持向量机算法的行驶工况识别及应用"", 《中国机械工程》 * |
| 罗少华: ""基于工况识别的混联式混合动力汽车能量管理策略研究"", 《《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》》 * |
| 邓涛等: ""混合动力汽车工况识别自适应能量管理策略"", 《西安交通大学学报》 * |
| 陈玉成: ""基于工况识别的混合动力汽车控制策略研究"", 《中国优秀博硕士学位论文全文数据库（硕士）工程科技Ⅱ辑》 * |
| 陈达奇: ""考虑实时交通信息的插电式混合动力汽车预测能量管理策略研究"", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》 * |
| 高建平: ""基于实际工况的插电式混合动力公交车参数自适应控制策略研究"", 《西安交通大学学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114248781A (en) * | 2020-09-21 | 2022-03-29 | 比亚迪股份有限公司 | Vehicle working condition prediction method and device and vehicle |
| CN114248781B (en) * | 2020-09-21 | 2024-04-16 | 比亚迪股份有限公司 | Vehicle working condition prediction method and device and vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109927709A (en) | A kind of route or travel by vehicle working condition determining method, energy management method and system | |
| CN105243430B (en) | The optimization method of the target velocity curve of energy-saving train operation | |
| Zheng et al. | An energy management approach of hybrid vehicles using traffic preview information for energy saving | |
| CN110264750A (en) | A kind of multi-intersection signal lamp cooperative control method of the Q value migration based on multitask depth Q network | |
| CN104766485A (en) | Traffic light optimization time distribution method based on improved fuzzy control | |
| CN103077615A (en) | Online learning method for optimizing signalized intersection queuing length | |
| Lin et al. | Traffic signal optimization based on fuzzy control and differential evolution algorithm | |
| CN109760523A (en) | Composite power source energy management method based on BP neural network speed prediction | |
| CN109376972A (en) | A kind of wisdom Power Network Short-Term Electric Load Forecasting method based on block cluster | |
| CN103680156A (en) | Multi-agent traffic signal control system | |
| CN109149648A (en) | A kind of adaptive width Dynamic Programming intelligent power generation control method | |
| CN101556458B (en) | Automatic control algorithm for feeding vitriol in tap water by coagulation | |
| CN110533262A (en) | A kind of operating condition rolling recognition methods of various dimensions | |
| CN113053120A (en) | Traffic signal lamp scheduling method and system based on iterative learning model predictive control | |
| CN116187161A (en) | Intelligent energy management method and system for hybrid electric bus in intelligent networking environment | |
| CN115534929A (en) | Plug-in hybrid electric vehicle energy management method based on multi-information fusion | |
| Haroon et al. | Switching control paradigms for adaptive cruise control system with stop-and-go scenario | |
| CN113479187A (en) | Layered different-step-length energy management method for plug-in hybrid electric vehicle | |
| CN117458477A (en) | Electric vehicle scheduling method considering participation of load aggregators in grouping optimization mode | |
| CN105083322A (en) | Subway train collision early warning method | |
| CN110021168B (en) | Grading decision method for realizing real-time intelligent traffic management under Internet of vehicles | |
| CN117134380A (en) | Hierarchical optimization operation method and system based on Yun Bian collaborative distributed energy storage | |
| Yang et al. | Regional boundary control of traffic network based on MFD and FR-PID | |
| Guo et al. | Based on MOPSO Algorithm of Real-Time Traffic Signal Optimization Control for Intelligent Transportation Intersections | |
| CN113276829A (en) | Vehicle running energy-saving optimization weight-changing method based on working condition prediction |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191203 |