CN113053135A - Global vehicle speed prediction method and device - Google Patents
Global vehicle speed prediction method and device Download PDFInfo
- Publication number
- CN113053135A CN113053135A CN201911368643.0A CN201911368643A CN113053135A CN 113053135 A CN113053135 A CN 113053135A CN 201911368643 A CN201911368643 A CN 201911368643A CN 113053135 A CN113053135 A CN 113053135A
- Authority
- CN
- China
- Prior art keywords
- global
- speed
- vehicle speed
- parking
- segments
- 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
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
Abstract
The invention relates to a global vehicle speed prediction method and a global vehicle speed prediction device. The method comprises the following steps: acquiring historical working condition data and current traffic information; carrying out global feature statistics on historical working condition data at different fixed routes, different running dates and different running times, wherein the global features comprise global distance, global running time and global speed features; cutting the global features into driving segments and parking segments; establishing a mixed Gaussian model according to all the driving segments and the parking segments; and taking the current traffic information as input, searching corresponding driving segments and parking segments, classifying and orderly splicing the corresponding driving segments and parking segments, and outputting the global working condition to realize the prediction of the global vehicle speed. The invention excavates the driving rule of the vehicle, can accurately construct the global working condition by taking the current traffic information as input when constructing the global working condition, has simple construction process and can improve the efficiency of constructing the global working condition.
Description
Technical Field
The invention relates to a global vehicle speed prediction method and device, and belongs to the technical field of new energy vehicle working conditions.
Background
Good traffic conditions can provide effective guarantee for traffic safety, and accurate vehicle speed prediction provides important support for improving traffic conditions. The traditional traffic condition prediction method cannot reliably predict the speed condition of the urban traffic network.
Based on this, it is proposed to predict the vehicle speed using a vehicle behavior model. The vehicle running condition is used for describing the running characteristics of the vehicle under different traffic environments and is represented as a curve of speed changing along with a road. And the driving condition has important influence on the aspects of improving the economy, smoothness and dynamic property of the vehicle, optimizing a control strategy and the like.
For urban buses, the urban bus operation has the characteristic of fixed routes, so that the urban buses are obviously different from vehicles with other purposes in actual working conditions. In the prior art, the working condition construction method mainly comprises a short-stroke method, a cluster analysis method, a Markov method and the like, and most of the current researches on the construction of the working conditions of domestic and foreign urban buses are concentrated on the construction of the working conditions of a single line or the combined construction of a plurality of lines, and the construction of the working conditions of the single line is only suitable for the test research of a specific line and has no transportability; the combination construction area of the multiple lines has poor representativeness and cannot truly represent the actual running state of the urban buses.
For this reason, dynamic reconstruction methods of global conditions have been proposed, for example: the application publication number is CN 107845261A, which discloses a tenser-fusion-based automobile global working condition dynamic reconstruction method, and the method comprises the steps of obtaining the current time traffic information of each road section of a planned route through the existing traffic information database; storing the traffic information at the cloud end by using a tensor model, judging whether the tensor model of the traffic information at the current moment is complete or not, and if the traffic information is incomplete, constructing a tensor complete traffic information database by using a tensor filling algorithm; and dividing the global road section into n road sections to respectively construct the working conditions of each road section, and sequentially arranging the working conditions of the 1 st to n road sections to form the global working condition. However, the method adopts real-time traffic information to construct the global working condition, so that the calculation is complex, the efficiency is low, the accuracy is low, and the prediction accuracy of the global speed is low.
Disclosure of Invention
The invention aims to provide a global vehicle speed prediction method and a global vehicle speed prediction device, which are used for solving the problems of low prediction efficiency and low accuracy in the prior art.
In order to achieve the above object, the present invention provides a global vehicle speed prediction method, including the following steps:
acquiring historical working condition data and current traffic information; the current traffic information comprises a fixed route for the current vehicle to travel, the current operation date and the current operation time;
carrying out global feature statistics on historical working condition data at different fixed routes, different running dates and different running times, wherein the global features comprise global distance, global running time and global speed features;
cutting the global features into driving segments and parking segments, wherein each driving segment comprises a local distance, a local running time and a local speed feature; each parking section comprises parking duration and parking times;
establishing a mixed Gaussian model according to all the driving segments and the parking segments;
and taking the current traffic information as input, searching corresponding driving segments and parking segments, classifying and orderly splicing the corresponding driving segments and parking segments, and outputting the global working condition to realize the prediction of the global vehicle speed.
In addition, the invention also provides a global vehicle speed prediction device, which comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor realizes the global vehicle speed prediction method when executing the computer program.
The beneficial effects are that: according to the invention, global characteristics and local characteristics of historical working condition data of different fixed routes, different running dates and different running times are counted, so that the driving rule of the vehicle is excavated, and a Gaussian mixture model is established. When the global working condition is constructed, the global working condition can be accurately constructed by taking the current traffic information as input, and the global working condition is a curve of the distance and the speed, so that the global speed is obtained.
Further, in the global vehicle speed prediction method and device, in order to ensure the accuracy of the construction of the working conditions, the method further comprises the step of performing data cleaning on historical working condition data: and processing and marking the data of the empty rows, the disorder and the abnormity.
Further, in the global vehicle speed prediction method and device, in order to improve the accuracy of the construction of the working conditions, the global characteristics further include a global acceleration characteristic and a global duration ratio characteristic.
Furthermore, in the global vehicle speed prediction method and device, in order to improve the accuracy of the construction of the working conditions, each driving segment further comprises a local acceleration characteristic.
Further, in the global vehicle speed prediction method and device, the global speed characteristics include a global average speed, a global maximum speed, and a global speed standard deviation.
Further, in the global vehicle speed prediction method and apparatus, the global acceleration characteristics include a global average acceleration, a global maximum deceleration, and a global acceleration standard deviation; the global duration ratio features include a global low-speed duration ratio, a global high-speed duration ratio, a global acceleration duration ratio and a global deceleration duration ratio.
Further, in the global vehicle speed prediction method and apparatus, the local speed characteristics include a local average speed, a local maximum speed, and a local speed standard deviation.
Further, in the global vehicle speed prediction method and apparatus, the local acceleration characteristic includes a local average acceleration, a local average deceleration, and a local acceleration standard deviation.
Further, in the global vehicle speed prediction method and device, in order to accurately divide the driving section and the parking section, the cutting basis of the driving section and the parking section is the zero-point speed.
Drawings
FIG. 1 is a flow chart of construction of global conditions of the present invention;
FIG. 2 is a diagram illustrating the effect of global condition construction.
Detailed Description
The embodiment of the global vehicle speed prediction method comprises the following steps:
the global vehicle speed prediction method proposed in the present embodiment, as shown in fig. 1, includes the following steps:
1) and acquiring historical working condition data.
The historical working condition data comprises historical working condition data of all fixed routes of urban buses in a city, and the acquisition process of the historical working condition data of the urban buses of a fixed route is taken as an example:
the historical working condition data is acquired online by iCard1S equipment, and the acquired information comprises the running date, running time, motor speed, vehicle speed and other relevant running information of the vehicle. In this embodiment, in order to obtain the vehicle speed information more accurately, the motor rotation speed is selected as the correlation quantity to obtain the vehicle speed. As another embodiment, the collected vehicle speed information may be directly used.
2) And carrying out global feature statistics on the historical working condition data at different fixed routes, different running dates and different running times, wherein the global features comprise global distance, global running time and global speed features.
In this embodiment, for accuracy of global velocity prediction, the global features further include a global acceleration feature and a global duration ratio feature. Of course, the global acceleration feature and the global duration ratio feature may not be counted.
The global speed characteristics comprise global average speed, global maximum speed and global speed standard; the global acceleration characteristics comprise global average acceleration, global maximum deceleration and global acceleration standard deviation; the global duration ratio features include a global low-speed duration ratio, a global high-speed duration ratio, a global acceleration duration ratio and a global deceleration duration ratio.
The specific process is as follows:
first, the positions of the start and stop points of the different fixed routes in all data are determined.
Due to the complexity of data, the automatic extraction of the start points and the stop points of all fixed routes is very difficult to realize, so that the extraction of the global working condition start points and the stop points of different fixed routes is carried out in a manual fixed point mode. The driving route of the bus is fixed, the total travel is basically unchanged although the global working condition changes along with time, and the total travel is maintained near a certain value.
In this embodiment, in order to solve the problem of data interruption in the historical operating condition data, the method further includes the step of performing data cleaning on the historical operating condition data:
a. and processing and marking the blank line. In the historical working condition data, empty rows exist among data rows, and time intervals exist among data before and after the empty rows under the condition, namely the empty rows indicate that the data are lost;
b. and (4) processing and marking wrong lines. Data disorder of a plurality of adjacent rows exists in historical working condition data, which causes trouble in data reading, and in this case, time intervals exist among the disorder rows, and data are lost;
c. and processing and marking an abnormal vehicle speed signal. The irregularity of the abnormal vehicle speed signals is represented by the fact that the abnormal vehicle speed signals exist at the beginning and the end of the global working condition and are not fixed in quantity, and meanwhile, the abnormal vehicle speed signals even appear in the middle of the global working condition.
The specific processes of treatment and marking are as follows: when empty rows and wrong rows occur, information loss occurs in the corresponding whole historical global working condition, and invalid data is considered to be removed; when the abnormal vehicle speed signal occurs, the abnormal vehicle speed signal must be excluded, namely the abnormal vehicle speed signal cannot be included in a single working condition.
Meanwhile, after the start points and the stop points of all the cycle working conditions are found preliminarily, the abnormal cycle working conditions which do not conform to the global distance need to be removed.
Secondly, after all the fixed routes are counted, the global features of each fixed route need to be counted.
The global working condition has a clear physical meaning and relatively stable data statistical characteristics, so that the data characteristics are necessarily mined by taking the global working condition as an analysis unit to reveal rules of the working condition data. The global features of each fixed route are divided into an overall level and a spatial level.
The whole layer is as follows: the data statistical characteristics of the global working condition comprise a global distance, a global running time length, a global average speed, a global maximum speed, a global speed standard deviation, a global average acceleration, a global maximum deceleration, a global acceleration standard deviation, a global low-speed time length ratio, a global high-speed time length ratio, a global acceleration time length ratio, a global deceleration time length ratio and the like.
And obtaining a corresponding total journey median, a total duration median and a speed median based on the global journey characteristic, the global duration characteristic and the global speed characteristic, and obtaining a journey-time relation for representing the journey characteristic of the fixed route.
The spatial layer is as follows:
a. global data characteristics at different run dates. Because the road traffic states of working days and double holidays may have certain differences which are closely related to the travel behaviors of people, in order to research the difference of the global working conditions corresponding to the working days and the double holidays, seven classes are divided from Monday to Sunday, the global working conditions are corresponding to corresponding classes, the statistical characteristics of working condition data of different types of running dates are compared, and the correlation between the global working conditions and the running dates is searched;
b. data characteristics of different operating periods (i.e., operating moments). The buses have different running conditions in the same day and different time periods, 16 classes are divided from 5 points in the morning to 8 points in the evening for researching the difference of the global working conditions of different time periods in one day mainly due to the change of the passenger flow and the road traffic flow in the morning, the middle and the evening, the global working conditions are corresponding to the corresponding classes, the statistical characteristics of the working condition data of different running time classes are compared, and the correlation between the global working conditions and the running time periods is searched.
3) The method comprises the steps of analyzing the characteristics of local working condition data, and cutting global characteristics into different speed segments (namely local working conditions), wherein the speed segments comprise driving segments and parking segments, and each driving segment comprises a local distance, a local running time and a local speed characteristic; each parking segment includes a parking time length and a number of parking times.
On the basis that the global characteristic comprises the global acceleration characteristic, each driving segment further comprises the local acceleration characteristic, and of course, the local acceleration characteristic can not be counted under the condition that the global acceleration is not counted.
The local speed characteristics comprise local average speed, local maximum speed and local speed standard deviation; the local acceleration characteristics comprise local average acceleration, local average deceleration and local acceleration standard deviation.
The specific process is as follows:
the global working condition (i.e. global characteristic) has a long distance and long time consumption, and is difficult to reflect the space-time characteristics of a tiny driving interval, so that the analysis of the working condition needs to be detailed to a local level. The local level here faces the segment level, and the global condition is the segment-by-segment accumulation of these segments. The method analyzes the working condition segments, searches the data characteristics of a certain position interval and a certain time period, can excavate richer information from the data, and further excavates the running characteristics of the vehicle.
In this embodiment, the cutting basis of the driving segment and the parking segment is the zero-point speed. A section between a zero-speed critical point of the converted parking into the traveling and the next zero-speed point is called a driving section and represents a basic operation interval of the vehicle; a section between a zero-speed critical point of the transition from the traveling to the parking and the last zero-speed point of the parking is called a parking section and represents a basic parking interval of the vehicle; the segment from the zero-speed critical point of the parking to the traveling to the next zero-speed critical point of the parking to the traveling is called a speed segment, namely the speed segment is composed of a driving segment and a parking segment and represents the basic condition unit of the vehicle, namely the minimum micro-condition, and the global condition is the ordered combination of the minimum micro-conditions.
The object of the minimum micro-condition (speed segment) segmentation is the global condition, the entry point is the zero-speed point of the vehicle, the aim is to find the turning point of the running state, and the corresponding driving and parking segments are obtained as the result. The key of the working condition segmentation is the acquisition of the turning point of the running state based on the zero speed point of the vehicle. The positions of all the speed zero points in the speed vector are marked, then the position indexes are differentiated, the position exceeding the threshold value in the difference result can be regarded as that the vehicle running state is changed, and the original position index is obtained in a reverse mode, so that the division of the working condition can be completed. It is obvious that the setting of the threshold has a direct influence on the division of the operating conditions. If the values of all data points corresponding to the parking sections are zero, the threshold value only needs to satisfy more than 1.
The characteristics of each driving section are similar to the characteristics of the global working condition, the basic parameters of the driving sections comprise local running duration, local distance, local average speed, local maximum speed, local speed standard deviation, local average positive acceleration (namely local acceleration), local average negative acceleration (namely local deceleration), local acceleration standard deviation and the like, and the driving sections are characterized by the driving sections with different running dates and different running times because the global working condition is the global working condition with different running dates and different running times. The characteristics for the driving sections include the total duration characteristic, the total route characteristic, the average speed characteristic of the driving sections, the driving section characteristics at different operation dates, and the driving section characteristics at different operation times.
For the parking section alone, the contained information is mainly the parking duration; if viewed on the scale of the global condition, the number of parking segments represents the number of parking cycles of a cycle. Thus, the parking segment includes two parameters, parking time and number of parking within the cycle. Similarly, similar to the characteristics of the global working condition, the characteristics of the parking sections include the parking duration and the parking times of the parking sections, and the parking sections under different operation dates and different operation moments.
4) And establishing a Gaussian mixture model according to all the driving segments and the parking segments.
5) Acquiring current traffic information which comprises a current fixed route for the vehicle to travel, a current operation date and a current operation time; based on a Gaussian mixture model, the current traffic information is used as input, corresponding driving segments and parking segments are searched, the corresponding driving segments and parking segments are classified and orderly spliced, then the global working condition is output, and the global speed is predicted.
The Gaussian mixture model realizes intelligent construction and updating of global working conditions, the goal of intelligent construction of the global working conditions is to take the space information as the basic basis and select the time information as the constraint under the condition that given space (position coordinate sequence, namely fixed route) and time information (current running date and current running time) are taken as input, and classification and ordered splicing of the minimum micro working conditions are carried out by means of the Gaussian mixture model, and the specific process is as follows:
a. and finishing the classification of the velocity segment based on a Gaussian mixture model. The gaussian mixture model refers to a linear combination of a plurality of gaussian distribution functions, and theoretically, the gaussian mixture model can be fitted with any type of distribution, and is generally used for solving the problem that data under the same set contains a plurality of different distributions. Since the parking conditions of the vehicle at each possible parking position are in accordance with the gaussian distribution, the parking rule of the vehicle is in accordance with the mixed gaussian distribution as a whole. Neglecting the parking points with small probability, selecting the mean value of Gaussian distribution at each position as the element of the parking position sequence, and finally obtaining the parking position vector which is the basis for classifying the working conditions, wherein the parking positions refer to all possible parking points with larger probability.
b. And setting a segment classification error limit. The elements of the parking position vector in the classification principle are determined numbers, and a certain floating error must be set when the speed segment is divided, namely when the starting position and the ending position of the speed segment are respectively positioned in a small interval taking two adjacent elements of the classification vector as the center, the segment can be classified into a position interval formed by the two elements. The float error can be set to a fixed value, i.e. the tolerance error is constant for all velocity segments. In practice, however, the uncertainty of the data increases with increasing length of the data, the fixed error limit does not reflect this property, so the setting of the variable error becomes the choice, and the segment classification error limit gradually increases with increasing distance traveled by the vehicle.
c. Probability weighting of parking positions. The parking positions reflected in the data are all possible parking points with a high probability, but the vehicle will not stop at these positions in the actual operation, but there is a certain probability of parking at some points. And selecting some data points with smaller probability in the parking position vector, and setting the parking probability for the data points so as to reflect the actual running condition more truly, thereby improving the construction precision of the global working condition.
d. Constraints of global runtime. The working condition construction is to recombine the micro working condition segments, and the finally obtained operation duration of the new working condition has uncertainty. The distribution interval of the overall operation duration can be obtained based on the existing working condition data, the total duration of the constructed working conditions needs to meet the constraint of the overall operation duration, and if the constraint is not met, a new working condition needs to be regenerated until the requirement is met.
e. And finishing the intelligent construction of the global working condition. Segment classification already establishes rules for segment recombination, so the segment recombination is to select segments from a classified database and then carry out sequential combination, and the result of recombination is a new constructed working condition. And determining the position of a first speed segment alternative library according to the time interval of the departure time, randomly selecting one segment, judging the time interval of the tail time of the segment, determining the position of the alternative library of the next speed segment, circulating in sequence until the last position section is reached, and completing the construction of the global working condition, wherein the intelligent construction result of the global working condition based on the traffic information is shown in figure 2 and is a curve of the distance and the speed, so that the prediction of the global vehicle speed is realized.
Based on the constructed global working condition speed curve, the global working condition speed curve is input into a whole vehicle energy management system, so that management strategy optimization control on an engine, a motor and a battery of a vehicle can be realized, and the effects of energy conservation and emission reduction are achieved.
Global vehicle speed prediction device embodiment:
the global vehicle speed prediction device provided by the embodiment comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor realizes a global vehicle speed prediction method when executing the computer program.
The specific implementation process of the global vehicle speed prediction method is described in the above embodiments of the global vehicle speed prediction method, and is not described herein again.
Claims (10)
1. A global vehicle speed prediction method, comprising the steps of:
acquiring historical working condition data and current traffic information; the current traffic information comprises a fixed route for the current vehicle to travel, the current operation date and the current operation time;
carrying out global feature statistics on historical working condition data at different fixed routes, different running dates and different running times, wherein the global features comprise global distance, global running time and global speed features;
cutting the global features into driving segments and parking segments, wherein each driving segment comprises a local distance, a local running time and a local speed feature; each parking section comprises parking duration and parking times;
establishing a mixed Gaussian model according to all the driving segments and the parking segments;
and taking the current traffic information as input, searching corresponding driving segments and parking segments, classifying and orderly splicing the corresponding driving segments and parking segments, and outputting the global working condition to realize the prediction of the global vehicle speed.
2. The global vehicle speed prediction method of claim 1, further comprising the step of data washing historical operating condition data: and processing and marking the data of the empty rows, the disorder and the abnormity.
3. The global vehicle speed prediction method of claim 1, wherein the global features further include a global acceleration feature and a global duration-over-time feature.
4. The global vehicle speed prediction method of claim 3, where each driving segment further includes a local acceleration feature.
5. The global vehicle speed prediction method of claim 1, where the global speed features include global average speed, global maximum speed, global standard deviation of speed.
6. The global vehicle speed prediction method according to claim 3, characterized in that the global acceleration characteristics include a global average acceleration, a global maximum deceleration, a global acceleration standard deviation; the global duration ratio features include a global low-speed duration ratio, a global high-speed duration ratio, a global acceleration duration ratio and a global deceleration duration ratio.
7. The global vehicle speed prediction method of claim 1, where local speed features include local average speed, local maximum speed, local standard deviation of speed.
8. The global vehicle speed prediction method of claim 4, where the local acceleration characteristics include local average acceleration, local average deceleration, local acceleration standard deviation.
9. The global vehicle speed prediction method of claim 1, wherein the cutting criteria for the drive segment and the stop segment are zero speed.
10. A global vehicle speed prediction apparatus comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the global vehicle speed prediction method as claimed in any one of claims 1 to 9 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911368643.0A CN113053135B (en) | 2019-12-26 | 2019-12-26 | Global vehicle speed prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911368643.0A CN113053135B (en) | 2019-12-26 | 2019-12-26 | Global vehicle speed prediction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113053135A true CN113053135A (en) | 2021-06-29 |
| CN113053135B CN113053135B (en) | 2023-03-31 |
Family
ID=76505500
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911368643.0A Active CN113053135B (en) | 2019-12-26 | 2019-12-26 | Global vehicle speed prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113053135B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114735013A (en) * | 2022-04-26 | 2022-07-12 | 重庆长安新能源汽车科技有限公司 | Vehicle typical working condition vehicle speed curve extraction method and system, vehicle and storage medium |
| WO2023098828A1 (en) * | 2021-12-01 | 2023-06-08 | 北京罗克维尔斯科技有限公司 | Vehicle speed combination method and apparatus, and electronic device and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106251625A (en) * | 2016-08-18 | 2016-12-21 | 上海交通大学 | Three-dimensional urban road network global state Forecasting Methodology under big data environment |
| CN107845261A (en) * | 2017-11-03 | 2018-03-27 | 北京理工大学 | A kind of automobile overall situation operating mode dynamic reconfiguration method based on tensor fusion transport information |
| CN110298579A (en) * | 2019-06-26 | 2019-10-01 | 重庆大学 | A kind of construction method of new energy passenger car urban operating condition |
| CN110610260A (en) * | 2019-08-21 | 2019-12-24 | 南京航空航天大学 | Driving energy consumption prediction system, method, storage medium and equipment |
-
2019
- 2019-12-26 CN CN201911368643.0A patent/CN113053135B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106251625A (en) * | 2016-08-18 | 2016-12-21 | 上海交通大学 | Three-dimensional urban road network global state Forecasting Methodology under big data environment |
| CN107845261A (en) * | 2017-11-03 | 2018-03-27 | 北京理工大学 | A kind of automobile overall situation operating mode dynamic reconfiguration method based on tensor fusion transport information |
| CN110298579A (en) * | 2019-06-26 | 2019-10-01 | 重庆大学 | A kind of construction method of new energy passenger car urban operating condition |
| CN110610260A (en) * | 2019-08-21 | 2019-12-24 | 南京航空航天大学 | Driving energy consumption prediction system, method, storage medium and equipment |
Non-Patent Citations (4)
| Title |
|---|
| 朱俊虎等: "城市公交车行驶工况的构建", 《交通科技与经济》 * |
| 王钦普等: "基于归类分析的城市公交客车线路行驶工况快速合成方法", 《城市公共交通》 * |
| 石琴等: "因子分析在汽车行驶工况构建过程中的应用", 《中国机械工程》 * |
| 麻笑艺等: "基于历史数据的HEV工况识别与预测方法", 《汽车电器》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023098828A1 (en) * | 2021-12-01 | 2023-06-08 | 北京罗克维尔斯科技有限公司 | Vehicle speed combination method and apparatus, and electronic device and storage medium |
| CN114735013A (en) * | 2022-04-26 | 2022-07-12 | 重庆长安新能源汽车科技有限公司 | Vehicle typical working condition vehicle speed curve extraction method and system, vehicle and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113053135B (en) | 2023-03-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220374712A1 (en) | Decision making for motion control | |
| CN107919014B (en) | Taxi running route optimization method for multiple passenger mileage | |
| CN110836675B (en) | Decision tree-based automatic driving search decision method | |
| CN104952248B (en) | A kind of vehicle convergence Forecasting Methodology based on Euclidean space | |
| CN113053135B (en) | Global vehicle speed prediction method and device | |
| CN110705774A (en) | Vehicle energy consumption analysis prediction method and system | |
| CN104792543A (en) | Constructing method of road cyclic conditions | |
| CN113011815A (en) | Truck stop point extraction method and travel characteristic determination method and device | |
| CN102087788A (en) | Method for estimating traffic state parameter based on confidence of speed of float car | |
| CN111210621B (en) | Signal green wave coordination route optimization control method and system based on real-time road condition | |
| CN106776988A (en) | A kind of anchor point based on time aggregation determines method and device | |
| CN108573600B (en) | Driver behavior induction and local traffic flow optimization method | |
| CN112735126A (en) | Mixed traffic flow cooperative optimization control method based on model predictive control | |
| CN116013087A (en) | Traffic flow statistical method based on urban moving vehicle detection | |
| CN115935672A (en) | Fuel cell automobile energy consumption calculation method fusing working condition prediction information | |
| CN106875681B (en) | A kind of traffic congestion tendency prediction technique and system | |
| Zheng et al. | A novel approach to coordinating green wave system with adaptation evolutionary strategy | |
| CN103680185A (en) | Vehicle traveling road level precise division method | |
| Liu et al. | Bustime: Which is the right prediction model for my bus arrival time? | |
| CN105139328B (en) | Hourage real-time predicting method and device towards license plate identification data | |
| CN113687247A (en) | New energy automobile remaining mileage dynamic prediction method, system, terminal and medium | |
| CN110852636B (en) | Rail transit system traction energy consumption optimization limit detection method based on operation plan | |
| CN111723871A (en) | Estimation method for real-time carriage full load rate of bus | |
| CN110097757B (en) | Intersection group critical path identification method based on depth-first search | |
| CN109598933A (en) | It is a kind of based on the k of data-driven adjacent to the traffic flow forecasting method of non parametric regression |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: No. 6, Yutong Road, Guancheng Hui District, Zhengzhou, Henan 450061 Applicant after: Yutong Bus Co.,Ltd. Address before: No.1, Shibali Heyu Road, Guancheng Hui District, Zhengzhou City, Henan Province Applicant before: ZHENGZHOU YUTONG BUS Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |