CN111831972A - Hybrid vehicle working condition prediction method and system based on road condition change - Google Patents

Hybrid vehicle working condition prediction method and system based on road condition change Download PDF

Info

Publication number
CN111831972A
CN111831972A CN202010684934.7A CN202010684934A CN111831972A CN 111831972 A CN111831972 A CN 111831972A CN 202010684934 A CN202010684934 A CN 202010684934A CN 111831972 A CN111831972 A CN 111831972A
Authority
CN
China
Prior art keywords
condition
vehicle
working condition
road condition
road
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
Application number
CN202010684934.7A
Other languages
Chinese (zh)
Inventor
陈征
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ningbo University of Technology
Original Assignee
Ningbo University of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ningbo University of Technology filed Critical Ningbo University of Technology
Priority to CN202010684934.7A priority Critical patent/CN111831972A/en
Publication of CN111831972A publication Critical patent/CN111831972A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization

Abstract

The invention belongs to the technical field of vehicle control, and relates to a hybrid vehicle working condition prediction method and system based on road condition change, which comprises the following steps: s1, setting road condition types, and establishing vectors of various road condition changes according to the road condition types; s2, establishing a conversion matrix according to the vector, and calculating a density function of the vehicle working condition corresponding to each vector; s3 obtaining vehicle working condition v at moment t according to the conversion matrix and the density functiontProbability generated by a certain road condition j and vehicle condition v at time ttThe probability that the road condition is j at the moment t +1 is obtained, and an optimal vehicle working condition matrix at the moment t +1 is obtained through recursion; s4, obtaining the mathematical expectation of the vehicle working condition according to the conversion matrix and the density function, wherein the vehicle working condition in the vehicle working condition matrix corresponding to the maximum mathematical expectation is the final predicted vehicle working condition. The method can accurately predict the future vehicle working condition of the hybrid vehicle under the condition that the road condition has an emergency.

Description

Hybrid vehicle working condition prediction method and system based on road condition change
Technical Field
The invention relates to a hybrid vehicle working condition prediction method and system based on road condition change, and belongs to the technical field of vehicle control.
Background
With the increasing exhaustion of petroleum resources and the improvement of urban environmental protection requirements, hybrid buses are widely applied to urban public transportation systems. Hybrid vehicles have a greater advantage in energy saving based on their unique structure than conventional vehicles. In order to achieve optimal energy consumption of a hybrid vehicle, the energy management strategy of the whole vehicle needs to be studied. The working condition of the vehicle is an important factor influencing the energy management strategy, so that the prediction of the working condition of the vehicle becomes an important research subject. The conventional working condition prediction method usually predicts the future working condition of the vehicle based on the existing working condition of the vehicle, but if the road condition changes at the moment, the predicted working condition of the vehicle is obviously deviated from an actual value, so that the prediction result is inaccurate. The invention provides a novel working condition prediction method,
disclosure of Invention
In view of the above-mentioned deficiencies of the prior art, the present invention provides a method and a system for predicting the working condition of a hybrid vehicle based on road condition changes, which can accurately predict the future vehicle working condition of the hybrid vehicle under the condition that the road condition is in an emergency.
In order to achieve the above object, the present invention provides a method for predicting the working condition of a hybrid vehicle based on the change of road conditions, comprising the following steps: s1, setting road condition types, and establishing vectors of various road condition changes according to the road condition types; s2, establishing a conversion matrix according to the vector, and calculating a density function of the vehicle working condition corresponding to each vector; s3 obtaining vehicle working condition v at moment t according to the conversion matrix and the density functiontProbability generated by a certain road condition j and vehicle condition v at time ttThe probability that the road condition is j at the moment t +1 is obtained, and an optimal vehicle working condition matrix at the moment t +1 is obtained through recursion; s4, obtaining the mathematical expectation of the vehicle working condition according to the conversion matrix and the density function, wherein the vehicle working condition in the vehicle working condition matrix corresponding to the maximum mathematical expectation is the final predicted vehicle working condition.
Further, the density function is obtained from a time series of vehicle operating conditions, the time series being
vt-μi＝φ(vt-μi)+t
Wherein, VtIs the speed at time t, StIs a vector of the road condition changes, a is a random road condition change, and alpha is (mu)i，μj，φ，σ2)，μiAnd mujConstant phi is S corresponding to road condition i and road condition j respectivelytThe parameters of the auto-regression of the following,tin accordance with normal distribution and independently distributed identically, σ2Is a mean square error in a normal distribution.
Further, the transformation matrix P is:
Figure BDA0002587192870000011
Figure BDA0002587192870000021
to represent
Figure BDA0002587192870000022
Which is the transition probability from road condition i to road condition j, and N is the number of road conditions.
Further, vehicle operating condition v at time ttThe probability produced by a certain road condition j is:
Figure BDA0002587192870000023
calculating the vehicle working condition v at the moment t of generating each road conditiontAnd generating the probability into a vector
Figure BDA0002587192870000024
Wherein θ represents α and
Figure BDA0002587192870000025
the parameter (c) of (c).
Further, vehicle operating condition v at time ttThe probability that the road condition is j at time t +1 is:
Figure BDA0002587192870000026
calculating the probability of the road condition being j at each road condition time t +1, and generating a vector by using the probability
Figure BDA0002587192870000027
Further, the optimal vehicle condition matrix at time t +1 is:
Figure BDA0002587192870000028
Figure BDA0002587192870000029
wherein eta istFor each vehicle corresponding to the vectorA vector consisting of the density functions of the conditions, P being a transformation matrix, indicates a dot product.
Further, the mathematical expectation of the vehicle operating conditions is: e (v)t+1|st+1＝j，vt(ii) a Theta), where theta is represented by alpha and
Figure BDA00025871928700000210
the parameter (c) of (c).
Further, the parameter θ is obtained by solving the following equation:
Figure BDA00025871928700000211
wherein T is the sampling duration.
The invention also discloses a hybrid vehicle working condition prediction system based on road condition change, which comprises the following steps: the vector establishing module is used for setting road condition types and establishing vectors changing with various road conditions according to the road condition types; the conversion matrix establishing module is used for establishing a conversion matrix according to the vector and calculating a density function of the vehicle working condition corresponding to each vector; a vehicle working condition matrix obtaining module for obtaining the vehicle working condition v at the moment t according to the conversion matrix and the density functiontFrom a certain road condition j
Probability of occurrence and vehicle behavior v at time ttThe probability that the road condition is j at the moment t +1 is obtained, and an optimal vehicle working condition matrix at the moment t +1 is obtained through recursion; and the predicted working condition output module is used for obtaining the mathematical expectation of the vehicle working condition according to the conversion matrix and the density function, and the vehicle working condition in the corresponding vehicle working condition matrix when the mathematical expectation is maximum is the finally predicted vehicle working condition.
Due to the adoption of the technical scheme, the invention has the following advantages: the scheme of the invention can accurately predict the future vehicle working condition of the hybrid vehicle under the conditions of road condition occurrence and emergency. The technical problem that the working condition of the vehicle cannot be predicted due to unpredictable road condition changes is solved. The prediction result is more accurate and reliable.
Detailed Description
The present invention is described in detail by way of specific embodiments in order to better understand the technical direction of the present invention for those skilled in the art. It should be understood, however, that the detailed description is provided for a better understanding of the invention only and that they should not be taken as limiting the invention. In describing the present invention, it is to be understood that the terminology used is for the purpose of description only and is not intended to be indicative or implied of relative importance.
Example one
The embodiment discloses a hybrid vehicle working condition prediction method based on road condition change, which comprises the following steps:
s1 sets the traffic type, and creates various traffic variation vectors according to the traffic type.
For clarity, two different road conditions are exemplified to illustrate the scheme of the embodiment. For example, the first road condition is congestion and the second road condition is smooth. Wherein the content of the first and second substances,
Figure BDA0002587192870000031
it indicates the first road condition and the second road condition,
Figure BDA0002587192870000032
indicating a second road condition. For the two different road conditions, four road condition changes exist, the first condition is that the time t is the first road condition, and the time t +1 is the first road condition; the second condition is that the time t is the first road condition, the time t +1 is the second road condition, the third condition is that the time t is the second road condition, and the time t +1 is the first road condition; the fourth case is that the time t is the second road condition, and the time t +1 is still the second road condition. In order to facilitate the expression of various situations, a new vector s is redefined in the embodimenttAnd the vector is used for representing various road condition changes. The specific expression form is as follows:
stif 1, then
Figure BDA0002587192870000033
And is
Figure BDA0002587192870000034
stIf 2, if
Figure BDA0002587192870000035
And is
Figure BDA0002587192870000036
stIf not 3, then
Figure BDA0002587192870000037
And is
Figure BDA0002587192870000038
stIf 4, if
Figure BDA0002587192870000039
And is
Figure BDA00025871928700000310
S2, establishing a conversion matrix according to the vector, and calculating the density function of the vehicle working condition corresponding to each vector.
Wherein, due to
Figure BDA00025871928700000311
Obeying a two-state Markov chain, the transition matrix P is therefore:
Figure BDA00025871928700000312
Figure BDA00025871928700000313
to represent
Figure BDA00025871928700000314
Which is the transition probability from road condition i to road condition j, and N is the number of road conditions.
For the four road condition changes in step S1, the corresponding transformation matrix is:
Figure BDA00025871928700000315
the time series of vehicle operating conditions is obtained by: road condition data are collected by vehicle-mounted equipment, and the preferred collection frequency in the embodiment is 1 Hz. The set of operating conditions may be denoted as v0，v2，…，vTWhere the subscripts 0, 2.., T denotes seconds, T is the sampling time, viDenotes the speed of the i-th second, i 0, 2. According to the characteristics of the working condition of the vehicle, the time sequence related to the working condition is assumed to be an autoregressive process, and the specific expression mode is as follows:
vt-μi＝φ(vt-μi)+t
wherein the content of the first and second substances,tis in accordance with normal distribution and is independently and identically distributed, σ2Is a mean square error in a normal distribution.
Specifically, for the four road condition changes in step S1, the density functions of the corresponding vehicle operating conditions are respectively:
Figure BDA0002587192870000041
Figure BDA0002587192870000042
Figure BDA0002587192870000043
Figure BDA0002587192870000044
s3 obtaining vehicle working condition v at moment t according to the conversion matrix and the density functiontProbability generated by a certain road condition j and vehicle condition v at time ttAnd obtaining the optimal vehicle working condition matrix at the moment t +1 through recursion according to the probability that the road condition is j at the moment t + 1.
This stepThe above parameters alpha and alpha are expressed by the parameter theta in a step
Figure BDA0002587192870000045
α＝(μi，μj，φ，σ2) Thereby obtaining:
vehicle operating mode v at time ttThe probability produced by a certain road condition j is:
Figure BDA0002587192870000046
calculating the vehicle working condition v at the moment t of generating each road conditiontAnd generating the probability into a vector
Figure BDA0002587192870000047
Wherein θ represents α and
Figure BDA0002587192870000048
the parameter (c) of (c).
Vehicle operating mode v at time ttThe probability that the road condition is j at time t +1 is:
Figure BDA0002587192870000049
calculating the probability of the road condition being j at each road condition time t +1, and generating a vector by using the probability
Figure BDA00025871928700000410
Further, the optimal vehicle condition matrix at time t +1 is:
Figure BDA00025871928700000411
Figure BDA00025871928700000412
wherein the initial conditions are
Figure BDA0002587192870000051
ρ is a fixed non-negative constant vector, which indicates a dot product. P is a transformation matrix. l' is a vector with 1 per componentTransposed vector, ηtThe vector formed by the density function of the vehicle working condition corresponding to each vector, for example, the situation corresponding to two different road conditions in step S1,
Figure BDA0002587192870000052
wherein the content of the first and second substances,
Figure BDA0002587192870000053
and
Figure BDA0002587192870000054
is a density function corresponding to each road condition.
The parameter θ is obtained by solving the following equation:
Figure BDA0002587192870000055
wherein T is the sampling duration.
S4, obtaining the mathematical expectation of the vehicle working condition according to the conversion matrix and the density function, wherein the vehicle working condition in the vehicle working condition matrix corresponding to the maximum mathematical expectation is the final predicted vehicle working condition.
The mathematical expectation of the vehicle operating conditions is: e (v)t+1|st+1＝j,vt(ii) a Theta), where theta is represented by alpha and
Figure BDA0002587192870000056
the parameter (c) of (c).
Example two
Based on the same inventive concept, the embodiment also discloses a hybrid vehicle working condition prediction system based on road condition changes, which comprises:
the vector establishing module is used for setting road condition types and establishing vectors of various road condition changes according to the road condition types;
the conversion matrix establishing module is used for establishing a conversion matrix according to the vector and calculating a density function of the vehicle working condition corresponding to each vector;
vehicle behavior matrix acquisition module forObtaining the vehicle condition v at the moment t according to the transformation matrix and the density functiontProbability generated by a certain road condition j and vehicle condition v at time ttThe probability that the road condition is j at the moment t +1 is obtained, and an optimal vehicle working condition matrix at the moment t +1 is obtained through recursion;
and the predicted working condition output module is used for obtaining the mathematical expectation of the vehicle working condition according to the conversion matrix and the density function, and the vehicle working condition in the corresponding vehicle working condition matrix when the mathematical expectation is maximum is the finally predicted vehicle working condition.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (9)

1. A hybrid vehicle working condition prediction method based on road condition change is characterized by comprising the following steps:
s1, setting road condition types, and establishing vectors of various road condition changes according to the road condition types;
s2, establishing a conversion matrix according to the vectors, and calculating the density function of the vehicle working condition corresponding to each vector;
s3 obtaining vehicle working condition v at time t according to the conversion matrix and the density functiontProbability generated by a certain road condition j and vehicle condition v at time ttThe probability that the road condition is j at the moment t +1 is obtained, and an optimal vehicle working condition matrix at the moment t +1 is obtained through recursion;
s4, obtaining the mathematical expectation of the vehicle working condition according to the conversion matrix and the density function, wherein the vehicle working condition in the vehicle working condition matrix corresponding to the maximum mathematical expectation is the final predicted vehicle working condition.
2. A method as claimed in claim 1, wherein the density function is obtained from a time series of vehicle conditions, the time series being:
vt-μi＝φ(vt-μi)+t
wherein, VtIs the speed at time t, StIs a vector of the road condition changes, a is a random road condition change, and alpha is (mu)i，μj，φ，σ2)，μiAnd mujConstant phi is S corresponding to road condition i and road condition j respectivelytThe parameters of the auto-regression of the following,tin accordance with normal distribution and independently distributed identically, σ2Is a mean square error in a normal distribution.
3. The method of claim 2, wherein the transformation matrix P is:
Figure FDA0002587192860000011
Figure FDA0002587192860000012
to represent
Figure FDA0002587192860000013
Which is the transition probability from road condition i to road condition j, and N is the number of road conditions.
4. The method of claim 3 wherein vehicle condition v is predicted at time ttThe probability produced by a certain road condition j is:
Figure FDA0002587192860000014
calculating the vehicle working condition v at the moment t of generating each road conditiontAnd generating the probability into a vector
Figure FDA0002587192860000015
Wherein θ represents α and
Figure FDA0002587192860000016
the parameter (c) of (c).
5. The method of claim 4 wherein vehicle condition v is predicted at time t based on the change in road conditionstThe probability that the road condition is j at time t +1 is:
Figure FDA0002587192860000017
calculating the probability of the road condition being j at each road condition time t +1, and generating a vector by using the probability
Figure FDA0002587192860000018
6. The method of claim 5 for predicting the operating conditions of a hybrid vehicle based on the change of road conditions, wherein the optimal vehicle operating condition matrix at the time t +1 is:
Figure FDA0002587192860000019
Figure FDA0002587192860000021
wherein eta istP is a vector formed by the density function of the vehicle working condition corresponding to each vector, is a conversion matrix, and indicates a dot product.
7. A method as claimed in claim 3 for predicting vehicle conditions based on changes in road conditions, wherein the mathematical expectation of the vehicle conditions is: e (v)t+1|st+1＝j，vt(ii) a Theta), where theta is represented by alpha and
Figure FDA0002587192860000022
parameter (d) of。
8. A method for predicting a condition of a hybrid vehicle according to any one of claims 5 to 7, wherein the parameter θ is obtained by solving the following equation:
Figure FDA0002587192860000023
wherein T is the sampling duration.
9. A hybrid vehicle condition prediction system based on road condition changes is characterized by comprising:
the vector establishing module is used for setting road condition types and establishing vectors of various road condition changes according to the road condition types;
the conversion matrix establishing module is used for establishing a conversion matrix according to the vectors and calculating a density function of the vehicle working condition corresponding to each vector;
a vehicle working condition matrix obtaining module for obtaining the vehicle working condition v at the moment t according to the conversion matrix and the density functiontProbability generated by a certain road condition j and vehicle condition v at time ttThe probability that the road condition is j at the moment t +1 is obtained, and an optimal vehicle working condition matrix at the moment t +1 is obtained through recursion;
and the predicted working condition output module is used for obtaining the mathematical expectation of the working condition of the vehicle according to the conversion matrix and the density function, and the corresponding working condition of the vehicle in the working condition matrix when the mathematical expectation is maximum is the final predicted working condition of the vehicle.
CN202010684934.7A 2020-07-16 2020-07-16 Hybrid vehicle working condition prediction method and system based on road condition change Pending CN111831972A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010684934.7A CN111831972A (en) 2020-07-16 2020-07-16 Hybrid vehicle working condition prediction method and system based on road condition change

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010684934.7A CN111831972A (en) 2020-07-16 2020-07-16 Hybrid vehicle working condition prediction method and system based on road condition change

Publications (1)

Publication Number Publication Date
CN111831972A true CN111831972A (en) 2020-10-27

Family

ID=72924076

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010684934.7A Pending CN111831972A (en) 2020-07-16 2020-07-16 Hybrid vehicle working condition prediction method and system based on road condition change

Country Status (1)

Country Link
CN (1) CN111831972A (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108128309A (en) * 2017-09-01 2018-06-08 特百佳动力科技有限公司 A kind of method that vehicle working condition is predicted in real time
CN109017809A (en) * 2018-08-27 2018-12-18 北京理工大学 A kind of energy distributing method based on the prediction of cross-country operating condition
CN109733378A (en) * 2018-12-19 2019-05-10 江苏大学 Optimize the torque distribution method predicted on line under a kind of line
CN109767619A (en) * 2018-12-29 2019-05-17 江苏大学 A kind of intelligent network connection pure electric automobile driving cycle prediction technique
CN110728772A (en) * 2019-10-15 2020-01-24 西南交通大学 Construction method for typical running condition of tramcar
CN110758121A (en) * 2019-11-13 2020-02-07 北京理工大学 Energy management system based on hierarchical control

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108128309A (en) * 2017-09-01 2018-06-08 特百佳动力科技有限公司 A kind of method that vehicle working condition is predicted in real time
CN109017809A (en) * 2018-08-27 2018-12-18 北京理工大学 A kind of energy distributing method based on the prediction of cross-country operating condition
CN109733378A (en) * 2018-12-19 2019-05-10 江苏大学 Optimize the torque distribution method predicted on line under a kind of line
CN109767619A (en) * 2018-12-29 2019-05-17 江苏大学 A kind of intelligent network connection pure electric automobile driving cycle prediction technique
CN110728772A (en) * 2019-10-15 2020-01-24 西南交通大学 Construction method for typical running condition of tramcar
CN110758121A (en) * 2019-11-13 2020-02-07 北京理工大学 Energy management system based on hierarchical control

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
吕林 等: "不同路况下汽车行驶工况的测试与分析", 《武汉理工大学学报（交通科学与工程版）》, vol. 30, no. 5, pages 781 - 784 *
张昕 等: "基于马尔可夫链的混合动力汽车行驶工况预测研究", 《汽车工程》, vol. 36, no. 10, pages 1216 - 1220 *

Similar Documents

Publication Publication Date Title
Zhang et al. Cloud computing-based real-time global optimization of battery aging and energy consumption for plug-in hybrid electric vehicles
CN106427589A (en) Electric car driving range estimation method based on prediction of working condition and fuzzy energy consumption
Li et al. Prediction of electric bus energy consumption with stochastic speed profile generation modelling and data driven method based on real-world big data
US20230139003A1 (en) Systems and methods for managing velocity profiles
Ullah et al. Modeling of machine learning with SHAP approach for electric vehicle charging station choice behavior prediction
CN103745110A (en) Method of estimating operational driving range of all-electric buses
CN111703418B (en) Multi-vehicle distributed cooperative collision avoidance method and device based on vehicle-to-vehicle communication
CN103745111A (en) Method of predicting driving range of all-electric passenger vehicles
CN112529437B (en) Multi-target satellite imaging planning method
CN109887279B (en) Traffic jam prediction method and system
CN106530680A (en) Combined service method of bus routes based on express buses
Zhou Attention based stack resnet for citywide traffic accident prediction
Xin et al. Optimal energy management of fuel cell hybrid electric vehicle based on model predictive control and on-line mass estimation
He et al. A new cost-minimizing power-allocating strategy for the hybrid electric bus with fuel cell/battery health-aware control
CN111047120A (en) Electric vehicle charging load prediction method under circuit-electric coupling network
Liu et al. High-precision transient fuel consumption model based on support vector regression
CN107506568A (en) A kind of traffic accident data analyze the method with prediction in real time
CN111831972A (en) Hybrid vehicle working condition prediction method and system based on road condition change
Li et al. A hybrid approach for short-term traffic flow forecasting based on similarity identification
CN115860185A (en) Power grid load prediction method considering charging modes of various types of electric automobiles in extremely high temperature weather
CN114463978B (en) Data monitoring method based on track traffic information processing terminal
US20230264578A1 (en) Method for predicting energy consumption-recovery ratio of new energy vehicle, and energy saving control method and system for new energy vehicle
CN115185183A (en) Green wave vehicle speed tracking control method and system based on safety critics
Radi et al. Enhanced Implementation of Intelligent Transportation Systems (ITS) based on Machine Learning Approaches
Feng et al. Traffic Flow Prediction of Urban Intersection Based on Environmental Impact Factors and Markov Chains

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