CN115214691A - Method and device for predicting vehicle running speed, electronic device and storage medium - Google Patents
Method and device for predicting vehicle running speed, electronic device and storage medium Download PDFInfo
- Publication number
- CN115214691A CN115214691A CN202210926840.5A CN202210926840A CN115214691A CN 115214691 A CN115214691 A CN 115214691A CN 202210926840 A CN202210926840 A CN 202210926840A CN 115214691 A CN115214691 A CN 115214691A
- Authority
- CN
- China
- Prior art keywords
- acceleration
- model
- automobile
- state
- predicting
- 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
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
- B60W40/105—Speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
- B60W40/107—Longitudinal acceleration
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Mathematical Physics (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The application provides a method for predicting the running speed of an automobile, which comprises the following steps of S01, capturing speed data in a preset period, and training and classifying an autoregressive model according to a fuzzy membership model and the speed data so as to obtain autoregressive models corresponding to different acceleration states; s02, collecting corresponding acceleration measurement values at different moments, classifying the acceleration measurement values through a fuzzy membership model, mapping the classified acceleration measurement values to a Markov chain model, and predicting the future acceleration state of the automobile through the Markov chain model; and S03, predicting the future driving speed of the automobile according to the predicted future acceleration state of the automobile and the auto-regression model corresponding to the future acceleration state of the automobile. The application also provides an automobile running speed prediction device, electronic equipment and a storage medium.
Description
Technical Field
The application relates to the technical field of automobile real-time working condition prediction, in particular to an automobile running speed prediction method, an automobile running speed prediction device, electronic equipment and a storage medium.
Background
With the increasing automobile holding capacity in China, the energy problem and the automobile exhaust emission problem become more serious day by day, and the automobile industry is urgently required to change to the direction of energy conservation and emission reduction. The hybrid electric vehicle is widely popularized in recent years by virtue of excellent fuel-saving performance, the fuel economy level of the hybrid electric vehicle determines the important position in a new energy vehicle, and the key is to adopt an optimized control strategy to improve the fuel economy. Various optimization algorithms are applied to the whole vehicle control of the hybrid electric vehicle at present, wherein Model Predictive Control (MPC) is used as a very promising control technology in a control algorithm and is well applied to the control of the hybrid electric vehicle, the precision of a prediction model of the MPC has great influence on the control effect, and the control effect is better when the precision of the prediction model is higher. The change of the required power in the prediction time domain is very large, so that the required power needs to be predicted and can be obtained by calculating the speed, however, the prior art cannot realize the improvement of the adaptivity and the accuracy of an energy management control strategy in the driving process of the hybrid electric vehicle under the complex and variable real-time working condition.
Disclosure of Invention
In view of the above, the present invention provides a method and an apparatus for predicting a vehicle driving speed, an electronic device, and a storage medium, for overcoming the defect in the prior art that the adaptivity and accuracy of an energy management control strategy in a driving process of a hybrid vehicle cannot be improved under complex and variable real-time conditions.
In a first aspect, the present invention provides a method for predicting a driving speed of an automobile, comprising the steps of,
s01, capturing vehicle speed data in a preset period, and training and classifying the autoregressive model according to the fuzzy membership model and the vehicle speed data to obtain autoregressive models corresponding to different acceleration states;
s02, collecting corresponding acceleration measurement values at different moments, classifying the acceleration measurement values through a fuzzy membership model, mapping the classified acceleration measurement values to a Markov chain model, and predicting the future acceleration state of the automobile through the Markov chain model;
and S03, predicting the future running speed of the automobile according to the predicted future acceleration state of the automobile and the autoregressive model corresponding to the future acceleration state of the automobile.
In the method for predicting the running speed of the hybrid electric vehicle according to the present invention,
in the step S01, different acceleration states comprise a rapid acceleration state, an acceleration state, a cruising state, a deceleration state and a rapid deceleration state.
In the method for predicting the running speed of the hybrid electric vehicle according to the present invention,
the fuzzy membership model is a fuzzy membership model based on a fuzzy C-means clustering method.
In the method for predicting the running vehicle speed of the hybrid vehicle according to the invention,
in step S02, the collecting of acceleration measurement values corresponding to different times, and the classifying of the acceleration measurement values by the fuzzy membership model includes:
acquiring acceleration measurement values corresponding to different moments, wherein the number of the acceleration measurement values is n, and the dimension of the acceleration measurement value is d;
and dividing the n d-dimensional acceleration measured values into a C class through a fuzzy membership model.
In the method for predicting the running speed of the hybrid electric vehicle according to the present invention,
the step of classifying the n d-dimensional acceleration measurement values into a class C through a fuzzy membership model comprises the following steps:
s11, selecting a constant epsilon larger than 0, initializing a clustering center of an acceleration measured value corresponding to the autoregressive model type, and setting the iteration number as t;
s12, determining a membership matrix of the fuzzy membership model through a first formula;
s13, calculating an objective function value of the fuzzy membership model through a second formula, judging whether the objective function value is smaller than a first preset threshold value or whether the absolute value of the change amount of the objective function value relative to the last objective function value is smaller than a constant epsilon, and finishing the classification of the acceleration measured values when the objective function value is smaller than the first preset threshold value or the absolute value of the change amount of the objective function value relative to the last objective function value is smaller than the constant epsilon; otherwise, jumping to the step S4;
and S14, setting t = t +1, correcting the clustering center of the acceleration measurement value corresponding to the autoregressive model type according to a third formula, and returning to execute the step S2.
In the method for predicting the running vehicle speed of the hybrid vehicle according to the invention,
the step S02 of mapping the classified acceleration measurement value to a markov chain model, and predicting the future acceleration state of the vehicle by the markov chain model includes:
s21, defining a discrete whole local area set containing all acceleration measurement values;
s22, converting the current acceleration value of the automobile into a fuzzy state distribution matrix, and calculating and predicting the corresponding prediction probability distribution of each acceleration measurement in the discrete whole-area set through a fourth formula;
and S23, converting the prediction probability distribution into Markov state membership in a Markov chain model through a fifth formula, and predicting the future acceleration state of the automobile through the Markov state membership.
In the method for predicting the running speed of the hybrid electric vehicle according to the present invention,
the step S03 of predicting the future driving speed of the vehicle according to the predicted future acceleration state of the vehicle and the auto-regression model corresponding to the future acceleration state of the vehicle includes:
s31, determining an autoregressive model for speed prediction according to the matching degree of the fuzzy state membership degree corresponding to the autoregressive model corresponding to the future acceleration state of the current automobile and the Markov state membership degree, and predicting the speed of the automobile through the determined autoregressive model;
s32, when the speed of the next speed area is predicted, the fuzzy state membership degree corresponding to the autoregressive model corresponding to the future acceleration state of the corresponding automobile is switched, the Markov probability transition matrix is updated, the autoregressive model used for speed prediction is determined again, and the automobile speed is predicted through the determined autoregressive model until the automobile speed prediction corresponding to all acceleration measured values in the discrete whole local area set is completed.
In a second aspect, the present invention further provides a device for predicting a driving speed of a vehicle, comprising the following modules,
the state classification module is used for capturing vehicle speed data in a preset period and training and classifying the autoregressive model according to the fuzzy membership model and the vehicle speed data so as to obtain autoregressive models corresponding to different acceleration states;
the state prediction module is used for acquiring corresponding acceleration measurement values at different moments, classifying the acceleration measurement values through a fuzzy membership model, mapping the classified acceleration measurement values to a Markov chain model, and predicting the future acceleration state of the automobile through the Markov chain model;
and the vehicle speed prediction module is used for predicting the future driving vehicle speed of the vehicle according to the predicted future acceleration state of the vehicle and the autoregressive model corresponding to the future acceleration state of the vehicle.
In a third aspect, the present invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement any of the method steps as described above.
In a fourth aspect, the invention also provides a computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method steps of any of the above-mentioned methods.
The invention has the beneficial effects that:
compared with the prior art, the automobile driving speed prediction method, the automobile driving speed prediction device, the electronic equipment and the storage medium have the following advantages that: the method for predicting the running speed of the automobile in a future period can predict the running speed of the automobile by adopting a method of combining a fuzzy membership model, a Markov chain model and an autoregressive model aiming at different types of working conditions, can improve the adaptivity and the accuracy of the control of the automobile energy management strategy under complex and variable real-time working conditions, and can improve the performance of the control strategy when the automobile runs.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flow chart of a method for predicting a driving speed of a vehicle according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating a vehicle speed prediction scheme provided by an embodiment of the present invention;
FIG. 3 is a diagram illustrating the center values of membership functions for different speed ranges according to an embodiment of the present invention;
FIG. 4a is a diagram of a probability transition matrix in a rapid acceleration state according to an embodiment of the present invention;
FIG. 4b is a diagram of a probability transition matrix under an acceleration state according to an embodiment of the present invention;
FIG. 4c is a graph of a probability transition matrix at cruise provided by an embodiment of the present invention;
FIG. 4d is a diagram of a probability transition matrix in a deceleration state according to an embodiment of the present invention;
fig. 4e is a probability transition matrix diagram in a rapid deceleration state according to an embodiment of the present invention;
FIG. 5 is a schematic structural diagram of a device for predicting a driving speed of a vehicle according to another embodiment of the present invention;
fig. 6 is a schematic diagram of an electronic structural device according to another embodiment of the present invention.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. The following description refers to the accompanying drawings in which the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with this description. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the specification, as detailed in the claims that follow.
The terminology used in the description herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the description. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, the first information may also be referred to as second information, and similarly, the second information may also be referred to as first information, without departing from the scope of the present specification. The word "if" as used herein may be interpreted as "at" \8230; "or" when 8230; \8230; "or" in response to a determination ", depending on the context.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.
Example 1
In a first aspect, as shown in fig. 1-2, an embodiment of the present invention provides a method for predicting a driving speed of a vehicle, including the steps of,
and S01, capturing vehicle speed data in a preset period, and training and classifying the autoregressive model according to the fuzzy membership model and the vehicle speed data to obtain autoregressive models corresponding to different acceleration states.
Optionally, the different acceleration states include a rapid acceleration state, an acceleration state, a cruising state, a deceleration state and a rapid deceleration state during the running process of the automobile.
Alternatively, the Autoregressive (AR) model may be an autoregressive model of order P, which is calculated as follows:
in the formula, theta i Is the autoregressive coefficient, i and k are the sequence order, P is the hysteresis order of the autoregressive model, ε k For noise sequences, v (k) is the vehicle speed per sample time, fromCoefficient of regression model theta i The vehicle speed data required by the autoregressive model is updated along with the update of the vehicle speed measured value; each set of coefficients theta i ......θ p The dynamic change conditions of the vehicle speed in a preset period are represented, and the vehicle speed is predicted by calculating the coefficient of the autoregressive model.
For the autoregressive model, the selection of the number of variables has a great influence on the prediction accuracy, and is mainly judged by the information content of the akachi pool (AIC). In the test process, 3000s of vehicle speed samples are adopted, and a first-order autoregressive model to a fourth-order autoregressive model are respectively used for predicting the vehicle speed for 7-10s, and the final result shows that the second-order autoregressive model has the best effect under the AIC criterion. The calculated parameter tables of the AR models in different states are shown in fig. 3.
Optionally, the fuzzy membership model in this embodiment may be a fuzzy membership model based on a fuzzy C-means clustering method.
S02, collecting corresponding acceleration measurement values at different moments, classifying the acceleration measurement values through a fuzzy membership model, mapping the classified acceleration measurement values to a Markov chain model, and predicting the future acceleration state of the automobile through the Markov chain model.
In the method for predicting the running speed of the hybrid electric vehicle according to the present invention,
in step S02, the collecting of acceleration measurement values corresponding to different times, and the classifying of the acceleration measurement values by the fuzzy membership model includes:
acquiring corresponding acceleration measurement values at different moments, wherein the number of the acceleration measurement values is n, and the dimension of the acceleration measurement value is d;
and dividing the n d-dimensional acceleration measurement values into C types through a fuzzy membership model.
Alternatively, in a more specific embodiment, the autoregressive model is classified by a fuzzy C-means clustering based FCM method that samples n d-dimensional acceleration measurements x i Are classified into C groups, where i =1,2The labels of different classes are different, and the clustering center set is { c 1 ，c 2 ...，c j And realizing a fuzzy membership model based on a fuzzy C-means clustering method by the following three formulas.
Wherein: u is a membership matrix, mu ij And the degree of the sample xi belonging to the class j is shown, and the parameter m is a weighted fuzzy indicator and reflects the degree of sharing of the control membership degree among the classes. N, N and M are maximum values in the mathematical formula, and the range of N, N and M is 1-N,1-N and 1-M.
When m =2 is selected, the step of classifying the n d-dimensional acceleration measurement values into a class C through a fuzzy membership model comprises the following steps:
s11, selecting a constant epsilon>0, initializing the clustering center c of the acceleration measurement value corresponding to the type of the autoregressive model j Wherein j =1,2,. C, the iteration number is t; firstly, determining a clustering center according to existing data, and then determining which acceleration class belongs to according to a membership function of each measured value, wherein c generally refers to each clustering center value.
And S12, determining a membership matrix U of the fuzzy membership model through a first formula.
S13, calculating an objective function value of the fuzzy membership model through a second formula, and judging whether the objective function value is smaller than a first preset threshold value or whether the absolute value of the change amount of the objective function value relative to the last objective function value is smaller than a constant epsilon, namely | J (t+1) -J (t) |<E, when the value of the objective function is smaller than a first preset threshold value or is opposite to the value of the objective functionWhen the absolute value of the change amount of the last objective function value is smaller than a constant epsilon, finishing the classification of the acceleration measured value; otherwise, the process jumps to step S4.
S14, setting t = t +1, and correcting the clustering center C of the acceleration measured value corresponding to the type of the autoregressive model according to a third formula (t) And returning to execute the step S2.
Further, the membership function used to reflect membership is as follows:
A i (x)＝exp(-k i (x-c i ) 2 ) And i belongs to {2,3,4}, and five types of acceleration at the position are obtained by calculating the 2/3/4 type by using the formula.
Wherein x is an acceleration element, A i (x) The membership degree of the corresponding state; k is a radical of formula i For controlling the width of the membership function, c i The central value of the membership function of each state; the center values of the membership function for the different speed ranges are shown in figure 3.
In a preferred embodiment, the step S02 of mapping the classified acceleration measurement values to a markov chain model, and predicting the future acceleration state of the vehicle by the markov chain model includes:
and S21, defining a discrete whole local area set containing all acceleration measurement values.
Alternatively, a more specific embodiment is as follows, defining a discrete global set X comprising N elements, the global set X covering all acceleration measurements, defining a 1X 14 row vector: x = [ -1.2-1.0.. 1.21.4].
And S22, converting the current acceleration value of the automobile into a fuzzy state distribution matrix, and calculating and predicting the corresponding prediction probability distribution of each acceleration measurement in the discrete whole-area set through a fourth formula.
Optionally, the current acceleration value x k Transition to fuzzy state distribution matrix
The calculation method is as follows:
F 0 (k)＝F 0 (k-1)+φ(τ(k)γ(k) T 1 5×1 -F 0 (k-1))
F(k)＝F(k-1)+φ(τ(k)γ(k) T 1 5×1 -F(k-1))
Π(k)＝diag(F 0 (k)) -1 F(k)
wherein
Pi is a state probability transition matrix, τ (k) and γ (k) are membership degrees of the 5 acceleration states in step S21 and this step, respectively, matrix F includes transition frequencies, an initial value is a positive value of a preset value, and matrix F 0 Representing the total transition frequency in each state, phi being a forgetting factor for fading out old data (i.e. old acceleration x) k ) The influence of (c). Prediction
Distribution at each step
S23, predicting probability distribution through a fifth formula
Markov state membership converted into Markov chain model
And predicting the future acceleration state of the automobile through the Markov state membership degree.
The fifth formula is as follows:
for discrete metrics that cross the boundary, the value is defined as the closest terminal state membership value, and the membership vector is
Or alternatively
And calculating to obtain the future state according to the steps, and then predicting the vehicle speed by using the AR model of the corresponding state. Only each acceleration measurement in S22 is repeatedly calculated throughout the course of vehicle speed prediction, and the amount of calculation thereof is relatively low.
And S03, predicting the future running speed of the automobile according to the predicted future acceleration state of the automobile and the autoregressive model corresponding to the future acceleration state of the automobile.
The principle of the embodiment is as follows: in order to capture transient change of the driving state, the Markov chain model is subjected to speed coding by using the membership data of the acceleration state, and k is selected 1,5 ＝3，k 2,4 ＝9，k 3 =15, measure acceleration at step k, calculate fuzzy markov state membership by the following equation
In the actual driving process, the change of the vehicle state is changed according to the external environment information and the intention of the driver, the change rule is unknown, and therefore the change of the vehicle speed state is a random process. At the extraneous driving moment, the state of the vehicle can be regarded as being related to the current vehicle speed and acceleration, and is not related to the history information, so the process of state change can be regarded as a markov process.
In the method for predicting the running speed of the hybrid electric vehicle according to the present invention,
the step S03 of predicting the future vehicle speed of the vehicle according to the predicted future acceleration state of the vehicle and the auto-regression model corresponding to the future acceleration state of the vehicle includes:
and S31, determining an autoregressive model for speed prediction according to the matching degree of the fuzzy state membership degree corresponding to the autoregressive model corresponding to the future acceleration state of the current automobile and the Markov state membership degree, and performing determined autoregression.
In the classification process, each history-trained autoregressive AR model is assigned with a fuzzy state membership degree beta i Thus, the autoregressive AR model with the highest membership similarity to the state membership prediction is searched. A deterministic velocity prediction is calculated from the selected autoregressive AR model.
The model predicts the speed of the vehicle.
S32, when the speed of the next speed area is predicted, the fuzzy state membership a corresponding to the autoregressive model corresponding to the future acceleration state of the automobile is switched, the Markov probability transition matrix pi is updated, the autoregressive model used for speed prediction is determined again, and the automobile speed is predicted through the determined autoregressive model until the speed prediction of the automobile corresponding to all the acceleration measured values in the discrete global area set is completed.
When the predicted speed reaches the next speed area, the Markov probability transition matrix pi and the state membership matrix a are switched, the probability distribution chi is updated in the switching step, and then the step S21 is carried out to predict the speed of the automobile corresponding to all the acceleration measured values in the discrete global area set. The probability transition matrices for different acceleration states are shown in fig. 4a-4 e.
The embodiment of the invention has the following beneficial effects: the method for predicting the running speed of the automobile in a future period can predict the running speed of the automobile by adopting a method of combining a fuzzy membership model, a Markov chain model and an autoregressive model aiming at different types of working conditions, can improve the adaptivity and the accuracy of the control of the automobile energy management strategy under complex and variable real-time working conditions, and can improve the performance of the control strategy when the automobile runs.
Example 2
In a second aspect, as shown in fig. 5, an embodiment of the invention further provides a device for predicting the running speed of an automobile, which includes the following modules,
and the state classification module 10 is used for capturing vehicle speed data in a preset period, and training and classifying the autoregressive model according to the fuzzy membership model and the vehicle speed data so as to obtain autoregressive models corresponding to different acceleration states.
And the state prediction module 20 is used for acquiring corresponding acceleration measurement values at different moments, classifying the acceleration measurement values through a fuzzy membership model, mapping the classified acceleration measurement values to a Markov chain model, and predicting the future acceleration state of the automobile through the Markov chain model.
And the vehicle speed prediction module 30 is configured to predict the future driving vehicle speed of the vehicle according to the predicted future acceleration state of the vehicle and the auto-regression model corresponding to the future acceleration state of the vehicle.
Example 3
In a third aspect, as shown in fig. 6, based on the same inventive concept, embodiment 3 of the present application provides an electronic device, as shown in fig. 6, including a memory 304, a processor 302, and a computer program stored in the memory 304 and executable on the processor 302, where the processor 302 implements the steps of one of the methods when executing the program.
Where in fig. 6 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 306 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be one and the same element, i.e. a transceiver, providing a means for communicating with various other apparatus over a transmission medium. The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
Example 4
In a fourth aspect, the present embodiment also provides a computer-readable storage medium, on which a computer program is stored, which program, when executed by a processor, performs the method steps as described in any of the above.
The inventive concept of examples 2-4 is the same as that of example 1, and its advantageous effects are not described herein.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
Various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It will be appreciated by those skilled in the art that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in the thermal emulation device, electronic device, or aluminum substrate according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from the internet or provided on a carrier signal, or in any other form.
The foregoing is only an embodiment of the present application, and it should be noted that, for those skilled in the art, many changes and modifications can be made without departing from the structure of the present application, which should also be considered as the protection scope of the present application, and these will not affect the effect of the implementation of the present application and the practicability of the patent. The scope of the claims of the present application shall be defined by the claims, and the description of the embodiments and the like in the specification shall be used to explain the contents of the claims.
Claims (10)
1. A method for predicting the running speed of an automobile is characterized by comprising the following steps,
s01, capturing vehicle speed data in a preset period, and training and classifying the autoregressive model according to the fuzzy membership model and the vehicle speed data to obtain autoregressive models corresponding to different acceleration states;
s02, collecting corresponding acceleration measurement values at different moments, classifying the acceleration measurement values through a fuzzy membership model, mapping the classified acceleration measurement values to a Markov chain model, and predicting the future acceleration state of the automobile through the Markov chain model;
and S03, predicting the future running speed of the automobile according to the predicted future acceleration state of the automobile and the autoregressive model corresponding to the future acceleration state of the automobile.
2. The method for predicting the traveling speed of an automobile according to claim 1,
in the step S01, different acceleration states comprise a rapid acceleration state, an acceleration state, a cruising state, a deceleration state and a rapid deceleration state.
3. The method for predicting the traveling vehicle speed of a hybrid vehicle according to claim 1,
the fuzzy membership model is a fuzzy membership model based on a fuzzy C-means clustering method.
4. The method for predicting the traveling vehicle speed of an automobile according to claim 3,
in the step S02, collecting acceleration measurement values corresponding to different times, and classifying the acceleration measurement values through a fuzzy membership model includes:
acquiring corresponding acceleration measurement values at different moments, wherein the number of the acceleration measurement values is n, and the dimension of the acceleration measurement value is d;
and dividing the n d-dimensional acceleration measured values into a C class through a fuzzy membership model.
5. The method for predicting the traveling speed of an automobile according to claim 4,
the step of classifying the n d-dimensional acceleration measurement values into a class C through a fuzzy membership model comprises the following steps:
s11, selecting a constant epsilon larger than 0, initializing a clustering center of an acceleration measured value corresponding to the autoregressive model type, and setting the iteration number as t;
s12, determining a membership matrix of the fuzzy membership model through a first formula;
s13, calculating an objective function value of the fuzzy membership model through a second formula, judging whether the objective function value is smaller than a first preset threshold value or whether the absolute value of the change amount of the objective function value relative to the last objective function value is smaller than a constant epsilon, and finishing the classification of the acceleration measured values when the objective function value is smaller than the first preset threshold value or the absolute value of the change amount of the objective function value relative to the last objective function value is smaller than the constant epsilon; otherwise, jumping to the step S4;
and S14, setting t = t +1, correcting the clustering center of the acceleration measurement value corresponding to the type of the autoregressive model according to a third formula, and returning to execute the step S2.
6. The method for predicting the traveling speed of an automobile according to claim 5,
the step S02 of mapping the classified acceleration measurement value to a markov chain model, and predicting the future acceleration state of the vehicle by the markov chain model includes:
s21, defining a discrete global area set containing all acceleration measurement values;
s22, converting the current acceleration value of the automobile into a fuzzy state distribution matrix, and calculating and predicting the corresponding prediction probability distribution of each acceleration measurement in the discrete whole-area set through a fourth formula;
and S23, converting the prediction probability distribution into Markov state membership in a Markov chain model through a fifth formula, and predicting the future acceleration state of the automobile through the Markov state membership.
7. The method for predicting the traveling vehicle speed of an automobile according to claim 6,
the step S03 of predicting the future vehicle speed of the vehicle according to the predicted future acceleration state of the vehicle and the auto-regression model corresponding to the future acceleration state of the vehicle includes:
s31, determining an autoregressive model for speed prediction according to the matching degree of the fuzzy state membership degree corresponding to the autoregressive model corresponding to the future acceleration state of the current automobile and the Markov state membership degree, and predicting the speed of the automobile through the determined autoregressive model;
s32, when the speed of the next speed area is predicted, the fuzzy state membership degree corresponding to the autoregressive model corresponding to the future acceleration state of the corresponding automobile is switched, the Markov probability transition matrix is updated, the autoregressive model used for speed prediction is determined again, and the automobile speed is predicted through the determined autoregressive model until the automobile speed prediction corresponding to all acceleration measured values in the discrete whole local area set is completed.
8. The automobile running speed predicting device is characterized by comprising the following modules,
the state classification module is used for capturing vehicle speed data in a preset period and training and classifying the autoregressive model according to the fuzzy membership model and the vehicle speed data so as to obtain autoregressive models corresponding to different acceleration states;
the state prediction module is used for acquiring corresponding acceleration measurement values at different moments, classifying the acceleration measurement values through a fuzzy membership model, mapping the classified acceleration measurement values to a Markov chain model, and predicting the future acceleration state of the automobile through the Markov chain model;
and the vehicle speed prediction module is used for predicting the future driving vehicle speed of the vehicle according to the predicted future acceleration state of the vehicle and the auto-regression model corresponding to the future acceleration state of the vehicle.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method steps of any of claims 1-7 when executing the program.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method steps of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210926840.5A CN115214691A (en) | 2022-08-03 | 2022-08-03 | Method and device for predicting vehicle running speed, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210926840.5A CN115214691A (en) | 2022-08-03 | 2022-08-03 | Method and device for predicting vehicle running speed, electronic device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115214691A true CN115214691A (en) | 2022-10-21 |
Family
ID=83615769
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210926840.5A Pending CN115214691A (en) | 2022-08-03 | 2022-08-03 | Method and device for predicting vehicle running speed, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115214691A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116039648A (en) * | 2023-04-03 | 2023-05-02 | 成都赛力斯科技有限公司 | Gradient calculation method and device based on weight and vehicle |
-
2022
- 2022-08-03 CN CN202210926840.5A patent/CN115214691A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116039648A (en) * | 2023-04-03 | 2023-05-02 | 成都赛力斯科技有限公司 | Gradient calculation method and device based on weight and vehicle |
| CN116039648B (en) * | 2023-04-03 | 2023-06-27 | 成都赛力斯科技有限公司 | Gradient calculation method and device based on weight and vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109624986B (en) | Driving style learning cruise control system and method based on mode switching | |
| Vatanparvar et al. | Extended range electric vehicle with driving behavior estimation in energy management | |
| Jing et al. | Vehicle speed prediction using a cooperative method of fuzzy Markov model and auto-regressive model | |
| CN107688343B (en) | Energy control method of hybrid power vehicle | |
| Zeng et al. | A stochastic driver pedal behavior model incorporating road information | |
| CN111284489B (en) | Intelligent networked automobile random prediction cruise control system | |
| CN113095558B (en) | Iterative optimization multi-scale fusion vehicle speed prediction method for intelligent networked automobile | |
| CN108960421B (en) | Improved online forecasting method for speed of unmanned surface vehicle based on BP neural network | |
| CN115742855A (en) | Electric automobile remaining mileage prediction method and device, electric automobile and medium | |
| CN112242059A (en) | Intelligent decision-making method for unmanned vehicle based on motivation and risk assessment | |
| Shin et al. | Ego-vehicle speed prediction using fuzzy Markov chain with speed constraints | |
| CN111191824B (en) | Power battery capacity attenuation prediction method and system | |
| CN112327168A (en) | XGboost-based electric vehicle battery consumption prediction method | |
| CN110615003A (en) | Cruise control system based on strategy gradient online learning algorithm and design method | |
| CN110490275A (en) | A kind of driving behavior prediction technique based on transfer learning | |
| CN115214691A (en) | Method and device for predicting vehicle running speed, electronic device and storage medium | |
| CN112977412A (en) | Vehicle control method, device and equipment and computer storage medium | |
| CN112036598A (en) | Charging pile use information prediction method based on multi-information coupling | |
| CN108734207B (en) | Method for predicting concentration of butane at bottom of debutanizer tower based on model of double-optimization semi-supervised regression algorithm | |
| Boada et al. | Neural-empirical tyre model based on recursive lazy learning under combined longitudinal and lateral slip conditions | |
| CN112035536A (en) | Electric automobile energy consumption prediction method considering dynamic road network traffic flow | |
| Hoekstra et al. | Evolving Markov chain models of driving conditions using onboard learning | |
| Chen et al. | Data-driven propulsion load profile prediction for all-electric ships | |
| CN113569460A (en) | Real vehicle fuel cell system state multi-parameter prediction method and device | |
| Natella et al. | A Q-learning approach for SoftECU design in hybrid electric vehicles |
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 |