CN112002124B - Vehicle travel energy consumption prediction method and device - Google Patents
Vehicle travel energy consumption prediction method and device Download PDFInfo
- Publication number
- CN112002124B CN112002124B CN202010699011.9A CN202010699011A CN112002124B CN 112002124 B CN112002124 B CN 112002124B CN 202010699011 A CN202010699011 A CN 202010699011A CN 112002124 B CN112002124 B CN 112002124B
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- data
- route
- vehicle
- condition data
- 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.)
- Active
Links
- 238000005265 energy consumption Methods 0.000 title claims abstract description 260
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000012549 training Methods 0.000 claims abstract description 15
- 230000006399 behavior Effects 0.000 claims description 96
- 238000010801 machine learning Methods 0.000 claims description 22
- 238000007781 pre-processing Methods 0.000 claims description 11
- 238000011084 recovery Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 9
- 238000009825 accumulation Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 238000012417 linear regression Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 7
- 238000003066 decision tree Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 4
- 230000036541 health Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- HEZMWWAKWCSUCB-PHDIDXHHSA-N (3R,4R)-3,4-dihydroxycyclohexa-1,5-diene-1-carboxylic acid Chemical compound O[C@@H]1C=CC(C(O)=O)=C[C@H]1O HEZMWWAKWCSUCB-PHDIDXHHSA-N 0.000 description 2
- 238000010923 batch production Methods 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000004378 air conditioning Methods 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 239000003638 chemical reducing agent Substances 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000009423 ventilation Methods 0.000 description 1
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
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Analytical Chemistry (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Game Theory and Decision Science (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Chemical & Material Sciences (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Traffic Control Systems (AREA)
- Navigation (AREA)
Abstract
The invention provides a method and a device for predicting vehicle travel energy consumption, wherein the method comprises the following steps: recovering route condition data of the target vehicle, and vehicle condition data, driving behavior data and energy consumption data corresponding to the route condition data; extracting and training the relation between the driving behavior data and the route condition data to establish a driving behavior prediction model; extracting and training the relation between the energy consumption data and the vehicle condition data, the route condition data and the driving behavior data to establish an energy consumption prediction model; when the target running route is selected, the route condition data of the target running route is obtained, the driving behavior prediction model is used for predicting the driving behavior of the car owner under the target running route according to the route condition data of the target running route, and then the energy consumption prediction model is used for predicting the energy consumption under the target running route according to the route condition data of the target running route and the predicted driving behavior of the car owner. Therefore, the energy consumption prediction of the vehicle journey can be accurately realized, and the user can reasonably plan the vehicle power mode.
Description
Technical Field
The invention relates to the technical field of automobiles, in particular to a method and a device for predicting vehicle travel energy consumption.
Background
With the continuous development of the electric automobile technology, a pure electric automobile or a hybrid electric automobile gradually becomes a vehicle purchasing choice for many users, and the popularization range is wider and wider.
Pure electric vehicles and hybrid vehicle all probably work under pure electric mode, possess very big customer experience and engineering development improvement meaning to accurate prediction of battery energy consumption under this power mode: the problem of mileage anxiety of the pure electric vehicle can be relieved by means of the function, and the vehicle owner is reminded to supplement electric energy in time when the electric quantity is insufficient; for the hybrid electric vehicle, the power mode of the vehicle can be reasonably planned based on the function and the navigation information, and when the electric energy is not enough to support the full journey running, the electric energy is preferentially distributed to the congested road sections, so that the optimal utilization of power energy is realized.
In the prior art, energy consumption of a certain fixed travel of an electric vehicle is calculated by adopting a traditional algorithm, namely, the energy consumption of the fixed travel is calculated and obtained according to historical travel, historical vehicle state information and corresponding travel consumed electric quantity, and a user judges whether the residual electric quantity can support the electric vehicle to travel to a destination or not according to the calculated energy consumption, so that travel arrangement is reasonably made.
However, the inventor finds that the accuracy of the travel energy consumption calculated by using the conventional algorithm is low, and the accuracy of the user for predicting whether the remaining electric quantity of the electric vehicle can reach the destination is affected.
Disclosure of Invention
The invention aims to provide a method and a device for predicting vehicle journey energy consumption, which aim to solve the problem that the vehicle journey energy consumption prediction is not accurate enough by adopting the prior art.
In order to solve the technical problem, the invention provides a method for predicting vehicle journey energy consumption, which comprises the following steps:
recovering route condition data of a target vehicle, and vehicle condition data, driving behavior data and energy consumption data corresponding to the route condition data;
extracting and training the relation between the driving behavior data and the route condition data to establish a driving behavior prediction model; extracting and training the relation among the energy consumption data, the vehicle condition data, the route condition data and the driving behavior data to establish an energy consumption prediction model;
when a target driving route is selected, obtaining route condition data of the target driving route, and predicting driving behaviors of an owner under the target driving route according to the route condition data of the target driving route by using the driving behavior prediction model; and predicting the energy consumption of the target driving route according to the route condition data of the target driving route and the predicted driving behavior of the vehicle owner by using the energy consumption prediction model.
Optionally, in the method for predicting vehicle trip energy consumption, the method for predicting vehicle trip energy consumption further includes:
the method comprises the steps of acquiring actual driving behavior data, actual vehicle condition data and actual energy consumption data of the current driving route of the target vehicle in real time, comparing the actual energy consumption data with the energy consumption data adopted when the energy consumption prediction model is established at present, updating the energy consumption prediction model according to the actual energy consumption data, the actual driving behavior data, the actual vehicle condition data and the route condition data of the current driving route if the comparison result exceeds a set threshold value, and keeping the current energy consumption prediction model if the comparison result does not exceed the set threshold value.
Optionally, in the vehicle trip energy consumption prediction method, a segmented accumulation mode is adopted when the energy consumption prediction model is used to predict the energy consumption of the target route, and the segmented accumulation mode includes:
and predicting the energy consumption of each road section according to the route condition data of each road section of the target driving route and the predicted driving behavior of the vehicle owner of each road section, and accumulating the predicted energy consumption of all the road sections of the target driving route to obtain the total energy consumption of the target route.
Optionally, in the method for predicting energy consumption of a vehicle trip, before establishing the energy consumption prediction model and the energy consumption prediction model, the method further includes:
and preprocessing the recovered route condition data, vehicle condition data, driving behavior data and energy consumption data, wherein the preprocessing comprises normalization and/or structured sorting.
Optionally, in the vehicle trip energy consumption prediction method, the energy consumption prediction model adopts a machine learning regression algorithm, and the machine learning regression algorithm includes one or more of a gaussian process regression algorithm, a decision tree regression algorithm, and a linear regression algorithm. Optionally, in the method for predicting energy consumption for vehicle journey, the route condition data includes: ambient weather data, road condition data, and route traffic data.
In order to solve the above problem, the present invention further provides a vehicle trip energy consumption prediction apparatus, including: the system comprises a data recovery module, a machine learning module and a driving behavior and energy consumption prediction module; wherein,
the data recovery module is used for recovering route condition data of a target vehicle, and vehicle condition data, driving behavior data and energy consumption data corresponding to the route condition data; and obtaining route condition data of the target driving route when the target driving route is selected;
the machine learning module is used for extracting and training the relation between the driving behavior data and the route condition data so as to establish a driving behavior prediction model; extracting and training the relation among the energy consumption data, the vehicle condition data, the route condition data and the driving behavior data to establish an energy consumption prediction model;
the driving behavior and energy consumption prediction module is used for predicting the driving behavior of the vehicle owner under the target driving route according to the route condition data of the target driving route by using the driving behavior prediction model; and predicting the energy consumption of the target driving route according to the route condition data of the target driving route and the predicted driving behavior of the vehicle owner by using the energy consumption prediction model.
Optionally, in the vehicle journey energy consumption prediction apparatus, the data recovery module is further configured to obtain actual driving behavior data, actual vehicle condition data, and actual energy consumption data of the current driving route of the target vehicle in real time, compare the actual energy consumption data with the energy consumption data adopted when the energy consumption prediction model is established at present, update the energy consumption prediction model according to the actual energy consumption data, the actual driving behavior data, the actual vehicle condition data, and the route condition data of the current driving route if a comparison result exceeds a set threshold, and keep the current energy consumption prediction model if the comparison result does not exceed the set threshold.
Optionally, in the vehicle trip energy consumption prediction apparatus, the vehicle trip energy consumption prediction apparatus further includes a data processing module, and the data processing module is further configured to perform preprocessing on the recovered route condition data, vehicle condition data, driving behavior data, and energy consumption data before the energy consumption prediction model and the energy consumption prediction model are established, where the preprocessing includes normalization and/or structured sorting.
Optionally, in the vehicle trip energy consumption prediction apparatus, the energy consumption prediction model adopts a machine learning regression algorithm, and the machine learning regression algorithm includes one or more of a gaussian process regression algorithm, a decision tree regression algorithm, and a linear regression algorithm. Optionally, in the vehicle trip energy consumption prediction apparatus, the route condition data includes: ambient weather data, road condition data, and route traffic data.
Optionally, in the vehicle trip energy consumption prediction apparatus, the vehicle trip energy consumption prediction apparatus further includes a human-machine interface module, and the human-machine interface module is configured to provide the route condition data and is configured to display the predicted energy consumption of the target driving route.
Compared with the prior art, the method and the device for predicting the vehicle journey energy consumption have the following advantages:
(1) when a vehicle travel energy consumption model is established, the relationship between the energy consumption data and the vehicle condition data, the relationship between the energy consumption data and the route condition data as well as the relationship between the energy consumption data and the driving behavior data are extracted and trained, so that when the vehicle travel energy consumption is predicted by using the vehicle travel energy consumption model, the predicted result not only considers the factors of the vehicle condition, but also considers the driving behavior factors and the influence factors of the route condition factors on the vehicle travel energy consumption, and the travel energy consumption prediction result is more accurate;
(2) extracting and training the relation between the driving behavior data and the route condition data, and establishing a driving behavior prediction model, so that when a target driving route is selected, the driving behavior prediction model can be used for predicting the driving behavior of an owner under the target driving route according to the route condition data of the target driving route, and the prediction result provides a practical basis for predicting the energy consumption of the vehicle route, so that the prediction of the energy consumption of the route can be realized through the established vehicle route energy consumption model;
(3) furthermore, the invention provides a vehicle journey energy consumption prediction method and a vehicle journey energy consumption prediction device, wherein a later compensation iteration scheme is designed, actual driving behavior data, actual vehicle condition data and actual energy consumption data of the current driving route of the target vehicle are obtained in real time, the actual energy consumption data are compared with the energy consumption data adopted when the current energy consumption prediction model is established, if the comparison result exceeds a set threshold value, the energy consumption prediction model is updated according to the actual energy consumption data, the actual driving behavior data, the actual vehicle condition data and the route condition data of the current driving route, and if the comparison result does not exceed the set threshold value, the current energy consumption prediction model is kept; thus, different energy consumption prediction data models are applied for vehicles in different engine phases: for vehicles which are just produced in batches, the data accumulation is insufficient, the actual energy consumption of the vehicles is tested through a data statistics method, or the energy consumption characteristic expression of the same type of batch vehicles is referred, a real energy consumption prediction model under a typical driving style and road traffic is established, and the energy consumption expression of the vehicles is predicted by taking the real energy consumption prediction model as a default model; for vehicles which accumulate certain energy consumption monitoring data after batch production, key characteristic data of all influence factors and actual performance of real energy consumption are extracted through continuous monitoring of driving styles, road traffic, vehicle health and real energy consumption, continuous optimization and upgrade iteration of accuracy of an energy consumption prediction model are achieved, and consumption of the energy consumption prediction model on computing resources is reduced.
(4) Furthermore, in the vehicle journey energy consumption prediction method and device provided by the invention, the vehicle journey energy consumption model adopts a linear regression algorithm or a Gaussian process regression algorithm, so that the interpretability is better, the robustness and compatibility of the model are higher, and the engineering implementation is easier.
Drawings
FIG. 1 is a flow chart of a method for predicting energy consumption for a vehicle trip, according to an embodiment of the present invention;
FIG. 2 is a block diagram of a vehicle trip energy consumption prediction apparatus according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an implementation of the method and apparatus for predicting energy consumption for vehicle journey according to the embodiment of the invention;
fig. 4 is a schematic diagram of another implementation of the method and the apparatus for predicting energy consumption of vehicle journey according to the embodiment of the invention;
wherein the reference numerals are as follows:
100-a data recovery module; 200-a machine learning module; 300-driving behavior and energy consumption prediction module; 400-a data processing module; 500-human interface module.
Detailed Description
The following describes the vehicle trip energy consumption prediction method and apparatus in further detail with reference to the accompanying drawings and specific embodiments. The advantages and features of the present invention will become more apparent from the following description. It is to be noted that the drawings are in a very simplified form and are not to precise scale, which is merely for the purpose of facilitating and distinctly claiming the embodiments of the present invention. Further, the structures illustrated in the drawings are often part of actual structures. In particular, the drawings may have different emphasis points and may sometimes be scaled differently.
As shown in fig. 1, the present embodiment provides a method for predicting energy consumption of a vehicle trip, including the following steps:
s11, recovering the route condition data of the target vehicle, and vehicle condition data, driving behavior data and energy consumption data corresponding to the route condition data;
s12, extracting and training the relation between the driving behavior data and the route condition data to establish a driving behavior prediction model; extracting and training the relation among the energy consumption data, the vehicle condition data, the route condition data and the driving behavior data to establish an energy consumption prediction model;
s13, when a target driving route is selected, obtaining route condition data of the target driving route, and predicting the driving behavior of an owner under the target driving route according to the route condition data of the target driving route by using the driving behavior prediction model; and predicting the energy consumption of the target driving route according to the route condition data of the target driving route and the predicted driving behavior of the vehicle owner by using the energy consumption prediction model.
As can be seen from the above steps, when the vehicle journey energy consumption prediction method provided by this embodiment is used for building the vehicle journey energy consumption model, the relationships between the energy consumption data and the vehicle condition data, the route condition data, and the driving behavior data are extracted and trained, so that when the vehicle journey energy consumption is predicted by using the vehicle journey energy consumption model, the prediction result not only takes into account the factors of the vehicle condition, but also takes into account the driving behavior factors and the influence factors of the route condition factors on the vehicle journey energy consumption, and therefore, the journey energy consumption prediction result is more accurate. In addition, a driving behavior prediction model is established by extracting and training the relation between the driving behavior data and the route condition data, so that when a target driving route is selected, the driving behavior prediction model can be used for predicting the driving behavior of the vehicle owner under the target driving route according to the route condition data of the target driving route, the prediction result provides a practical basis for predicting the energy consumption of the vehicle route, and the prediction of the route energy consumption can be realized through the established vehicle route energy consumption model.
The above steps are described in detail below.
First, step S11 is executed to recover route condition data, including, in this embodiment, ambient weather data, road condition data, and route traffic data, vehicle condition data, driving behavior data, and energy consumption data. Wherein, each data is as follows:
the vehicle condition data mainly comprises the health state of an electric drive system, such as the state of battery SOH (state of health), the efficiency of a motor and a speed reducer, the energy consumption of two ends of high voltage/low voltage of DCDC and other information;
the environmental weather data mainly comprises data such as external environmental temperature, rain and snow states and the like, and the related data can influence the temperature discharge performance on one hand and the operation of an automobile owner on an HVAC (Heating, Ventilation and Air Conditioning) system so as to influence the electric energy demand;
road conditions mainly comprise road gradient and the like, and relevant data have great influence on the relation between the vehicle speed and the working condition of the engine;
the route traffic mainly comprises a route congestion state, a speed limit, the number of traffic lights, vehicle steering requirements and the like, and related data can influence the magnitude of vehicle speed and further influence the working condition of the power assembly;
driving data, including accelerator/brake pedal operation, wiper, window, HVAC and other equipment operation data, and also setting data such as ACC (adaptive cruise control system) cruise, power mode setting (hybrid vehicle) and the like;
the actual energy consumption includes data such as battery SOC (state of charge), short-time power of the motor, short-time power of the DCDC, short-time power of components such as an air conditioner compressor, PTC (Positive Temperature Coefficient), and seat heating device. The instantaneous energy consumption of the vehicle for various purposes such as power output, component driving and the like can be directly extracted or indirectly calculated by analyzing based on the related data.
After the above data recovery is completed, step S12 is executed to build a driving behavior prediction model and an energy consumption prediction model by using the recovered data through a machine learning method.
Before executing step S12, the recovered route condition data, vehicle condition data, driving behavior data and energy consumption data are preferably preprocessed, wherein the preprocessing includes normalization and/or structured sorting. Because the data contents of environmental weather, vehicle conditions, roads, traffic and the like are various and the data contents are different according to different sources, normalization and structuring processing is firstly carried out before machine learning is carried out, and the usability of a machine learning algorithm can be ensured.
After the driving behavior prediction model and the energy consumption prediction model are established, step S13 is executed, the two models are applied, when the vehicle prepares to run, the vehicle owner inputs the position information of the starting point and the destination to the map server, the map server provides the target driving route and provides the route condition data of the target driving route, so that the driving behavior prediction model can be used to predict the driving behavior of the vehicle owner under the target driving route according to the route condition data of the target driving route, and the energy consumption prediction model is used to predict the energy consumption under the target driving route according to the route condition data of the target driving route and the predicted driving behavior of the vehicle owner.
In this embodiment, when the energy consumption prediction model is used to predict the energy consumption of the target route, a segmented accumulation mode may be adopted, where the segmented accumulation mode includes: and predicting the energy consumption of each road section according to the route condition data of each road section of the target driving route and the predicted driving behavior of the vehicle owner of each road section, and accumulating the predicted energy consumption of all the road sections of the target driving route to obtain the total energy consumption of the target route.
Preferably, the vehicle trip energy consumption prediction method provided by this embodiment further includes: the method comprises the steps of acquiring actual driving behavior data, actual vehicle condition data and actual energy consumption data of the current driving route of the target vehicle in real time, comparing the actual energy consumption data with the energy consumption data adopted when the energy consumption prediction model is established at present, updating the energy consumption prediction model according to the actual energy consumption data, the actual driving behavior data, the actual vehicle condition data and the route condition data of the current driving route if the comparison result exceeds a set threshold value, and keeping the current energy consumption prediction model if the comparison result does not exceed the set threshold value.
Namely, the vehicle journey energy consumption prediction method provided by the embodiment designs a late compensation iteration scheme. For vehicles which are just produced in batches, the data accumulation is insufficient, the actual energy consumption of the vehicles is tested through a data statistics method, or the energy consumption characteristic expression of the same type of batch vehicles is referred, a real energy consumption prediction model under a typical driving style and road traffic is established, and the energy consumption expression of the vehicles is predicted by taking the real energy consumption prediction model as a default model; for vehicles which accumulate certain energy consumption monitoring data after batch production, key characteristic data of all influence factors and actual performance of real energy consumption are extracted through continuous monitoring of driving styles, road traffic, vehicle health and real energy consumption, continuous optimization and upgrade iteration of accuracy of an energy consumption prediction model are achieved, and consumption of the energy consumption prediction model on computing resources is reduced.
Based on the same idea, as shown in fig. 2, the present embodiment further provides a vehicle trip energy consumption prediction apparatus, including: a data recovery module 100, a machine learning module 200, and a driving behavior and energy consumption prediction module 300.
The data recovery module 100 is configured to recover route condition data of a target vehicle, and vehicle condition data, driving behavior data, and energy consumption data corresponding to the route condition data; and acquiring the route condition data of the target driving route when the target driving route is selected. In this embodiment, the route condition data includes: ambient weather data, road condition data, and route traffic data. Each data is already described in detail in the vehicle trip energy consumption prediction method section, and is not described herein again.
The machine learning module 200 is configured to extract and train a relationship between the driving behavior data and the route condition data to establish a driving behavior prediction model; and extracting and training the relation among the energy consumption data, the vehicle condition data, the route condition data and the driving behavior data to establish an energy consumption prediction model.
The driving behavior and energy consumption prediction module 300 is configured to predict a driving behavior of the vehicle owner under the target driving route according to the route condition data of the target driving route by using the driving behavior prediction model; and predicting the energy consumption of the target driving route according to the route condition data of the target driving route and the predicted driving behavior of the vehicle owner by using the energy consumption prediction model.
Corresponding to the vehicle trip energy consumption prediction method provided in this embodiment, in the vehicle trip energy consumption prediction apparatus provided in this embodiment, preferably, the data recovery module 100 is further configured to obtain actual driving behavior data, actual vehicle condition data, and actual energy consumption data of the current driving route of the target vehicle in real time, compare the actual energy consumption data with the energy consumption data adopted when the energy consumption prediction model is currently established, update the energy consumption prediction model according to the actual energy consumption data, the actual driving behavior data, the actual vehicle condition data, and the route condition data of the current driving route if a comparison result exceeds a set threshold, and keep the current energy consumption prediction model if the comparison result does not exceed the set threshold. Preferably, the vehicle trip energy consumption prediction apparatus further includes a data processing module 400, and the data processing module 400 is further configured to perform preprocessing on the recovered route condition data, vehicle condition data, driving behavior data and energy consumption data before establishing the energy consumption prediction model and the energy consumption prediction model, where the preprocessing includes normalization and/or structured sorting.
The vehicle journey energy consumption prediction device provided by the embodiment further comprises a human-machine interface module 500, wherein the human-machine interface module 500 is used for providing the route condition data and displaying the predicted energy consumption under the target driving route. Thus, the user can perform reasonable routing according to the energy consumption information displayed by the human-computer interface module 500.
In addition, in the method and the device for predicting vehicle trip energy consumption provided by this embodiment, the driving behavior prediction model preferentially adopts a lazy learning algorithm (such as a KNN algorithm, etc.), establishes a model based on the driving operation data in the scene of combining various input parameters in the recently set driving time window, and predicts the driving operation behavior based on the model; the energy consumption prediction model preferentially adopts a machine learning regression algorithm, the machine learning regression algorithm comprises one or more of a Gaussian process regression algorithm, a decision tree regression algorithm and a linear regression algorithm, so that the interpretability of the model is ensured, the requirement on computing resources is reduced, the robustness and compatibility of the model are higher, and the engineering implementation is easier. In other embodiments, other machine learning regression algorithms are also used in the energy consumption prediction model.
For convenience of description, the above vehicle trip energy consumption prediction apparatus is described as being divided into various modules by functions, and described separately. Of course, the functionality of the various modules may be implemented in the same one or more software and/or hardware implementations of the invention.
Several exemplary implementations are provided below.
Example one: as shown in fig. 3, a vehicle-mounted controller VCU (including a powertrain controller, a vehicle body controller, etc.) collects data contents such as vehicle condition data, driving behavior data, energy consumption data, etc., and an HMI system (which may include an instrument, a vehicle machine, etc., and generally refers to a component capable of performing human-computer interaction) provides information such as environmental weather, road conditions, route traffic, etc., and uploads the information to a cloud platform through a wireless communication module. The cloud platform is responsible for data preprocessing, machine learning, data storage, driving behavior and energy consumption prediction functions, and feeds back energy consumption prediction results to the HMI system terminal through the communication module for the vehicle owner to use.
Example two: for a system of vehicle configuration XCU (domain controller) and cloud service, since a vehicle deploys strong computing resources locally, an energy consumption prediction model with high real-time computing demand can be deployed locally to the XCU, and a machine learning algorithm suitable for cloud computing is deployed to a cloud platform, as shown in fig. 4. According to the scheme, the HMI system and the VCU directly transmit related data to the XCU, and the data is uploaded to the cloud platform after data preprocessing is completed in the XCU; after the cloud platform completes the development of machine learning models of a driving behavior prediction model and an energy consumption prediction model, relevant application models are issued and deployed to an XCU; the XCU completes the acquisition of driving behavior and energy consumption prediction result data based on the preprocessed input data, and provides the relevant result data for an HMI system, a VCU and the like for use.
The implementation provides the functions of each functional module of the vehicle journey energy consumption prediction device, which are realized by the corresponding hardware of the first example and the second example, and the functions correspond to each other. In addition, in the first and second examples, the communication module mainly refers to a data connection module between the vehicle and the cloud, and the vehicle-mounted controller for the internal communication of the vehicle sound controller does not belong to the category. The communication module can be a vehicle machine with built-in 3G/4G/5G function, a Tbox or an intelligent gateway and other parts.
It should be noted that, regarding the road information, for a system using a high-precision map or a navigation map integrated with ADASIS, the gradient information can be directly read from the navigation data, and there is related information to better establish a prediction model between the road information and the vehicle condition information. For road conditions which cannot provide gradient information, the relevance between the road conditions and the actual energy consumption can be established, and the difference between the influence of each road section on the actual energy consumption and the conventional non-gradient road is identified and marked at the cloud end, so that the energy consumption prediction precision is optimized through vehicles. When the energy consumption prediction device provided by the invention is just deployed, if the gradient information cannot be acquired, the vehicle can be assumed to run on a non-gradient road. At the moment, the vehicle electric driving system is in a new delivery state, the energy consumption influence relation of the road where the vehicle electric driving system passes is calculated based on the real energy consumption expression of the road where the vehicle electric driving system passes and the actual energy consumption index of the vehicle, and the prediction precision of a follow-up model is optimized based on relevant information.
In conclusion, the vehicle journey energy consumption prediction method and the vehicle journey energy consumption prediction device provided by the invention solve the problem that the vehicle journey energy consumption prediction is not accurate enough by adopting the prior art, influence of factors such as driving style, vehicle aging and ambient temperature is considered in the aspect of energy consumption influence factors, a later compensation iteration scheme is designed, and the adopted linear regression or Gaussian process regression algorithm has better interpretability, so that the robustness and compatibility of a prediction model are higher, and the engineering implementation is easier.
The above description is only for the purpose of describing the preferred embodiments of the present invention, and is not intended to limit the scope of the present invention, and any variations and modifications made by those skilled in the art based on the above disclosure are within the scope of the appended claims.
Claims (12)
1. A method for predicting energy consumption for a vehicle trip, comprising:
recovering route condition data of a target vehicle, and vehicle condition data, driving behavior data and energy consumption data corresponding to the route condition data;
extracting and training the relation between the driving behavior data and the route condition data to establish a driving behavior prediction model; extracting and training the relation among the energy consumption data, the vehicle condition data, the route condition data and the driving behavior data to establish an energy consumption prediction model;
when a target driving route is selected, obtaining route condition data of the target driving route, and predicting driving behaviors of an owner under the target driving route according to the route condition data of the target driving route by using the driving behavior prediction model; and predicting the energy consumption of the target driving route by using the energy consumption prediction model according to the route condition data of the target driving route and the predicted driving behavior of the vehicle owner.
2. The vehicle trip energy consumption prediction method of claim 1, further comprising:
the method comprises the steps of acquiring actual driving behavior data, actual vehicle condition data and actual energy consumption data of the current driving route of the target vehicle in real time, comparing the actual energy consumption data with the energy consumption data adopted when the energy consumption prediction model is established at present, updating the energy consumption prediction model according to the actual energy consumption data, the actual driving behavior data, the actual vehicle condition data and the route condition data of the current driving route if the comparison result exceeds a set threshold value, and keeping the current energy consumption prediction model if the comparison result does not exceed the set threshold value.
3. The vehicle trip energy consumption prediction method of claim 1, wherein the energy consumption prediction model is used for predicting the energy consumption of the target route by means of segment accumulation, and the segment accumulation comprises:
and predicting the energy consumption of each road section according to the route condition data of each road section of the target driving route and the predicted driving behavior of the vehicle owner of each road section, and accumulating the predicted energy consumption of all the road sections of the target driving route to obtain the total energy consumption of the target route.
4. The vehicle trip energy consumption prediction method of claim 1, further comprising, prior to establishing the energy consumption prediction model and the energy consumption prediction model:
and preprocessing the recovered route condition data, vehicle condition data, driving behavior data and energy consumption data, wherein the preprocessing comprises normalization and/or structured sorting.
5. The vehicle trip energy consumption prediction method of claim 1, wherein the energy consumption prediction model employs a machine learning regression algorithm including one or more of a gaussian process regression algorithm, a decision tree regression algorithm, and a linear regression algorithm.
6. The vehicle trip energy consumption prediction method of claim 1, wherein the route condition data comprises: ambient weather data, road condition data, and route traffic data.
7. A vehicle trip energy consumption prediction apparatus, comprising: the system comprises a data recovery module, a machine learning module and a driving behavior and energy consumption prediction module; wherein,
the data recovery module is used for recovering route condition data of a target vehicle, and vehicle condition data, driving behavior data and energy consumption data corresponding to the route condition data; and obtaining route condition data of the target driving route when the target driving route is selected;
the machine learning module is used for extracting and training the relation between the driving behavior data and the route condition data so as to establish a driving behavior prediction model; extracting and training the relation among the energy consumption data, the vehicle condition data, the route condition data and the driving behavior data to establish an energy consumption prediction model;
the driving behavior and energy consumption prediction module is used for predicting the driving behavior of the vehicle owner under the target driving route according to the route condition data of the target driving route by using the driving behavior prediction model; and predicting the energy consumption of the target driving route according to the route condition data of the target driving route and the predicted driving behavior of the vehicle owner by using the energy consumption prediction model.
8. The vehicle trip energy consumption prediction device according to claim 7, wherein the data recovery module is further configured to obtain actual driving behavior data, actual vehicle condition data, and actual energy consumption data of the current driving route of the target vehicle in real time, compare the actual energy consumption data with the energy consumption data adopted when the energy consumption prediction model is currently established, update the energy consumption prediction model according to the actual energy consumption data, the actual driving behavior data, the actual vehicle condition data, and the route condition data of the current driving route if a comparison result exceeds a set threshold, and keep the current energy consumption prediction model if the comparison result does not exceed the set threshold.
9. The vehicle trip energy consumption prediction device according to claim 7, further comprising a data processing module, wherein the data processing module is further configured to pre-process the recovered route condition data, vehicle condition data, driving behavior data and energy consumption data before establishing the energy consumption prediction model and the energy consumption prediction model, and the pre-process comprises a normalization and/or a structured arrangement.
10. The vehicle trip energy consumption prediction device of claim 7, wherein the energy consumption prediction model employs a machine learning regression algorithm including one or more of a gaussian process regression algorithm, a decision tree regression algorithm, and a linear regression algorithm.
11. The vehicle trip energy consumption prediction device of claim 7, wherein the route condition data comprises: ambient weather data, road condition data, and route traffic data.
12. The vehicle trip energy consumption prediction apparatus of claim 7, further comprising a human machine interface module for providing the route condition data and for displaying the predicted amount of energy consumption for the target travel route.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010699011.9A CN112002124B (en) | 2020-07-20 | 2020-07-20 | Vehicle travel energy consumption prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010699011.9A CN112002124B (en) | 2020-07-20 | 2020-07-20 | Vehicle travel energy consumption prediction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112002124A CN112002124A (en) | 2020-11-27 |
| CN112002124B true CN112002124B (en) | 2022-07-01 |
Family
ID=73468228
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010699011.9A Active CN112002124B (en) | 2020-07-20 | 2020-07-20 | Vehicle travel energy consumption prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112002124B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111891130B (en) * | 2020-07-27 | 2021-10-15 | 吉利汽车研究院（宁波）有限公司 | Vehicle running method and device |
| WO2022178654A1 (en) * | 2021-02-23 | 2022-09-01 | 浙江吉利控股集团有限公司 | Driving method for hybrid vehicle, system, and hybrid vehicle |
| CN113071497B (en) * | 2021-04-28 | 2022-05-24 | 中国第一汽车股份有限公司 | Driving scene judging method, device, equipment and storage medium |
| CN113428159A (en) * | 2021-05-28 | 2021-09-24 | 合肥国轩高科动力能源有限公司 | Vehicle energy consumption analysis method |
| CN113869580A (en) * | 2021-09-27 | 2021-12-31 | 广州远正智能科技股份有限公司 | Energy consumption parameter prediction tracking method and system and computer readable storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109740213A (en) * | 2018-12-24 | 2019-05-10 | 斑马网络技术有限公司 | Energy consumption of vehicles appraisal procedure, equipment and storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2136182B1 (en) * | 2008-06-19 | 2016-10-12 | Harman Becker Automotive Systems GmbH | Calculation of energy optimised route |
| TWI591492B (en) * | 2016-12-19 | 2017-07-11 | Chunghwa Telecom Co Ltd | Energy consumption estimation system and method |
| CN109141459A (en) * | 2018-09-28 | 2019-01-04 | 吉林大学 | A kind of electric car navigation system and method with Analysis of Electricity prediction |
| CN110126841B (en) * | 2019-05-09 | 2020-08-04 | 吉林大学 | Pure electric vehicle energy consumption model prediction method based on road information and driving style |
| CN110610260B (en) * | 2019-08-21 | 2023-04-18 | 南京航空航天大学 | Driving energy consumption prediction system, method, storage medium and equipment |
| CN110705774A (en) * | 2019-09-26 | 2020-01-17 | 汉纳森（厦门）数据股份有限公司 | Vehicle energy consumption analysis prediction method and system |
-
2020
- 2020-07-20 CN CN202010699011.9A patent/CN112002124B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109740213A (en) * | 2018-12-24 | 2019-05-10 | 斑马网络技术有限公司 | Energy consumption of vehicles appraisal procedure, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112002124A (en) | 2020-11-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112002124B (en) | Vehicle travel energy consumption prediction method and device | |
| WO2022236751A1 (en) | Battery state of charge estimation method and device | |
| CN109927709B (en) | Vehicle driving route working condition determining method, energy management method and system | |
| CN107791854B (en) | System and method for estimating available travel distance of electric vehicle | |
| CN111806240B (en) | China working condition-based electric automobile driving range prediction method | |
| KR101500362B1 (en) | System and method for providing driving information of electric vehicle | |
| CN111497624B (en) | Method and device for determining remaining mileage of vehicle and vehicle | |
| CN111483322B (en) | Method and device for determining remaining mileage of vehicle and vehicle | |
| CN103914985A (en) | Method for predicting future speed trajectory of hybrid power bus | |
| CN112824196A (en) | Driver model estimation, classification, and adaptation for range prediction | |
| US10801848B2 (en) | Crowd sourcing to predict vehicle energy consumption | |
| CN110103773A (en) | A kind of electric car continual mileage prediction technique and system | |
| WO2017047171A1 (en) | Traveling plan generation apparatus, vehicle, traveling plan generation system, and computer program | |
| Ferreira et al. | Data mining approach for range prediction of electric vehicle | |
| CN113415288B (en) | Sectional type longitudinal vehicle speed planning method, device, equipment and storage medium | |
| CN112406875B (en) | Vehicle energy consumption analysis method and device | |
| DE102015226229A1 (en) | Method and device for range calculation for a vehicle | |
| CN115140046A (en) | Vehicle control method and system, vehicle controller and cloud server | |
| CN113335126B (en) | Intelligent charging control method for new energy automobile, storage medium and electronic equipment | |
| WO2022062569A1 (en) | Vehicle energy consumption scoring method and device | |
| CN114025985A (en) | System and method for controlling energy consumption in a vehicle | |
| US20240053161A1 (en) | Method for Predicting a Velocity Profile of a Vehicle | |
| CN115688957A (en) | Vehicle energy consumption determination method and device, electronic equipment and storage medium | |
| CN115056778A (en) | Apparatus and method for determining available regenerative braking energy in a vehicle route | |
| CN114274840B (en) | Intelligent internet electric vehicle electric quantity consumption prediction method and system based on S-CRANN |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |