WO2020211456A1 - 电动车辆续航里程测量方法、电子设备及存储介质 - Google Patents

电动车辆续航里程测量方法、电子设备及存储介质 Download PDF

Info

Publication number
WO2020211456A1
WO2020211456A1 PCT/CN2019/129471 CN2019129471W WO2020211456A1 WO 2020211456 A1 WO2020211456 A1 WO 2020211456A1 CN 2019129471 W CN2019129471 W CN 2019129471W WO 2020211456 A1 WO2020211456 A1 WO 2020211456A1
Authority
WO
WIPO (PCT)
Prior art keywords
historical
data
electric vehicle
cruising range
driving data
Prior art date
Application number
PCT/CN2019/129471
Other languages
English (en)
French (fr)
Inventor
陈旋
李敏
王瑜
孟格思
Original Assignee
北京嘀嘀无限科技发展有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京嘀嘀无限科技发展有限公司 filed Critical 北京嘀嘀无限科技发展有限公司
Publication of WO2020211456A1 publication Critical patent/WO2020211456A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
    • B60L3/00—Electric devices on electrically-propelled vehicles for safety purposes; Monitoring operating variables, e.g. speed, deceleration or energy consumption
    • B60L3/12—Recording operating variables ; Monitoring of operating variables
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
    • B60L50/00—Electric propulsion with power supplied within the vehicle
    • B60L50/50—Electric propulsion with power supplied within the vehicle using propulsion power supplied by batteries or fuel cells
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition
    • G06V30/19—Recognition using electronic means
    • G06V30/192—Recognition using electronic means using simultaneous comparisons or correlations of the image signals with a plurality of references
    • G06V30/194—References adjustable by an adaptive method, e.g. learning
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
    • B60L2260/00—Operating Modes
    • B60L2260/40—Control modes
    • B60L2260/50—Control modes by future state prediction
    • B60L2260/52—Control modes by future state prediction drive range estimation, e.g. of estimation of available travel distance
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/60—Other road transportation technologies with climate change mitigation effect
    • Y02T10/70—Energy storage systems for electromobility, e.g. batteries

Definitions

  • the present invention relates to the technical field related to electric vehicles, in particular to a method for measuring the cruising range of electric vehicles, electronic equipment and storage media.
  • the inaccurate cruising range of electric vehicles mainly includes two scenarios: one is the situation where the cruising range of the vehicle viewed by the user through the APP before the vehicle is ignited is inconsistent with the cruising range displayed on the instrument after the ignition; the other is that the vehicle is only driving after the ignition It is 2km, but the cruising range displayed on the dashboard is 5km less.
  • the current method is to multiply the estimated remaining mileage by the attenuation factor, but it is not accurate.
  • the present invention provides a method for measuring the cruising range of an electric vehicle, including:
  • the historical driving data is used as the input object, and the historical cruising range is used as the supervised object to train and generate a prediction model.
  • the input of the prediction model is the current driving data, and the output of the prediction model is the estimated cruising range ;
  • the acquiring historical driving data of the electric vehicle and the historical cruising range corresponding to the historical driving data specifically includes:
  • the historical driving data of the electric vehicle is acquired. For any historical remaining power, the actual mileage of the electric vehicle after the historical remaining power and before the battery power reaches the preset power value is acquired as the historical cruising range corresponding to the historical remaining power.
  • the driving data further includes at least one state data
  • the current driving data includes the current remaining power of the electric vehicle and current state data
  • the historical driving data includes historical remaining power and corresponding historical state data.
  • the acquiring historical driving data of the electric vehicle and the historical cruising range corresponding to the historical driving data specifically includes:
  • the comprehensive value of the state data is: the average value or weighted value of the same state data after the historical remaining power to before the battery power reaches the preset power value.
  • the state data includes: vehicle speed data, body quality data, battery temperature data, environmental data, road data, driving habits data, battery life data, battery aging data, and/or Battery discharge rate data.
  • the road data includes a road condition index and/or a congestion index.
  • the driving habit data includes: a driving habit index generated according to the number of sudden stops, the number of sudden starts, the number of sharp turns, and/or the average speed.
  • the above-mentioned method for measuring the cruising range of an electric vehicle also includes:
  • the invention also provides an electronic device for measuring the cruising range of an electric vehicle, including:
  • At least one processor and,
  • a memory communicatively connected with the at least one processor; wherein,
  • the memory stores instructions executable by the one processor, and the instructions are executed by the at least one processor so that the at least one processor can:
  • the historical driving data is used as the input object, and the historical cruising range is used as the supervised object to train and generate a prediction model.
  • the input of the prediction model is the current driving data, and the output of the prediction model is the estimated cruising range ;
  • the acquiring historical driving data of the electric vehicle and the historical cruising range corresponding to the historical driving data specifically includes:
  • the historical driving data of the electric vehicle is acquired. For any historical remaining power, the actual mileage of the electric vehicle after the historical remaining power and before the battery power reaches the preset power value is acquired as the historical cruising range corresponding to the historical remaining power.
  • the driving data further includes at least one state data
  • the current driving data includes the current remaining power of the electric vehicle and current state data
  • the historical driving data includes historical remaining power and corresponding historical state data.
  • the acquiring historical driving data of the electric vehicle and the historical cruising range corresponding to the historical driving data specifically includes:
  • the comprehensive value of the state data is: the average or weighted value of the same state data after the historical remaining power to before the battery power reaches the preset power value.
  • the state data includes: vehicle speed data, body quality data, battery temperature data, environmental data, road data, driving habits data, battery life data, battery aging data, and / Or battery discharge rate data.
  • the road data includes a road condition index and/or a congestion index.
  • the driving habit data includes: a driving habit index generated according to the number of sudden stops, the number of sudden starts, the number of sharp turns, and/or the average speed.
  • the processor can also:
  • the present invention also provides a storage medium that stores computer instructions, and when the computer executes the computer instructions, it is used to execute all the steps of the aforementioned method for measuring the cruising range of an electric vehicle.
  • the method for measuring the cruising range of the electric vehicle, the electronic equipment and the storage medium provided by the present invention can obtain a more accurate remaining range of the electric vehicle by training the prediction model and predicting the cruising range based on the driving data of the electric vehicle. It can improve the accuracy of the cruising range display, thereby improving the user experience.
  • Fig. 1 shows a flowchart of an embodiment of the method for measuring the cruising range of an electric vehicle provided by the present invention.
  • Fig. 2 shows a flowchart of another embodiment of the method for measuring the cruising range of an electric vehicle provided by the present invention.
  • Fig. 3 shows a flowchart of another embodiment of the method for measuring the cruising range of an electric vehicle provided by the present invention.
  • FIG. 4 shows a schematic diagram of the hardware structure of the electronic device for measuring the cruising range of an electric vehicle provided by the present invention.
  • Figure 1 shows a working flow chart of a method for measuring the cruising range of an electric vehicle according to an embodiment of the present invention, including:
  • Step S101 Obtain historical driving data of an electric vehicle and historical cruising range corresponding to the historical driving data, where the driving data includes at least the remaining power of the electric vehicle;
  • Step S102 using the historical driving data as the input object and the historical cruising range as the supervising object, train to generate an estimation model, the input of the estimation model is the current driving data, and the output of the estimation model is the forecast Estimated mileage;
  • Step S103 acquiring current driving data of the electric vehicle
  • Step S104 input the current driving data into a trained estimation model, and obtain the estimated cruising range on the current driving data from the estimation model;
  • Step S105 displaying the estimated cruising range.
  • step S101 and step S102 historical driving data and historical cruising range are used for supervised learning training, so as to generate an estimation model.
  • the driving data can be recorded by the vehicle's on-board T-BOX hardware system at regular intervals (for example, at intervals of 5 seconds, 1 minute) to obtain historical driving data.
  • Telematics BOX referred to as on-board T-BOX.
  • the existing car networking system consists of four parts: the host, the car T-BOX, mobile phone applications and the background system. Among them, the vehicle-mounted T-BOX is mainly used to communicate with the background system or mobile phone applications.
  • the vehicle-mounted T-BOX can record and obtain various driving data of the vehicle.
  • step S103 the current driving data of the electric vehicle is obtained, and then the current driving data is input to the estimation model in step S102, and the estimated cruising range of the current driving data is obtained as a feedback from the estimation model. . And displayed in step S105.
  • the model used in supervised learning training can be implemented by using various existing models.
  • x is the input parameter vector, which can include one or more driving data.
  • y is the object of supervision during training, that is, the historical cruising range, and in step S104, it is the function output value, which is the estimated cruising range.
  • the data can be preprocessed. Since the amount of data is large enough, it is possible to filter out the points with large deviations in the cruising range under a certain power based on the historical driving data of each vehicle. This step is to ensure as much accuracy as possible for the subsequent data used as training samples.
  • a reference value for example, an average value
  • the user shows that the remaining power is 60% before picking up the car, and the remaining mileage is 60km. After picking up the car, it is displayed as 30km, then the remaining mileage of 60km is unreasonable and can be filtered out; or, after the actual driving is 10km If the remaining mileage is 30km, the unreasonable points can be filtered out if the remaining mileage is 60km.
  • the invention trains the estimation model and estimates the cruising range based on the driving data of the electric vehicle to obtain a more accurate remaining range of the electric vehicle, thereby improving the accuracy of the cruising range display, thereby improving user experience.
  • Fig. 2 shows a working flowchart of a method for measuring the cruising range of an electric vehicle according to an optional embodiment of the present invention, including:
  • Step S201 Obtain historical driving data of the electric vehicle, where the driving data includes at least the remaining power of the electric vehicle and at least one state data.
  • Step S202 For any historical remaining power, obtain the actual mileage of the electric vehicle after the historical remaining power to before the battery power reaches the preset power value as the historical cruising range corresponding to the historical remaining power, and obtain the historical remaining power After the battery power reaches the preset power value, the comprehensive value of the same state data is used as the historical state data corresponding to the historical remaining power, and the comprehensive value of the state data is: after the historical remaining power, the battery power reaches the preset value. Before setting the power value, the average value or weighted value of the same state data.
  • the historical cruising range is the actual mileage of the electric vehicle after the corresponding historical remaining power point in time, which is equivalent to the true remaining mileage.
  • the preset power value may be 0 or a protection value, for example, 10%.
  • take the remaining power of 80% and the preset power value of 10% as an example record the actual mileage when the remaining power is 80%, and then record the actual mileage when the remaining power is 10%, and the remaining power
  • the actual mileage driven at 10% minus the actual mileage driven when the remaining power is 80%, and the difference obtained is used as the historical cruising range corresponding to the remaining power of 80%.
  • the state data includes: vehicle speed data, vehicle body quality data, battery temperature data, environmental data, road data, driving habits data, battery life data, battery aging data, and/or battery discharge rate data, wherein:
  • the road data includes a road condition index and/or a congestion index
  • the driving habit data includes: a driving habit index generated according to the number of sudden stops, the number of sudden starts, the number of sharp turns, and/or the average speed.
  • this embodiment adds the vehicle speed as the input of the prediction model, and the vehicle speed can be obtained through the vehicle speed sensor. Since the difference in the body mass will cause the energy consumed to be different, this embodiment adds the body mass as the input of the prediction model.
  • Body quality data can be obtained through the weight of the entire vehicle and the number of people in the vehicle, and the number of people in the vehicle can be detected by sensors in the vehicle, such as a weight sensor. Whether the battery generates heat will affect the power consumption rate of the battery. Therefore, this embodiment adds the battery temperature as the input of the estimation model.
  • the battery temperature data can be obtained through the vehicle's battery temperature sensor. Environmental data includes temperature inside the car, temperature outside the car, weather conditions, etc.
  • this embodiment adds environmental data as the input of the prediction model.
  • Various environmental data can be obtained by querying the weather server through the in-vehicle temperature sensor, the outside temperature sensor, and the vehicle's positioning data.
  • the road data includes a road condition index and/or a congestion index.
  • the road condition index is the index corresponding to different road types.
  • Road types include, but are not limited to: muddy roads, urban roads, highways, etc.
  • the road index can be obtained by obtaining the positioning signal of the electric vehicle, and then obtaining the road index of the road where the electric vehicle is located from the map server.
  • the congestion index is an index corresponding to different road congestion situations. Road congestion conditions include but are not limited to: unobstructed, slightly congested, congested, very congested, etc.
  • the congestion index can be obtained by obtaining the positioning signal of the electric vehicle, and then obtaining the congestion index of the road where the electric vehicle is located from the map server. Since the energy consumed by electric vehicles is different under different road conditions, the road index is added as the input of the prediction model in this embodiment.
  • Driving habits include: driving habits index generated based on the number of sudden stops, the number of sudden starts, the number of sharp turns, and/or the average speed.
  • the number of sudden brakes can be obtained by recording the number of times that the pedaling speed of the brake pedal exceeds the preset brake pedal speed threshold by the brake pedal sensor of the electric vehicle, and the number of sudden starts can be recorded by the accelerator pedal sensor of the electric vehicle to record that the pedaling speed of the accelerator pedal exceeds the preset
  • the number of accelerator pedal speed thresholds is obtained, and the number of sharp turns can be obtained by recording the number of times the steering angle speed of the steering wheel exceeds the preset steering speed threshold by the steering wheel sensor of the electric vehicle.
  • the average speed can be obtained by the speed sensor of the electric vehicle.
  • this embodiment adds the driving habit index generated by the driving habit data as the input of the prediction model.
  • the driving habit index may be a weighted value of the number of sudden stops, the number of sudden starts, the number of sharp turns, and/or the average speed.
  • Battery life data, battery aging data, and/or battery discharge rate data will affect the discharge speed and discharge efficiency of the battery. Therefore, this embodiment adds battery life data, battery aging data, and/or battery discharge rate data as a preliminary Estimate the input of the model.
  • Step S203 using the historical driving data as the input object and the historical cruising range as the supervising object, train to generate an estimation model, the input of the estimation model is the current driving data, and the output of the estimation model is the forecast Estimate the mileage.
  • Step S204 Acquire current driving data of the electric vehicle.
  • Step S205 Input the current driving data into a trained estimation model, and obtain the estimated cruising range on the current driving data from the estimation model.
  • Step S206 displaying the estimated cruising range.
  • the embodiment of the present invention adds more state data to the prediction model to obtain a more accurate prediction model.
  • Fig. 3 shows a working flowchart of a method for measuring the cruising range of an electric vehicle according to another optional embodiment of the present invention, including:
  • Step S301 Obtain a prediction model of another electric vehicle of the same type as the electric vehicle.
  • the prediction model of other electric vehicles is obtained by the server from other electric vehicles of the same type as the electric vehicle.
  • Step S302 Obtain historical driving data of the electric vehicle and historical cruising range corresponding to the historical driving data, where the driving data includes at least the remaining power of the electric vehicle;
  • Step S303 Taking the historical driving data as the input object and the historical cruising range as the supervising object, train to generate an estimation model, the input of the estimation model is the current driving data, and the output of the estimation model is the forecast Estimated mileage;
  • Step S304 acquiring current driving data of the electric vehicle
  • Step S305 Input the current driving data into a trained estimation model, and obtain the estimated cruising range on the current driving data from the estimation model;
  • Step S306 displaying the estimated cruising range.
  • a preliminary prediction model is formed by obtaining prediction models of other electric vehicles of the same type as the electric vehicle.
  • the prediction model is further trained based on the vehicle's historical driving data and historical cruising range to form a prediction model that is more in line with the habits of the vehicle.
  • Figure 4 is a schematic diagram of the hardware structure of an electronic device for measuring the cruising range of an electric vehicle according to an embodiment of the present invention, including:
  • At least one processor 401 and,
  • the memory 402 stores instructions that can be executed by the one processor, and the instructions are executed by the at least one processor, so that the at least one processor can:
  • the historical driving data is used as the input object, and the historical cruising range is used as the supervised object to train and generate a prediction model.
  • the input of the prediction model is the current driving data, and the output of the prediction model is the estimated cruising range ;
  • the electronic device is preferably an electronic control unit (ECU), also known as “travel computer”, “vehicle computer” and so on.
  • ECU electronice control unit
  • a processor 402 is taken as an example.
  • the electronic device may further include: an input device 403 and an output device 404.
  • the processor 401, the memory 402, the input device 403, and the display device 404 may be connected by a bus or in other ways. In the figure, the connection by a bus is taken as an example.
  • the memory 402 as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the method for measuring the range of electric vehicles in the embodiments of the present application.
  • Program instructions/modules for example, the method flow shown in Figure 1, Figure 2, Figure 3.
  • the processor 401 executes various functional applications and data processing by running non-volatile software programs, instructions, and modules stored in the memory 402, that is, realizes the method for measuring the cruising range of the electric vehicle in the foregoing embodiment.
  • the memory 402 may include a storage program area and a storage data area, where the storage program area can store an operating system and an application program required by at least one function; the storage data area can store data created according to the use of an electric vehicle mileage measurement method, etc. .
  • the memory 402 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices.
  • the memory 402 may optionally include memories remotely provided with respect to the processor 401, and these remote memories may be connected to a device that executes the method for measuring the cruising range of the electric vehicle through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
  • the input device 403 can receive input user clicks and generate signal inputs related to user settings and function control of the electric vehicle mileage measurement method.
  • the display device 404 may include a display device such as a display screen.
  • the one or more modules are stored in the memory 402, and when run by the one or more processors 401, the method for measuring the cruising range of an electric vehicle in any of the foregoing method embodiments is executed.
  • the invention trains the estimation model and estimates the cruising range based on the driving data of the electric vehicle to obtain a more accurate remaining range of the electric vehicle, thereby improving the accuracy of the cruising range display, thereby improving user experience.
  • An optional embodiment of the present invention is an electronic device for measuring the cruising range of an electric vehicle, including:
  • At least one processor and,
  • a memory communicatively connected with the at least one processor; wherein,
  • the memory stores instructions executable by the one processor, and the instructions are executed by the at least one processor so that the at least one processor can:
  • the actual mileage of the electric vehicle after the historical remaining power until the battery power reaches the preset power value is obtained as the historical cruising range corresponding to the historical remaining power.
  • the comprehensive value of the same state data is used as the historical state data corresponding to the historical remaining power, and the comprehensive value of the state data is: after the historical remaining power, the battery power reaches the preset power value Previously, the average or weighted value of the same state data;
  • the state data includes: vehicle speed data, vehicle body quality data, battery temperature data, environmental data, road data, driving habits data, battery life data, battery aging data, and/or battery discharge rate data, wherein:
  • the road data includes a road condition index and/or a congestion index
  • the driving habit data includes: a driving habit index generated according to the number of sudden stops, the number of sudden starts, the number of sharp turns, and/or the average speed;
  • the historical driving data is used as the input object, and the historical cruising range is used as the supervised object to train and generate a prediction model.
  • the input of the prediction model is the current driving data, and the output of the prediction model is the estimated cruising range ;
  • the embodiment of the present invention adds more state data to the prediction model to obtain a more accurate prediction model.
  • Another optional embodiment of the present invention is an electronic device for measuring the cruising range of an electric vehicle, including:
  • At least one processor and,
  • a memory communicatively connected with the at least one processor; wherein,
  • the memory stores instructions executable by the one processor, and the instructions are executed by the at least one processor so that the at least one processor can:
  • the historical driving data is used as the input object, and the historical cruising range is used as the supervised object to train and generate a prediction model.
  • the input of the prediction model is the current driving data, and the output of the prediction model is the estimated cruising range ;
  • a preliminary prediction model is formed by obtaining prediction models of other electric vehicles of the same type as the electric vehicle.
  • the prediction model is further trained based on the vehicle's historical driving data and historical cruising range to form a prediction model that is more in line with the habits of the vehicle.
  • the seventh embodiment of the present invention provides a storage medium that stores computer instructions, and when the computer executes the computer instructions, it is used to execute all the steps of the method for measuring the cruising range of an electric vehicle as described above.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Databases & Information Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Sustainable Development (AREA)
  • Sustainable Energy (AREA)
  • Power Engineering (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Electric Propulsion And Braking For Vehicles (AREA)

Abstract

一种电动车辆续航里程测量方法、电子设备及存储介质，其中方法包括：获取电动车辆的历史行车数据、以及与历史行车数据对应的历史续航里程，行车数据至少包括电动车辆的剩余电量（S101）；以历史行车数据为输入对象，以历史续航里程为监督对象，训练生成预估模型，预估模型的输入为当前行车数据，预估模型的输出为预估续航里程（S102）；获取电动车辆的当前行车数据（S103）；将当前行车数据输入经过训练的预估模型，从预估模型得到关于当前行车数据的预估续航里程（S104）；显示预估续航里程（S105）。这种方法通过对预估模型进行训练，根据电动车辆的行车数据来预估续航里程，从而可以提高续航里程显示的准确度。

Description

电动车辆续航里程测量方法、电子设备及存储介质
本申请要求在2019年04月16日提交中国专利局、申请号为201910303261.3、发明名称为“电动车辆续航里程测量方法、电子设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及电动车辆相关技术领域，特别是一种电动车辆续航里程测量方法、电子设备及存储介质。
背景技术
近年来，随着社会环保意识的增强，电动车辆作为绿色低碳的出行工具而广受欢迎。
然而，发明人在实现本发明的过程中发现，在使用电动车辆时，经常会出现续航里程不准确的问题。电动车辆续航里程不准确主要包括2种场景：一种是车辆点火前，用户通过APP查看到的车辆续航里程与点火后仪表显示的续航里程不一致的情况；另一种是车辆点火后实际只行驶了2km，但是仪表盘显示的续航里程少掉了5km的情况。目前的方法是预估的剩余里程乘以衰减因子，但是并不准确。
发明内容
以下给出一个或多个方面的简要概述以提供对这些方面的基本理解。此概述不是所有构想到的方面的详尽综览，并且既非旨在指认出所有方面的关键性或决定性要素亦非试图界定任何或所有方面的范围。其唯一的目的是要以简化形式给出一个或多个方面的一些概念以为稍后给出的更加详细的描述之序。
为了解决现有技术中存在电动车辆续航里程预估不准确的技术问题，需要提供一种可以提高续航里程显示的准确度的电动车辆续航 里程测量方法、电子设备及存储介质。
为了达到上述目的，本发明提供了一种电动车辆续航里程测量方法，包括：
获取电动车辆的历史行车数据、以及与所述历史行车数据对应的历史续航里程，所述行车数据至少包括电动车辆的剩余电量；
以所述历史行车数据为输入对象，以所述历史续航里程为监督对象，训练生成预估模型，所述预估模型的输入为当前行车数据，所述预估模型的输出为预估续航里程；
获取电动车辆的当前行车数据；
将所述当前行车数据输入经过训练的预估模型，从所述预估模型得到关于所述当前行车数据的预估续航里程；
显示所述预估续航里程。
如上所述的电动车续航里程测量方法，所述获取电动车辆的历史行车数据、以及与所述历史行车数据对应的历史续航里程，具体包括：
获取电动车辆的历史行车数据，对于任一历史剩余电量，获取在该历史剩余电量之后到电池电量达到预设电量值之前，电动车辆实际行驶的里程作为与该历史剩余电量对应的历史续航里程。
如上所述的电动车续航里程测量方法，所述行车数据还包括至少一种状态数据；
所述当前行车数据包括电动车辆的当前剩余电量、以及当前状态数据；
所述历史行车数据包括历史剩余电量、以及对应的历史状态数据。
如上所述的电动车续航里程测量方法，所述获取电动车辆的历史行车数据、以及与所述历史行车数据对应的历史续航里程，具体包括：
获取电动车辆的历史行车数据，对于任一历史剩余电量，获取在该历史剩余电量之后到电池电量达到预设电量值之前，电动车辆实际行驶的里程作为与该历史剩余电量对应的历史续航里程，获取在该历史剩余电量之后到电池电量达到预设电量值之前，同一状态数据的综合值作为与该历史剩余电量对应的历史状态数据。
如上所述的电动车续航里程测量方法，所述状态数据的综合值为：在该历史剩余电量之后到电池电量达到预设电量值之前，同一状态数据的平均值或加权值。
如上所述的电动车续航里程测量方法，所述状态数据包括：车速数据、车身质量数据、电池温度数据、环境数据、道路数据、驾驶习惯数据、电池寿命数据、电池老化程度数据、和/或电池放电率数据。
如上所述的电动车续航里程测量方法，所述道路数据包括路况指数、和/或拥堵指数。
如上所述的电动车续航里程测量方法，所述驾驶***均速度生成的驾驶习惯指数。
如上所述的电动车续航里程测量方法，还包括：
获取与所述电动车辆同一类型的其他电动车辆的预估模型。
本发明还提供一种电动车辆续航里程测量的电子设备，包括：
至少一个处理器；以及，
与所述至少一个处理器通信连接的存储器；其中，
所述存储器存储有可被所述一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够：
获取电动车辆的历史行车数据、以及与所述历史行车数据对应的历史续航里程，所述行车数据至少包括电动车辆的剩余电量；
以所述历史行车数据为输入对象，以所述历史续航里程为监督对象，训练生成预估模型，所述预估模型的输入为当前行车数据，所述预估模型的输出为预估续航里程；
获取电动车辆的当前行车数据；
将所述当前行车数据输入经过训练的预估模型，从所述预估模型得到关于所述当前行车数据的预估续航里程；
显示所述预估续航里程。
如上所述的电动车辆续航里程测量的电子设备，所述获取电动车辆的历史行车数据、以及与所述历史行车数据对应的历史续航里程，具体包括：
获取电动车辆的历史行车数据，对于任一历史剩余电量，获取在该历史剩余电量之后到电池电量达到预设电量值之前，电动车辆实际行驶的里程作为与该历史剩余电量对应的历史续航里程。
如上所述的电动车辆续航里程测量的电子设备，所述行车数据还包括至少一种状态数据；
所述当前行车数据包括电动车辆的当前剩余电量、以及当前状态数据；
所述历史行车数据包括历史剩余电量、以及对应的历史状态数据。
如上所述的电动车续航里程测量方法，所述获取电动车辆的历史行车数据、以及与所述历史行车数据对应的历史续航里程，具体包括：
获取电动车辆的历史行车数据，对于任一历史剩余电量，获取在该历史剩余电量之后到电池电量达到预设电量值之前，电动车辆实际行驶的里程作为与该历史剩余电量对应的历史续航里程，获取在该历史剩余电量之后到电池电量达到预设电量值之前，同一状态数据的综合值作为与该历史剩余电量对应的历史状态数据。
如上所述的电动车辆续航里程测量的电子设备，所述状态数据的综合值为：在该历史剩余电量之后到电池电量达到预设电量值之前，同一状态数据的平均值或加权值。
如上所述的电动车辆续航里程测量的电子设备，所述状态数据包括：车速数据、车身质量数据、电池温度数据、环境数据、道路数据、驾驶习惯数据、电池寿命数据、电池老化程度数据、和/或电池放电率数据。
如上所述的电动车辆续航里程测量的电子设备，所述道路数据包括路况指数、和/或拥堵指数。
如上所述的电动车辆续航里程测量的电子设备，所述驾驶***均速度生成的驾驶习惯指数。
如上所述的电动车辆续航里程测量的电子设备，所述处理器还能够：
获取与所述电动车辆同一类型的其他电动车辆的预估模型。
本发明还提供一种存储介质，所述存储介质存储计算机指令，当计算机执行所述计算机指令时，用于执行如前所述的电动车辆续航里程测量方法的所有步骤。
本发明所提供的电动车续航里程测量方法、电子设备及存储介质，通过对预估模型进行训练，根据电动车辆的行车数据来预估续航里程，来获得更准确的电动车的剩余里程，从而可以提高续航里程显示的准确度，进而提高用户体验。
附图说明
在结合以下附图阅读本公开的实施例的详细描述之后，能够更好地理解本发明的上述特征和优点。在附图中，各组件不一定是按比例绘制，并且具有类似的相关特性或特征的组件可能具有相同或相近的附图标记。
图1示出了本发明提供的电动车辆续航里程测量方法的一实施例流程图。
图2示出了本发明提供的电动车辆续航里程测量方法的另一实施例流程图。
图3示出了本发明提供的电动车辆续航里程测量方法的另一实施例流程图。
图4示出了本发明提供的电动车辆续航里程测量的电子设备的硬件结构示意图。
具体实施方式
以下结合附图和具体实施例对本发明作详细描述。注意，以下结合附图和具体实施例描述的诸方面仅是示例性的，而不应被理解为对本发明的保护范围进行任何限制。
实施例一
如图1所示为本发明一实施例一种电动车辆续航里程测量方法的工作流程图，包括：
步骤S101，获取电动车辆的历史行车数据、以及与所述历史行车数据对应的历史续航里程，所述行车数据至少包括电动车辆的剩余电量；
步骤S102，以所述历史行车数据为输入对象，以所述历史续航里程为监督对象，训练生成预估模型，所述预估模型的输入为当前行车数据，所述预估模型的输出为预估续航里程；
步骤S103，获取电动车辆的当前行车数据；
步骤S104，将所述当前行车数据输入经过训练的预估模型，从所述预估模型得到关于所述当前行车数据的预估续航里程；
步骤S105，显示所述预估续航里程。
具体来说，步骤S101和步骤S102采用历史行车数据和历史续航里程进行有监督学习训练，从而生成预估模型。行车数据可以由车辆的车载T-BOX硬件***定期(例如，间隔5秒钟、1分钟)保存记录，从而得到历史行车数据。Telematics BOX，简称车载T-BOX。现有的车联网***包含四部分：主机、车载T-BOX、手机应用程序及后台***。其中，车载T-BOX主要用于和后台***或手机应用程序通信。车载T-BOX能记录并获取车辆的各种行车数据。现有的电动车辆会自带剩余里程的估计值，然而该估计值并不准确。因此，可以通过测算车轮转圈数获得行驶里程，从而进行续航里程的计算。通过保存历史的续航里程，并与历史的形成数据进行成对保存，生成成对的历史行车数据和历史续航里程，以用作训练。
然后，在步骤S103中，获取电动车辆当前的行车数据，然后将当前行车数据在步骤S102中输入预估模型，则得到该预估模型所反馈得到的关于所述当前行车数据的预估续航里程。并在步骤S105中显示。
有监督学习训练所采用的模型，可以采用现有的各种模型实现。例如，可以采用回归拟合曲线y＝f(x)实现。其中x为输入参数向量，可以包括一个或多个行车数据。y在训练时为监督对象，即历史续航里程，而在步骤S104中，则为函数输出值，即为预估续航里程。
其中，在步骤S103之后，可以对数据进行预处理。由于数据量 足够大，可以基于每一辆车的历史行车数据，将某一电量下可续航里程偏差较大的点筛除。该步骤是为了尽可能保证后续用作训练样本的数据有较高的准确度。
例如，80％电量下，有的历史点显示续航里程100km，但是大多数据显示续航里程在60km至75km之间，此时取一个基准值(比如，取平均值)，从而可以把特别不合理的点去掉。又例如，用户在取车之前显示剩余电量为60％，剩余里程为60km，在取车之后，显示为30km，则剩余里程为60km为不合理的点可以筛除；或者，实际行驶了10km后，剩余里程为30km，则剩余里程为60km为不合理的点可以筛除。
本发明通过对预估模型进行训练，根据电动车辆的行车数据来预估续航里程，来获得更准确的电动车的剩余里程，从而可以提高续航里程显示的准确度，进而提高用户体验。
实施例二
如图2所示为本发明可选实施例一种电动车辆续航里程测量方法的工作流程图，包括：
步骤S201，获取电动车辆的历史行车数据，所述行车数据至少包括电动车辆的剩余电量、以及至少一种状态数据。
步骤S202，对于任一历史剩余电量，获取在该历史剩余电量之后到电池电量达到预设电量值之前，电动车辆实际行驶的里程作为与该历史剩余电量对应的历史续航里程，获取在该历史剩余电量之后到电池电量达到预设电量值之前，同一状态数据的综合值作为与该历史剩余电量对应的历史状态数据，所述状态数据的综合值为：在该历史剩余电量之后到电池电量达到预设电量值之前，同一状态数据的平均值或加权值。
具体来说，历史续航里程为所对应的历史剩余电量的时间点之后，电动车辆实际又行驶的里程，相当于真实的剩余里程。其中，预设电量值可以为0，也可以为一个保护值，例如，10％。作为一个例子，以剩余电量为80％，预设电量值为10％为例，记录剩余电量80％时的实际已行驶里程，然后记录剩余电量为10％时的实际已行驶里程，将剩 余电量10％时的实际已行驶里程减去剩余电量为80％时的实际已行驶里程，将得到的差值作为剩余电量80％对应的历史续航里程。
优选地，所述状态数据包括：车速数据、车身质量数据、电池温度数据、环境数据、道路数据、驾驶习惯数据、电池寿命数据、电池老化程度数据、和/或电池放电率数据，其中：
所述道路数据包括路况指数、和/或拥堵指数；
所述驾驶***均速度生成的驾驶习惯指数。
由于不同车速会对电池的使用速度有影响，因此，本实施例增加车速作为预估模型的输入，车速可以通过车辆的速度传感器获取。由于车身质量的不同会使得所消耗的能量不同，因此，本实施例增加车身质量作为预估模型的输入。车身质量数据可以通过全车的重量以及车内人员数量得到，车内人员数量可以通过车内传感器，例如重量传感器，检测得到。电池是否发热会影响电池的耗电速度，因此，本实施例增加电池温度作为预估模型的输入。电池温度数据可以通过车辆的电池温度传感器得到。环境数据包括车内温度、车外温度、天气情况等。在不同的环境下，用户会开启或关闭车内的空调***。例如天气冷，用户会开启暖气，天气热，用户会开启冷气。同时，在雨天时，用户会开启雨刷。因此，这些不同的环境因素，都会增加剩余电量的额外损耗。因此，本实施例增加环境数据作为预估模型的输入。各种环境数据可以通过车内温度传感器、车外温度传感器、以及车辆的定位数据查询天气服务器得到。道路数据包括路况指数、和/或拥堵指数。路况指数为不同的道路类型所对应的指数。道路类型包括但不限于：泥泞道路、城市道路、高速公路等。道路指数可以通过获取电动车辆的定位信号，然后从地图服务器中获取电动车辆所在道路的道路指数。拥堵指数为不同的道路拥堵情况所对应的指数。道路拥堵情况包括但不限于：通畅、轻微拥堵、拥堵、非常拥堵等。拥堵指数可以通过获取电动车辆的定位信号，然后从地图服务器中获取电动车辆所在道路的拥堵指数。由于在不同的道路情况下电动车辆所消耗的能量不同，因此，本实施例增加道路指数作为预估模型的输入。驾驶***均速度生成的驾驶***均速度可以通过电动车辆的速度传感器得到。由于急刹车、急启动、急转弯、较高的平均速度会消耗较大的电池电量，因此，这些驾驶***均速度的加权值。电池寿命数据、电池老化程度数据、和/或电池放电率数据会影响电池的放电速度、放电效率，因此，本实施例增加电池寿命数据、电池老化程度数据、和/或电池放电率数据作为预估模型的输入。
步骤S203，以所述历史行车数据为输入对象，以所述历史续航里程为监督对象，训练生成预估模型，所述预估模型的输入为当前行车数据，所述预估模型的输出为预估续航里程。
步骤S204，获取电动车辆的当前行车数据。
步骤S205，将所述当前行车数据输入经过训练的预估模型，从所述预估模型得到关于所述当前行车数据的预估续航里程。
步骤S206，显示所述预估续航里程。
本发明实施例对预估模型增加更多的状态数据，以获得更为精准的预估模型。
实施例三
如图3所示为本发明另一可选实施例一种电动车辆续航里程测量方法的工作流程图，包括：
步骤S301，获取与所述电动车辆同一类型的其他电动车辆的预估模型。
本实施例中其他电动车辆的预估模型由服务器从与所述电动车辆同一类型的其他电动车辆中获取。
步骤S302，获取电动车辆的历史行车数据、以及与所述历史行车数据对应的历史续航里程，所述行车数据至少包括电动车辆的剩余电量；
步骤S303，以所述历史行车数据为输入对象，以所述历史续航里程为监督对象，训练生成预估模型，所述预估模型的输入为当前行车数据，所述预估模型的输出为预估续航里程；
步骤S304，获取电动车辆的当前行车数据；
步骤S305，将所述当前行车数据输入经过训练的预估模型，从所述预估模型得到关于所述当前行车数据的预估续航里程；
步骤S306，显示所述预估续航里程。
由于新的电动车辆没有太多的历史行车数据以及历史续航里程，这会导致其预估模型的训练集不足。本实施例通过获取与所述电动车辆同一类型的其他电动车辆的预估模型，形成一个前期的预估模型。该预估模型在后续的步骤中，通过本车的历史行车数据以及历史续航里程进行进一步训练，从而形成更为符合本车习惯的预估模型。
实施例四
如图4所示为本发明一实施例一种电动车辆续航里程测量的电子设备的硬件结构示意图，包括：
至少一个处理器401；以及，
与所述至少一个处理器401通信连接的存储器402；其中，
所述存储器402存储有可被所述一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够：
获取电动车辆的历史行车数据、以及与所述历史行车数据对应的历史续航里程，所述行车数据至少包括电动车辆的剩余电量；
以所述历史行车数据为输入对象，以所述历史续航里程为监督对象，训练生成预估模型，所述预估模型的输入为当前行车数据，所述预估模型的输出为预估续航里程；
获取电动车辆的当前行车数据；
将所述当前行车数据输入经过训练的预估模型，从所述预估模型得到关于所述当前行车数据的预估续航里程；
显示所述预估续航里程。
电子设备优选为电子控制单元(Electronic Control Unit，ECU)，又称“行车电脑”、“车载电脑”等。图4中以一个处理器402为例。
电子设备还可以包括：输入装置403和输出装置404。
处理器401、存储器402、输入装置403及显示装置404可以通过总线或者其他方式连接，图中以通过总线连接为例。
存储器402作为一种非易失性计算机可读存储介质，可用于存储非易失性软件程序、非易失性计算机可执行程序以及模块，如本申请实施例中的电动车辆续航里程测量方法对应的程序指令/模块，例如，图1、图2、图3所示的方法流程。处理器401通过运行存储在存储器402中的非易失性软件程序、指令以及模块，从而执行各种功能应用以及数据处理，即实现上述实施例中的电动车辆续航里程测量方法。
存储器402可以包括存储程序区和存储数据区，其中，存储程序区可存储操作***、至少一个功能所需要的应用程序；存储数据区可存储根据电动车辆续航里程测量方法的使用所创建的数据等。此外，存储器402可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实施例中，存储器402可选包括相对于处理器401远程设置的存储器，这些远程存储器可以通过网络连接至执行电动车辆续航里程测量方法的装置。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
输入装置403可接收输入的用户点击，以及产生与电动车辆续航里程测量方法的用户设置以及功能控制有关的信号输入。显示装置404可包括显示屏等显示设备。
在所述一个或者多个模块存储在所述存储器402中，当被所述一个或者多个处理器401运行时，执行上述任意方法实施例中的电动车 辆续航里程测量方法。
本发明通过对预估模型进行训练，根据电动车辆的行车数据来预估续航里程，来获得更准确的电动车的剩余里程，从而可以提高续航里程显示的准确度，进而提高用户体验。
实施例五
本发明可选实施例一种电动车辆续航里程测量的电子设备，包括：
至少一个处理器；以及，
与所述至少一个处理器通信连接的存储器；其中，
所述存储器存储有可被所述一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够：
获取电动车辆的历史行车数据，所述行车数据至少包括电动车辆的剩余电量、以及至少一种状态数据；
对于任一历史剩余电量，获取在该历史剩余电量之后到电池电量达到预设电量值之前，电动车辆实际行驶的里程作为与该历史剩余电量对应的历史续航里程，获取在该历史剩余电量之后到电池电量达到预设电量值之前，同一状态数据的综合值作为与该历史剩余电量对应的历史状态数据，所述状态数据的综合值为：在该历史剩余电量之后到电池电量达到预设电量值之前，同一状态数据的平均值或加权值；
优选地，所述状态数据包括：车速数据、车身质量数据、电池温度数据、环境数据、道路数据、驾驶习惯数据、电池寿命数据、电池老化程度数据、和/或电池放电率数据，其中：
所述道路数据包括路况指数、和/或拥堵指数；
所述驾驶***均速度生成的驾驶习惯指数；
以所述历史行车数据为输入对象，以所述历史续航里程为监督对象，训练生成预估模型，所述预估模型的输入为当前行车数据，所述预估模型的输出为预估续航里程；
获取电动车辆的当前行车数据；
将所述当前行车数据输入经过训练的预估模型，从所述预估模型得到关于所述当前行车数据的预估续航里程；
显示所述预估续航里程。
本发明实施例对预估模型增加更多的状态数据，以获得更为精准的预估模型。
实施例六
本发明另一可选实施例一种电动车辆续航里程测量的电子设备，包括：
至少一个处理器；以及，
与所述至少一个处理器通信连接的存储器；其中，
所述存储器存储有可被所述一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够：
获取与所述电动车辆同一类型的其他电动车辆的预估模型。
获取电动车辆的历史行车数据、以及与所述历史行车数据对应的历史续航里程，所述行车数据至少包括电动车辆的剩余电量；
以所述历史行车数据为输入对象，以所述历史续航里程为监督对象，训练生成预估模型，所述预估模型的输入为当前行车数据，所述预估模型的输出为预估续航里程；
获取电动车辆的当前行车数据；
将所述当前行车数据输入经过训练的预估模型，从所述预估模型得到关于所述当前行车数据的预估续航里程；
显示所述预估续航里程。
本实施例通过获取与所述电动车辆同一类型的其他电动车辆的预估模型，形成一个前期的预估模型。该预估模型在后续的步骤中，通过本车的历史行车数据以及历史续航里程进行进一步训练，从而形成更为符合本车习惯的预估模型。
实施例七
本发明第七实施例提供一种存储介质，所述存储介质存储计算机 指令，当计算机执行所述计算机指令时，用于执行如前所述的电动车辆续航里程测量方法的所有步骤。
提供对本公开的先前描述是为使得本领域任何技术人员皆能够制作或使用本公开。对本公开的各种修改对本领域技术人员来说都将是显而易见的，且本文中所定义的普适原理可被应用到其他变体而不会脱离本公开的精神或范围。由此，本公开并非旨在被限定于本文中所描述的示例和设计，而是应被授予与本文中所公开的原理和新颖性特征相一致的最广范围。

Claims (19)

  1. 一种电动车辆续航里程测量方法，包括：
    获取电动车辆的历史行车数据、以及与所述历史行车数据对应的历史续航里程，所述行车数据至少包括电动车辆的剩余电量；
    以所述历史行车数据为输入对象，以所述历史续航里程为监督对象，训练生成预估模型，所述预估模型的输入为当前行车数据，所述预估模型的输出为预估续航里程；
    获取电动车辆的当前行车数据；
    将所述当前行车数据输入经过训练的预估模型，从所述预估模型得到关于所述当前行车数据的预估续航里程；
    显示所述预估续航里程。
  2. 如权利要求1所述的电动车辆续航里程测量方法，其特征在于，所述获取电动车辆的历史行车数据、以及与所述历史行车数据对应的历史续航里程，具体包括：
    获取电动车辆的历史行车数据，对于任一历史剩余电量，获取在该历史剩余电量之后到电池电量达到预设电量值之前，电动车辆实际行驶的里程作为与该历史剩余电量对应的历史续航里程。
  3. 如权利要求2所述的电动车辆续航里程测量方法，其特征在于，所述行车数据还包括至少一种状态数据；
    所述当前行车数据包括电动车辆的当前剩余电量、以及当前状态数据；
    所述历史行车数据包括历史剩余电量、以及对应的历史状态数据。
  4. 如权利要求3所述的电动车辆续航里程测量方法，其特征在于，所述获取电动车辆的历史行车数据、以及与所述历史行车数据对应的历史续航里程，具体包括：
    获取电动车辆的历史行车数据，对于任一历史剩余电量，获取在该历史剩余电量之后到电池电量达到预设电量值之前，电动车辆实际 行驶的里程作为与该历史剩余电量对应的历史续航里程，获取在该历史剩余电量之后到电池电量达到预设电量值之前，同一状态数据的综合值作为与该历史剩余电量对应的历史状态数据。
  5. 如权利要求4所述的电动车辆续航里程测量方法，其特征在于，所述状态数据的综合值为：在该历史剩余电量之后到电池电量达到预设电量值之前，同一状态数据的平均值或加权值。
  6. 如权利要求4所述的电动车辆续航里程测量方法，其特征在于，所述状态数据包括：车速数据、车身质量数据、电池温度数据、环境数据、道路数据、驾驶习惯数据、电池寿命数据、电池老化程度数据、和/或电池放电率数据。
  7. 如权利要求6所述的电动车辆续航里程测量方法，其特征在于，所述道路数据包括路况指数、和/或拥堵指数。
  8. 如权利要求6所述的电动车辆续航里程测量方法，其特征在于，所述驾驶***均速度生成的驾驶习惯指数。
  9. 如权利要求1至8任一项所述的电动车辆续航里程测量方法，其特征在于，所述方法还包括：
    获取与所述电动车辆同一类型的其他电动车辆的预估模型。
  10. 一种电动车辆续航里程测量的电子设备，包括：
    至少一个处理器；以及，
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够：
    获取电动车辆的历史行车数据、以及与所述历史行车数据对应的历史续航里程，所述行车数据至少包括电动车辆的剩余电量；
    以所述历史行车数据为输入对象，以所述历史续航里程为监督对象，训练生成预估模型，所述预估模型的输入为当前行车数据，所述预估模型的输出为预估续航里程；
    获取电动车辆的当前行车数据；
    将所述当前行车数据输入经过训练的预估模型，从所述预估模型得到关于所述当前行车数据的预估续航里程；
    显示所述预估续航里程。
  11. 如权利要求10所述的电子设备，其特征在于，所述获取电动车辆的历史行车数据、以及与所述历史行车数据对应的历史续航里程，具体包括：
    获取电动车辆的历史行车数据，对于任一历史剩余电量，获取在该历史剩余电量之后到电池电量达到预设电量值之前，电动车辆实际行驶的里程作为与该历史剩余电量对应的历史续航里程。
  12. 如权利要求11所述的电子设备，其特征在于，所述行车数据还包括至少一种状态数据；
    所述当前行车数据包括电动车辆的当前剩余电量、以及当前状态数据；
    所述历史行车数据包括历史剩余电量、以及对应的历史状态数据.
  13. 如权利要求12所述的电子设备，其特征在于，所述获取电动车辆的历史行车数据、以及与所述历史行车数据对应的历史续航里程，具体包括：
    获取电动车辆的历史行车数据，对于任一历史剩余电量，获取在该历史剩余电量之后到电池电量达到预设电量值之前，电动车辆实际行驶的里程作为与该历史剩余电量对应的历史续航里程，获取在该历史剩余电量之后到电池电量达到预设电量值之前，同一状态数据的综合值作为与该历史剩余电量对应的历史状态数据。
  14. 如权利要求12所述的电子设备，其特征在于，所述状态数据的综合值为：在该历史剩余电量之后到电池电量达到预设电量值之前，同一状态数据的平均值或加权值。
  15. 如权利要求12所述的电子设备，其特征在于，所述状态数据包括：车速数据、车身质量数据、电池温度数据、环境数据、道路数 据、驾驶习惯数据、电池寿命数据、电池老化程度数据、和/或电池放电率数据。
  16. 如权利要求15所述的电子设备，其特征在于，所述道路数据包括路况指数、和/或拥堵指数。
  17. 如权利要求16所述的电子设备，其特征在于，所述驾驶***均速度生成的驾驶习惯指数。
  18. 如权利要求10至17任一项所述的电子设备，其特征在于，所述处理器还能够：
    获取与所述电动车辆同一类型的其他电动车辆的预估模型。
  19. 一种存储介质，所述存储介质存储计算机指令，当计算机执行所述计算机指令时，用于执行如权利要求1～9任一项所述的电动车辆续航里程测量方法的所有步骤。
PCT/CN2019/129471 2019-04-16 2019-12-27 电动车辆续航里程测量方法、电子设备及存储介质 WO2020211456A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910303261.3 2019-04-16
CN201910303261.3A CN111806239B (zh) 2019-04-16 2019-04-16 电动车辆续航里程测量方法、电子设备及存储介质

Publications (1)

Publication Number Publication Date
WO2020211456A1 true WO2020211456A1 (zh) 2020-10-22

Family

ID=72836908

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/129471 WO2020211456A1 (zh) 2019-04-16 2019-12-27 电动车辆续航里程测量方法、电子设备及存储介质

Country Status (2)

Country Link
CN (1) CN111806239B (zh)
WO (1) WO2020211456A1 (zh)

Cited By (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112383107A (zh) * 2020-11-13 2021-02-19 苏州索尔智行新能源科技有限公司 换电站信息显示方法、装置、计算机设备和存储介质
CN112613128A (zh) * 2020-12-29 2021-04-06 联合汽车电子有限公司 续航里程的预测方法、装置、设备、车辆和存储介质
CN112668515A (zh) * 2020-12-31 2021-04-16 车主邦（北京）科技有限公司 车辆基本信息获取方法和装置
CN112881917A (zh) * 2021-01-21 2021-06-01 四川野马汽车股份有限公司 一种基于大数据平台的动力电池寿命预测方法及***
CN113002311A (zh) * 2021-03-30 2021-06-22 安徽江淮汽车集团股份有限公司 剩余续航里程的计算方法、装置、设备以及存储介质
CN113071497A (zh) * 2021-04-28 2021-07-06 中国第一汽车股份有限公司 一种驾驶场景判断方法、装置、设备及存储介质
CN113085655A (zh) * 2021-05-11 2021-07-09 国网黑龙江省电力有限公司电力科学研究院 一种车载电动汽车综合服务***
CN113484765A (zh) * 2021-08-03 2021-10-08 广州极飞科技股份有限公司 无人机的续航时间确定方法、装置、处理设备及介质
CN113525171A (zh) * 2021-06-28 2021-10-22 浙江吉利控股集团有限公司 一种电动汽车电池充放电控制方法及装置
CN114013284A (zh) * 2021-11-02 2022-02-08 上汽大众汽车有限公司 一种车辆续航里程的计算方法和***
CN114091735A (zh) * 2021-10-28 2022-02-25 华人运通(上海)云计算科技有限公司 一种电动车续航里程预测方法
CN114407660A (zh) * 2022-02-10 2022-04-29 上海集嘉同速汽车科技有限公司 一种场地运行电动车辆剩余行驶圈数估计方法
CN114537219A (zh) * 2022-02-16 2022-05-27 北京海博思创科技股份有限公司 充电截止荷电状态确定方法、装置、设备及介质
CN114655074A (zh) * 2021-11-16 2022-06-24 吉林大学 一种基于贝叶斯回归的电动汽车实际行驶能耗估计方法
CN114670709A (zh) * 2021-03-23 2022-06-28 北京新能源汽车股份有限公司 一种行车加热的控制方法、装置、***及车辆
CN115100756A (zh) * 2022-06-28 2022-09-23 浙江吉利控股集团有限公司 续驶里程确定方法、车辆及计算机可读存储介质
CN115583153A (zh) * 2022-11-17 2023-01-10 达芬骑动力科技(北京)有限公司 一种续航里程计算方法、装置及计算机设备
CN115828578A (zh) * 2022-11-29 2023-03-21 成都赛力斯科技有限公司 一种续航里程的预测方法、装置、电子设备及存储介质
CN116416795A (zh) * 2023-04-06 2023-07-11 广东云钜网络科技有限公司 基于交通大数据的僵尸车监察方法及***
CN116945907A (zh) * 2023-09-19 2023-10-27 江西五十铃汽车有限公司 一种新能源电动汽车里程计算方法及***
CN117901717A (zh) * 2024-03-20 2024-04-19 江苏海铂德能源科技有限公司 适用于低速四轮车基于边缘迁跃状态机的bms控制***

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112549970A (zh) * 2020-12-09 2021-03-26 广州橙行智动汽车科技有限公司 车辆续航里程预测方法、装置、车辆及存储介质
CN112818036B (zh) * 2021-01-29 2022-12-30 清华大学 基于云端大数据的电动车剩余里程预估方法和装置
CN113459896B (zh) * 2021-06-28 2022-11-08 岚图汽车科技有限公司 一种电动汽车续航里程确定方法及装置
CN114347852B (zh) * 2021-12-31 2024-05-03 中国第一汽车股份有限公司 车辆续航时间的显示方法、装置、电子设备及存储介质
CN114274780A (zh) * 2022-01-10 2022-04-05 中国第一汽车股份有限公司 车辆续航里程预测方法、装置、设备和存储介质
CN115042667B (zh) * 2022-05-25 2024-05-14 东风柳州汽车有限公司 行车提醒方法、装置、设备及存储介质
CN116894525B (zh) * 2023-09-04 2023-12-08 北京玖行智研交通科技有限公司 一种电动重型卡车续航里程预测方法及装置

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2505663A (en) * 2012-09-06 2014-03-12 Jaguar Land Rover Ltd Dynamically variable residual range indicator for motor vehicle
EP2789977A1 (en) * 2011-12-08 2014-10-15 Hitachi, Ltd. Device, method and program for calculating accessible range
CN106515478A (zh) * 2016-10-27 2017-03-22 合肥工业大学 电动汽车剩余行驶里程在线预测方法及装置
CN106908075A (zh) * 2017-03-21 2017-06-30 福州大学 大数据采集与处理***及基于其电动汽车续航估计方法
CN107844613A (zh) * 2016-09-18 2018-03-27 大陆汽车投资（上海）有限公司 基于数据分析的电动车续航管理方法
EP3369604A1 (en) * 2015-10-30 2018-09-05 Beijing Electric Vehicle Co., Ltd. Method and system for estimating remaining range of electric car, and electric car
CN109606197A (zh) * 2018-10-19 2019-04-12 蔚来汽车有限公司 用于预测电动汽车剩余行驶里程的方法、装置和存储介质

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2628628B1 (en) * 2010-10-14 2020-03-11 Toyota Jidosha Kabushiki Kaisha Display system for electrically powered vehicle and electrically powered vehicle having the same
CN104986043B (zh) * 2015-07-30 2017-03-22 深圳东风汽车有限公司 一种电动汽车续航里程预测方法
CN105235543B (zh) * 2015-10-27 2017-11-14 北京新能源汽车股份有限公司 用于电动汽车剩余行驶里程的处理方法、装置及***
JP6551332B2 (ja) * 2016-07-26 2019-07-31 トヨタ自動車株式会社 車両の走行可能距離算出システムおよび走行可能距離算出方法
CN109606119B (zh) * 2019-01-15 2020-05-12 深圳四海万联科技有限公司 一种电动汽车的续航里程校准方法及***

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2789977A1 (en) * 2011-12-08 2014-10-15 Hitachi, Ltd. Device, method and program for calculating accessible range
GB2505663A (en) * 2012-09-06 2014-03-12 Jaguar Land Rover Ltd Dynamically variable residual range indicator for motor vehicle
EP3369604A1 (en) * 2015-10-30 2018-09-05 Beijing Electric Vehicle Co., Ltd. Method and system for estimating remaining range of electric car, and electric car
CN107844613A (zh) * 2016-09-18 2018-03-27 大陆汽车投资（上海）有限公司 基于数据分析的电动车续航管理方法
CN106515478A (zh) * 2016-10-27 2017-03-22 合肥工业大学 电动汽车剩余行驶里程在线预测方法及装置
CN106908075A (zh) * 2017-03-21 2017-06-30 福州大学 大数据采集与处理***及基于其电动汽车续航估计方法
CN109606197A (zh) * 2018-10-19 2019-04-12 蔚来汽车有限公司 用于预测电动汽车剩余行驶里程的方法、装置和存储介质

Cited By (35)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112383107B (zh) * 2020-11-13 2023-01-31 苏州索尔智行新能源科技有限公司 换电站信息显示方法、装置、计算机设备和存储介质
CN112383107A (zh) * 2020-11-13 2021-02-19 苏州索尔智行新能源科技有限公司 换电站信息显示方法、装置、计算机设备和存储介质
CN112613128B (zh) * 2020-12-29 2024-05-31 联合汽车电子有限公司 续航里程的预测方法、装置、设备、车辆和存储介质
CN112613128A (zh) * 2020-12-29 2021-04-06 联合汽车电子有限公司 续航里程的预测方法、装置、设备、车辆和存储介质
CN112668515A (zh) * 2020-12-31 2021-04-16 车主邦（北京）科技有限公司 车辆基本信息获取方法和装置
CN112881917A (zh) * 2021-01-21 2021-06-01 四川野马汽车股份有限公司 一种基于大数据平台的动力电池寿命预测方法及***
CN112881917B (zh) * 2021-01-21 2022-11-22 四川野马汽车股份有限公司 一种基于大数据平台的动力电池寿命预测方法及***
CN114670709B (zh) * 2021-03-23 2024-02-20 北京新能源汽车股份有限公司 一种行车加热的控制方法、装置、***及车辆
CN114670709A (zh) * 2021-03-23 2022-06-28 北京新能源汽车股份有限公司 一种行车加热的控制方法、装置、***及车辆
CN113002311B (zh) * 2021-03-30 2022-06-28 安徽江淮汽车集团股份有限公司 剩余续航里程的计算方法、装置、设备以及存储介质
CN113002311A (zh) * 2021-03-30 2021-06-22 安徽江淮汽车集团股份有限公司 剩余续航里程的计算方法、装置、设备以及存储介质
CN113071497A (zh) * 2021-04-28 2021-07-06 中国第一汽车股份有限公司 一种驾驶场景判断方法、装置、设备及存储介质
CN113071497B (zh) * 2021-04-28 2022-05-24 中国第一汽车股份有限公司 一种驾驶场景判断方法、装置、设备及存储介质
CN113085655A (zh) * 2021-05-11 2021-07-09 国网黑龙江省电力有限公司电力科学研究院 一种车载电动汽车综合服务***
CN113085655B (zh) * 2021-05-11 2022-08-26 国网黑龙江省电力有限公司电力科学研究院 一种车载电动汽车综合服务***
CN113525171A (zh) * 2021-06-28 2021-10-22 浙江吉利控股集团有限公司 一种电动汽车电池充放电控制方法及装置
CN113525171B (zh) * 2021-06-28 2024-04-12 浙江吉利控股集团有限公司 一种电动汽车电池充放电控制方法及装置
CN113484765A (zh) * 2021-08-03 2021-10-08 广州极飞科技股份有限公司 无人机的续航时间确定方法、装置、处理设备及介质
CN113484765B (zh) * 2021-08-03 2024-04-09 广州极飞科技股份有限公司 无人机的续航时间确定方法、装置、处理设备及介质
CN114091735A (zh) * 2021-10-28 2022-02-25 华人运通(上海)云计算科技有限公司 一种电动车续航里程预测方法
CN114013284B (zh) * 2021-11-02 2023-09-22 上汽大众汽车有限公司 一种车辆续航里程的计算方法和***
CN114013284A (zh) * 2021-11-02 2022-02-08 上汽大众汽车有限公司 一种车辆续航里程的计算方法和***
CN114655074B (zh) * 2021-11-16 2024-01-30 吉林大学 一种基于贝叶斯回归的电动汽车实际行驶能耗估计方法
CN114655074A (zh) * 2021-11-16 2022-06-24 吉林大学 一种基于贝叶斯回归的电动汽车实际行驶能耗估计方法
CN114407660A (zh) * 2022-02-10 2022-04-29 上海集嘉同速汽车科技有限公司 一种场地运行电动车辆剩余行驶圈数估计方法
CN114537219A (zh) * 2022-02-16 2022-05-27 北京海博思创科技股份有限公司 充电截止荷电状态确定方法、装置、设备及介质
CN114537219B (zh) * 2022-02-16 2023-11-14 北京海博思创科技股份有限公司 充电截止荷电状态确定方法、装置、设备及介质
CN115100756A (zh) * 2022-06-28 2022-09-23 浙江吉利控股集团有限公司 续驶里程确定方法、车辆及计算机可读存储介质
CN115583153A (zh) * 2022-11-17 2023-01-10 达芬骑动力科技(北京)有限公司 一种续航里程计算方法、装置及计算机设备
CN115828578A (zh) * 2022-11-29 2023-03-21 成都赛力斯科技有限公司 一种续航里程的预测方法、装置、电子设备及存储介质
CN116416795B (zh) * 2023-04-06 2023-11-10 广东云钜网络科技有限公司 基于交通大数据的僵尸车监察方法及***
CN116416795A (zh) * 2023-04-06 2023-07-11 广东云钜网络科技有限公司 基于交通大数据的僵尸车监察方法及***
CN116945907B (zh) * 2023-09-19 2024-01-26 江西五十铃汽车有限公司 一种新能源电动汽车里程计算方法及***
CN116945907A (zh) * 2023-09-19 2023-10-27 江西五十铃汽车有限公司 一种新能源电动汽车里程计算方法及***
CN117901717A (zh) * 2024-03-20 2024-04-19 江苏海铂德能源科技有限公司 适用于低速四轮车基于边缘迁跃状态机的bms控制***

Also Published As

Publication number Publication date
CN111806239A (zh) 2020-10-23
CN111806239B (zh) 2022-04-05

Similar Documents

Publication Publication Date Title
WO2020211456A1 (zh) 电动车辆续航里程测量方法、电子设备及存储介质
CN110126841B (zh) 基于道路信息和驾驶风格的纯电动汽车能耗模型预测方法
CN108885114B (zh) 基于云的动态车辆共享***和方法
CN111497679B (zh) 一种纯电动汽车能耗监测优化方法及***
CN109558988B (zh) 一种基于大数据融合的电动汽车能耗预测方法及***
CN109733248A (zh) 基于路径信息的纯电动汽车剩余里程模型预测方法
CN106596135B (zh) 一种纯电动汽车实际行驶能耗测试、评价和预测方法
WO2021218313A1 (zh) 车辆的剩余里程确定方法、装置及车辆
Yavasoglu et al. Implementation of machine learning based real time range estimation method without destination knowledge for BEVs
CN111806240B (zh) 一种基于中国工况的电动汽车续驶里程预测方法
WO2017067439A1 (zh) 电动汽车的续驶里程显示方法、装置和***
US20040088205A1 (en) Driving workload estimation
CN112406630B (zh) 一种基于工况识别的电动车续驶里程计算方法
CN107458259A (zh) 一种新能源电动汽车剩余里程估算方法
CN103927866B (zh) 基于gps的车辆等待红绿灯时间预测方法
CN112224089A (zh) 基于能耗的行程规划方法、装置、电子设备及存储介质
CN104442825A (zh) 一种电动汽车剩余行驶里程的预测方法和***
US10384687B2 (en) Method and system for assessing the trip performance of a driver
US9539904B2 (en) Energy consumption rate in distance domain
CN108001453B (zh) 一种识别高能耗驾驶行为的方法及***
CN111497624A (zh) 一种车辆剩余里程确定方法、装置及车辆
CN114778140B (zh) 车辆能耗台架测试方法和***
JP2010144701A (ja) 省燃費運転評価装置及び省燃費運転評価方法
CN107478289A (zh) 获取平均油耗的方法和装置
WO2018045650A1 (zh) 一种车速控制方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19925441

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19925441

Country of ref document: EP

Kind code of ref document: A1