WO2024239494A1 - 一种增程式插电混合动力汽车预约充电智能方法、装置及计算机系统 - Google Patents

一种增程式插电混合动力汽车预约充电智能方法、装置及计算机系统 Download PDF

Info

Publication number
WO2024239494A1
WO2024239494A1 PCT/CN2023/118295 CN2023118295W WO2024239494A1 WO 2024239494 A1 WO2024239494 A1 WO 2024239494A1 CN 2023118295 W CN2023118295 W CN 2023118295W WO 2024239494 A1 WO2024239494 A1 WO 2024239494A1
Authority
WO
WIPO (PCT)
Prior art keywords
charging
recommended
idle
round
fast
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.)
Ceased
Application number
PCT/CN2023/118295
Other languages
English (en)
French (fr)
Inventor
陈孔武
许朋涛
杨淑娟
张娜
陈沁�
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Dongfeng Motor Group Co Ltd
Original Assignee
Dongfeng Motor Group Co Ltd
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 Dongfeng Motor Group Co Ltd filed Critical Dongfeng Motor Group Co Ltd
Publication of WO2024239494A1 publication Critical patent/WO2024239494A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06Q10/02—Reservations, e.g. for tickets, services or events
    • 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
    • B60L53/00—Methods of charging batteries, specially adapted for electric vehicles; Charging stations or on-board charging equipment therefor; Exchange of energy storage elements in electric vehicles
    • 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
    • B60L58/00—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles
    • B60L58/10—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles for monitoring or controlling batteries
    • B60L58/12—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles for monitoring or controlling batteries responding to state of charge [SoC]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
    • 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 an extended-range plug-in hybrid electric vehicle, and in particular to an intelligent method, device and computer system for pre-charging an extended-range plug-in hybrid electric vehicle.
  • Extended-range plug-in hybrid electric vehicles can effectively respond to the country's requirements for energy conservation and emission reduction and eliminate customers' mileage anxiety. They have both traditional internal combustion engines and pure electric vehicle motors, which can reduce dependence on and demand for petroleum fuels and improve automobile fuel economy and emission performance. Extended-range plug-in hybrid electric vehicles usually have the following driving modes: 1. Pure electric mode, in which the car relies on the high-voltage battery to provide power to the drive motor, and the drive motor drives the car; 2. Series mode, in which the engine starts running.
  • the engine drives the generator to charge the high-voltage battery; on the other hand, the engine drives the generator to provide power to the drive motor to drive the car; therefore, when the battery power is very low, the series mode can be used to drive the car to eliminate users' mileage anxiety.
  • the industry has noticed the charging needs of new energy vehicles and tried to propose relevant solutions.
  • the State Grid Corporation of China has an invention application with the publication number CN104779680A and the invention name "Electric Vehicle Appointment Charging Control Method and Device", which discloses an electric vehicle appointment charging control method and device.
  • the method includes: obtaining appointment charging information and pre-set optimization control parameters; obtaining vehicle status information of the vehicle pre-bound to the appointment charging information; determining the vehicle appointment charging plan set based on the appointment charging information and vehicle status information; using the optimization control parameters to filter out the recommended charging plan from the appointment charging plan set.
  • the present invention solves the technical problems of charging equipment resource waste and poor user charging experience caused by the inability to optimize the scheduled charging of electric vehicles.
  • the invention patent application is aimed at pure electric vehicles, while the present invention is aimed at extended-range plug-in hybrid vehicles, which have significant differences in the overall vehicle mode; 2.
  • the driver's specific driving habits are not taken into account, and the driver's actual driving mode and habitual user behavior analysis is not performed; 3. It is mainly aimed at the power grid side or the charging pile side, and no specific description is given for the specific vehicle control parameters; 4.
  • the impact of actual road conditions on scheduled charging is not considered.
  • Another utility model which was declared by Jiangsu Jintan Damai Automotive Engineering Research Institute Co., Ltd. and Jiangsu Jintan Automotive Industry Co., Ltd., with the publication number CN207683369U and the name of the utility model, is a kind of automobile reservation charging system. It discloses a kind of automobile reservation charging system, including a remote control terminal, TBOX, an on-board charger OBC, a battery management system BMS, and a vehicle controller VCU.
  • the remote control terminal is connected to the TBOX
  • the TBOX is respectively connected to the on-board charger OBC and the battery management system BMS
  • the battery management system BMS is connected to the vehicle controller VCU.
  • the purpose of the present invention is to overcome the shortcomings of the above-mentioned background technology and to provide an intelligent method, device and computer system for pre-booking charging of an extended-range plug-in hybrid electric vehicle, so that it has the function of reasonably arranging the optimal pre-booked charging station and route information according to the user's pre-booking conditions.
  • the present invention provides an intelligent method for pre-charging an extended-range plug-in hybrid electric vehicle.
  • Multiple rounds of recommendations are made for the scheduled charging stations, including the following steps: first round of recommendations: based on the number of scheduled charging records, the first batch of recommended charging stations are selected, and based on the historical idle data of the charging stations, the idle fast and slow charging idle numbers and the total idle numbers of the charging stations at the scheduled charging time are predicted, and based on the idle number threshold, the first round of final recommended scheduled charging stations are selected; second round of recommendations: based on the map information and the power consumption calculation logic in the pure electric mode, the remaining SOC to reach the first round of final recommended scheduled charging stations is calculated, and the second round of recommended scheduled charging stations is recommended based on the remaining SOC; final recommendation: when arriving at the scheduled time point, the SOC to reach the second round of recommended scheduled charging stations is calculated based on the real-time traffic information on the map and the power consumption calculation logic in the pure electric mode, and the final charging station recommendation is made based on the SOC and the real-
  • the specific process of the first round of recommendation steps is as follows: departure information reservation: input the departure location and departure time of the scheduled charging through the car computer or mobile phone; first reservation record acquisition: if the number of user reservation charging records in the system is less than n, the system calculates the y nearest charging stations within x km near the departure point as recommended charging stations, and obtains the charging station information; second reservation record acquisition: if the number of user reservation charging records in the system is greater than n, first sort the charging stations actually used by the user by the number of times used, select the z charging stations with the most times used, calculate the distance between the departure point and the selected charging station, if it is less than or equal to the distance threshold, retain it as the recommended charging station, and obtain the charging station information; if it is greater than the distance threshold, remove it; information extraction: extract the information on the number of idle charging guns of the recommended charging station in the past m days from the charging station history data system.
  • Normalization normalize the fast and slow charging data of m 1 and m 2 days respectively; time series analysis: use the time series machine learning model to perform time series analysis, use the root mean square error R 2 to evaluate the time series model, select the model with the smallest R 2 value, predict the number of fast and slow charging idle times at a charging station at the driver's appointment time, and use it as the final charging station recommendation for the first round.
  • the normalization step is the min-max method.
  • the normalized fast charging idle number is: (fast-fast min )/(fast max -fast min ).
  • the normalized slow charging idle number is: (slow-slow fast )/(slow max -slow min ).
  • the average fast charging number ⁇ 3 and the average slow charging number ⁇ 4 of the target set m2 are used to fill the empty values of the target data set, and the maximum values fastTarget max and fastTarget min of the target set are used to normalize the target set.
  • the process of predicting the number of fast and slow charging idle positions at a charging station at the driver's reservation time is: if a station finally predicts that the number of fast charging idle positions > fast0 and the number of slow charging idle positions > slow0, and the total number of fast charging idle positions and the total number of slow charging idle positions > total0, then it is recommended as the final charging station in the first round.
  • the time series machine learning model includes but is not limited to the LSTM ⁇ RNN model.
  • the specific process of the two-round recommendation steps is as follows: map information acquisition: according to the starting point input by the user and the charging station recommended in the first round, the map information from the starting point to each charging station is obtained; speed segment map conversion: according to the actual map road condition information, the road condition information is converted into a speed segment map; remaining SOC calculation: according to the actual SOC of the vehicle, combined with the pure electric mode cruising range calibration table, the actual power consumption is obtained, and the remaining SOC1 after the vehicle completely passes through the first section of the road can be calculated; the remaining SOCn after passing through the second section of the road, the third section of the road...
  • the specific process of the final recommendation step is as follows: Pure electric mode SOC calculation: When the user's scheduled time point is reached, the actual map information of the route to the second round of recommended charging stations at that time point is obtained from the map, and the remaining SOC when the pure electric mode reaches the second round of recommended charging stations is recalculated according to the two-round recommendation steps. If the calculated remaining SOC ⁇ 0, the user is prompted to use the series mode to reach the station; Comparison and sorting recommendations: If the remaining SOC>0, then as a recommended charging station, query the fast charging idle number, slow charging idle number and total idle number of the recommended charging station in the charging station information system.
  • the fast charging idle number is greater than fastLast
  • the slow charging idle number is greater than slowLast and the total idle number is greater than totalLast
  • it can be used as the final recommended charging station, and the final recommended charging stations are sorted from large to small according to the remaining SOC as the final recommended charging station list, and the corresponding driving routes are recommended.
  • the present invention further provides an intelligent device for pre-charging an extended-range plug-in hybrid electric vehicle, which stores a computer program capable of executing an intelligent method for pre-charging an extended-range plug-in hybrid electric vehicle.
  • the present invention also provides a computer system, which includes an intelligent device for pre-charging an extended-range plug-in hybrid electric vehicle.
  • the present invention provides an intelligent method, device and computer system for scheduled charging of an extended-range plug-in hybrid electric vehicle, which has the following beneficial effects:
  • the present invention is mainly aimed at extended-range plug-in hybrid electric vehicles, taking into account the actual road conditions, user historical behavior, the actual conditions of the vehicle itself and the charging station, and based on the advantages of the cloud platform being cheap, reliable, and scalable, a set of extended-range plug-in hybrid electric vehicle reservation charging intelligent system and method is established on the cloud platform taking into account vehicle characteristics, user historical charging behavior, road condition information on the way to the charging station, and charging station information, etc., which can be used for extended-range plug-in hybrid electric vehicles. Provide users with the most economical and available reserved charging stations and driving routes.
  • FIG1 is a schematic diagram of the power structure of a range-extended plug-in hybrid electric vehicle of the present invention.
  • FIG2 is a schematic diagram of the overall process of the intelligent method for scheduled charging of an extended-range plug-in hybrid electric vehicle according to the present invention
  • FIG3 is a schematic diagram of a specific flow chart of the first round of recommendation steps in the intelligent method for scheduled charging of an extended-range plug-in hybrid electric vehicle according to the present invention
  • FIG4 is a schematic diagram of a specific flow chart of the second round recommendation step in the intelligent method for scheduled charging of an extended-range plug-in hybrid electric vehicle according to the present invention
  • 5 is a diagram of actual road speed segments of sub-step 2.2 of the second round recommendation step in the intelligent method for scheduled charging of an extended-range plug-in hybrid electric vehicle of the present invention
  • FIG6 is a schematic diagram of a specific flow chart of the final recommended step in the intelligent method for scheduled charging of an extended-range plug-in hybrid electric vehicle according to the present invention
  • FIG7 is a schematic structural diagram of an intelligent device for pre-charging an extended-range plug-in hybrid electric vehicle according to the present invention.
  • FIG8 is a schematic diagram of the structure of the computer system of the present invention.
  • FIG1 The power structure of the extended-range plug-in hybrid electric vehicle of the present invention is shown in FIG1 , in which the engine is a gasoline engine.
  • the solid line connection in the figure is a mechanical connection, and the dotted line connection is an electrical connection; there are two driving modes, electric mode and series mode; 1. When the vehicle is in electric mode, the engine does not work, and the vehicle relies on the high-voltage battery to provide power to the drive motor. The vehicle is driven by the drive motor; 2. When the vehicle is in series mode, the engine starts working. On the one hand, the engine drives the generator to charge the high-voltage battery. On the other hand, the engine drives the generator to provide electrical energy to the drive motor, and the drive motor drives the vehicle.
  • the intelligent method for pre-charging of a range-extended plug-in hybrid electric vehicle of the present invention is arranged in a server, a vehicle computer or a controller, and is connected to a client in the vehicle computer or a mobile terminal; the server, the vehicle computer or the controller obtains charging station information and map information based on the Internet of Things, and obtains information such as the remaining SOC of the vehicle from the vehicle; the client in the vehicle computer or the mobile terminal is used for the user to input the departure location and departure time for pre-charging, and displays the map, charging station location information, etc.
  • the server is connected to the charging station information system network, and obtains various parameter information of the charging station from the charging station information system.
  • the charging station information system can be an existing external system, or it can be a part of the present invention.
  • First round of recommendations Based on the number of scheduled charging records, a specific method is selected to select the first batch of recommended charging stations. Based on the historical idle data of charging stations, the idle fast and slow charging idle number and the total idle number of charging stations at the scheduled charging time are predicted, and based on the idle number threshold, the first round of final recommended scheduled charging stations are selected;
  • the driver enters the departure location and departure time for scheduled charging through the vehicle computer or mobile phone;
  • the system calculates the y (configurable, e.g. 40) nearest charging stations within x km (configurable, e.g. 20km) of the starting point as recommended charging stations, and obtains the charging station information;
  • n e.g. 500, configurable
  • n e.g. 500, configurable
  • the z e.g. 50, configurable
  • the distance threshold which can be set, such as 20km
  • the sampling frequency of the idle information of charging stations in the charging station information system is t hours (settable, default 1h).
  • the data of the number of idle charging guns of fast and slow charging at recommended charging stations for 30 days is processed as follows: the data of the number of idle charging guns of fast and slow charging at recommended charging stations for 30 days is divided into an input set and a target set. The data of the first 27 days is used as the input data set, and the data of the last 3 days is used as the target data set;
  • the fast and slow charging idle number average values ⁇ 1 (corresponding to the fast charging average value) and ⁇ 2 (corresponding to the slow charging average value) of 27 days are used to fill the empty values of fast and slow charging respectively;
  • the normalized fast charging idle number is: (fast-fastmin)/(fastmax-fastmin)
  • the normalized slow charging idle number is: (slow-slowfast)/(slowmax-slowmin).
  • the average values of the fast and slow charging numbers ⁇ 3 and ⁇ 4 of the target set (3 days of data) are used to fill the empty values of the target data set (corresponding to the last 3 days of data), and the maximum values of the target set fastTargetmax and fastTargetmin are used to normalize the target set;
  • time series machine learning models (not limited to LSTM ⁇ RNN models) to perform time series analysis, use the root mean square error R2 to evaluate the time series model, select the model with the smallest R2 value, and predict the number of fast and slow charging idle times at a charging station at the driver's reservation time (accurate to h).
  • Second round of recommendations Based on the map information and the power consumption calculation logic in pure electric mode, the remaining SOC to reach the final recommended charging station in the first round is calculated, and the second round of recommended charging stations is recommended based on the remaining SOC;
  • Table 1 is the basic calibration table of battery consumption in pure electric mode, in which the horizontal axis is the remaining power SOC of the high-voltage battery, and the vertical axis is the uniform vehicle speed.
  • the data in the table represents the percentage of power consumption per kilometer when the horizontal axis SOC reaches 0% when the vehicle speed is equal to the vertical axis vehicle speed;
  • Table 2 represents the ambient temperature correction factor, which corrects the power consumption in Table 1;
  • Table 3 represents the power correction factor, which corrects Table 1 according to the user's past historical behavior.
  • the specific historical behavior analysis is as follows: 1) When the vehicle's driving distance is less than or equal to 1000km, the default power correction table is used. is a power correction table, as shown in the values in Table 3; 2) when the vehicle travels more than 1000km, based on the user's historical behavior, the power at a certain speed (10km/h, 20km/h, 30km/h, 40km/h, 50km/h, 60km/h, 70km/h, 80km/h, 100km/h, 120km/h, 140km/h, 160km/h, etc.) is counted, and the average value is taken as the driving demand power at the speed, divided by the demand power under uniform speed conditions, as the power correction coefficient at the speed, where the demand power at uniform speed can be obtained through actual road tests. If there is no such speed in the historical behavior data, the default value in Table 3 is used.
  • the road condition information is converted into a speed segment diagram, as shown in Figure 5.
  • the maximum speed of the first section is v1. If the vehicle mileage is ⁇ 50km, the vehicle speed of the section is set to v1. If the vehicle mileage is ⁇ 50km, the average speed of the customer's history of passing the speed section is the vehicle speed of the section.
  • the actual power consumption can be obtained, and the remaining SOC1 after the vehicle completely passes the first section of the road can be calculated; the remaining SOCn after passing the second section of the road, the third section of the road, and so on can be calculated in sequence;
  • the charging station with a remaining SOCn>0 i.e., reachable in pure electric mode is selected as the second round of recommended charging stations, and the accessible route information is provided;
  • the remaining SOC>0 it is recommended as a charging station.
  • the charging station information system query the fast charging idle number, slow charging idle number and total idle number of the recommended charging station. If the fast charging idle number is greater than fastLast (settable, such as 2) and the slow charging idle number is greater than slowLast (settable, such as 2) and the total idle number is greater than totalLast (settable, such as 2), it can be used as the final recommended charging station. Sort the final recommended charging stations from large to small according to the remaining SOC as the final recommended charging station list, and recommend the corresponding driving route.
  • the intelligent device for pre-booking charging of a range-extended plug-in hybrid electric vehicle of the present invention makes multiple rounds of recommendations for pre-booked charging stations, including the following contents:
  • First round recommendation module According to the number of scheduled charging records, a specific method is selected to select the first batch of recommended charging stations. According to the historical idle data of charging stations, the idle fast and slow charging idle number and the total idle number of charging stations at the scheduled charging time are predicted, and according to the idle number threshold, the first round of final recommended scheduled charging stations are selected;
  • Second round recommendation module Based on the map information and the power consumption calculation logic in pure electric mode, the remaining SOC to reach the final recommended charging station in the first round is calculated, and the second round of recommended charging stations is recommended based on the remaining SOC;
  • Final recommendation module When the appointment time is reached, the SOC of the charging station recommended for the second round is calculated based on the real-time traffic information on the map and the power consumption calculation logic of the pure electric mode, and the final charging station recommendation is made based on the SOC and the real-time fast and slow charging idle information of the charging station.
  • the computer system of the present invention includes an intelligent device for pre-charging an extended-range plug-in hybrid electric vehicle.
  • An intelligent method and device for charging reservation for extended-range plug-in hybrid electric vehicles which makes multiple rounds of recommendations for reserved charging stations, selects a specific method to select the first batch of recommended charging stations based on the number of reserved charging records, predicts the number of idle fast and slow charging stations and the total idle number at the reserved charging time point based on the historical idle data of the charging stations, and selects the first round of final recommended reserved charging stations based on the idle number threshold; calculates the remaining SOC to reach the first round of final recommended reserved charging stations based on the map information and the power consumption calculation logic in pure electric mode, and recommends the second round of recommended reserved charging stations based on the remaining SOC; when the reserved time point is reached, calculates the SOC to reach the second round of recommended reserved charging stations based on the real-time traffic information on the map and the power consumption calculation logic in pure electric mode, and makes the final charging station recommendation based on the SOC and the real-time idle information of the fast and slow charging stations.
  • the specific method for recommending the first batch of charging stations is that when the number of scheduled charging records is less than a certain threshold (such as 500), the system calculates the y (configurable, such as 40) nearest charging stations within x km (configurable, such as 20km) near the starting point and obtains the charging station information; when it is greater than the threshold, the charging stations actually used by the user are first sorted by the number of times they are used, and the z (such as 50, configurable) charging stations with the most times of use are selected, and the distance between the scheduled charging departure point and the selected charging station is calculated. If it is less than or equal to the distance threshold (configurable), the charging station is selected. If the distance is greater than the threshold, for example, 20km, it will be retained as the recommended charging station for the first round; if it is greater than the distance threshold, it will be removed.
  • a certain threshold such as 500
  • the system calculates the y (configurable, such as 40) nearest charging stations within x km (configurable, such as
  • the idle fast and slow charging stations and the total idle number at the scheduled charging time are predicted from the historical idle data of the charging stations. This time point is accurate to the hour.
  • the method used to predict the idle number is time series prediction.
  • the time series model used is not limited to machine learning models such as LSTM/RNN.
  • the model accuracy evaluation standard used is the root mean square error ( R2 ) standard. According to the evaluation standard, the final machine learning model is selected to predict the idle fast and slow charging stations at the scheduled time. According to the predicted idle fast and slow charging numbers, the final first-round recommended charging stations are selected.
  • the pure electric mode power consumption calculation logic mentioned above takes into account the basic battery power consumption, the impact of ambient temperature and the customer's historical actual power consumption.
  • the basic battery power consumption takes into account the impact of vehicle speed and high-voltage battery SOC.
  • the customer's historical actual power represents the customer's historical actual demand driving power at a specific vehicle speed.
  • the path information needs to be converted into a speed segment map, and the SOC to reach the first round of final recommended reserved charging stations is calculated based on the speed segment map and the power consumption calculation logic.
  • the remaining SOC required to reach the second round of recommended charging stations needs to be calculated again based on the real-time traffic information on the map and the power consumption calculation logic of the pure electric mode. If the SOC is less than or equal to 0, the customer is prompted that the series mode is required to reach a certain scheduled charging station. If the remaining SOC is greater than 0, the real-time fast and slow charging idle information of the second round of recommended charging stations needs to be obtained. If it is greater than the fast and slow charging idle number threshold, it is sorted from large to small according to the remaining SOC as the final recommended charging station, and the corresponding driving route is recommended.
  • the present invention aims at the problem of charging reservation of extended-range plug-in hybrid electric vehicles and designs an extended-range plug-in hybrid electric vehicle.
  • An intelligent system and method for reserving charging for plug-in hybrid electric vehicles take into account the calculation method of the remaining SOC of the vehicle, the user's historical driving behavior habits, the historical and real-time usage information of the integrated charging station, and the map information to intelligently recommend the best reservable charging station and driving route for the driver.
  • This system can provide users with the best reservable and available charging station information and driving route information.
  • VCU vehicle control unit
  • PDCU Power Domain Controller
  • VIN Vehicle Identification Number

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Transportation (AREA)
  • Tourism & Hospitality (AREA)
  • Power Engineering (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Sustainable Energy (AREA)
  • Sustainable Development (AREA)
  • Development Economics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Economics (AREA)
  • Data Mining & Analysis (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Electric Propulsion And Braking For Vehicles (AREA)

Abstract

一种增程式插电混合动力汽车预约充电智能方法，步骤如下：首轮推荐：选择具体方法选取首批推荐充电站，对预约充电时间点的充电站空闲快慢充空闲数和总空闲数进行预测，选取首轮最终推荐预约充电站；二轮推荐：根据地图信息结合纯电模式下的耗电计算逻辑，计算到达首轮最终推荐预约充电站的剩余SOC，推荐第二轮推荐预约充电站；最终推荐：当到达预约时间点时，根据地图实时路况信息和纯电模式耗电计算逻辑，根据SOC和实时充电站快慢充空闲信息推荐最终充电站。还涉及一种增程式插电混合动力汽车预约充电智能装置和计算机系统。具有根据用户预约条件，安排最优预约充电站及路线的功能，可以广泛应用于增程式插电混合动力汽车上。

Description

一种增程式插电混合动力汽车预约充电智能方法、装置及计算机系统 技术领域
本发明涉及增程式插电混合动力汽车，特别是涉及一种增程式插电混合动力汽车预约充电智能方法、装置及计算机系统。
背景技术
增程式插电混合动力汽车能够有效应对国家对节能减排的要求并消除客户的里程焦虑，其兼具传统内燃机和纯电动汽车电机，可以减少对石油燃料的依赖和需求，改善汽车燃油经济性和排放性能。增程式插电混合动力通常具有以下几种驱动模式：1.纯电模式，此时汽车依靠高压电池给驱动电机提供电能，由驱动电机驱动汽车行驶；2.串联模式，发动机此时开始运行，一方面，发动机驱动发电机给高压电池充电；另一方面，发动机驱动发电机为驱动电机提供电能，以驱动汽车行驶；因此在电池电量很低时，可利用串联模式驱动汽车，消除用户里程焦虑问题。
针对新能源汽车，业内注意到其充电需求，并尝试提出相关解决方案。比如，国家电网公司的一件公开号为CN104779680A、发明名称为电动汽车预约充电控制方法及装置的发明申请，公开了一种电动汽车预约充电控制方法及装置。其中，该方法包括：获取预约充电信息和预先设置的优化控制参数；获取与预约充电信息预先绑定车辆的车辆状态信息；根据预约充电信息和车辆状态信息，确定车辆的预约充电方案集合；使用优化控制参数从预约充电方案集合中筛选得到推 荐充电方案。本发明解决了由于无法对电动车的预约充电进行优化，导致出现的充电设备资源浪费和用户充电体验欠佳等技术问题。
然而，该发明也存在如下缺点：1.该发明专利申请针对的是纯电动汽车，而本发明针对的是增程式插电混合动力汽车，在整车模式上有较大差异；2.未考虑驾驶员具体的驾驶习惯，未对驾驶员进行实际的驾驶模式和习惯用户行为分析；3.主要还是针对的是电网侧或者充电桩侧，对具体的车辆控制参数未做具体说明；4.未考虑实际道路情况对预约充电的影响。
另外一件由江苏金坛大迈汽车工程研究院有限公司和江苏金坛汽车工业有限公司申报、公开号为CN207683369U、实用新型名称为一种汽车预约充电系统的实用新型，公开了一种汽车预约充电系统，包括远程控制终端、TBOX、车载充电器OBC、电池管理系统BMS、整车控制器VCU，所述的远程控制终端与TBOX连接，所述的TBOX分别连接车载充电器OBC和电池管理系统BMS，所述的电池管理系统BMS与整车控制器VCU连接。该实用新型的优点在于：采用直接网络管理控制BMS和TBOX的关闭和启停，从而简化实现预约充电功能；通过手机远程设置预约时间进行充电，方便简化充电流程。与前面发明一样，其不足之处在于：1.没有区分具体的新能源车型，未对整车模式和控制进行详细描述；2.未考虑用户以往充电习惯和充电站本身情况、及实际道路情况。
发明内容
本发明的目的是为了克服上述背景技术的不足，提供一种增程式插电混合动力汽车预约充电智能方法、装置及计算机系统，使其具有根据用户预约条件，合理安排最优预约充电站及路线信息的功能。
本发明提供的一种增程式插电混合动力汽车预约充电智能方法， 对预约充电站进行多轮推荐，包括如下步骤：首轮推荐：根据预约充电记录数，选取首批推荐充电站，根据充电站历史空闲数据，对预约充电时间点的充电站空闲快慢充空闲数和总空闲数进行预测，并根据空闲数阈值，选取首轮最终推荐预约充电站；二轮推荐：根据地图信息，结合纯电模式下的耗电计算逻辑，计算到达首轮最终推荐预约充电站的剩余SOC，根据剩余SOC推荐第二轮推荐预约充电站；最终推荐：当到达预约时间点时，根据地图实时路况信息和纯电模式耗电计算逻辑，对到达第二轮推荐预约充电站的SOC进行计算，根据SOC和实时充电站快慢充空闲信息进行最终充电站推荐。
在上述技术方案中，所述首轮推荐步骤的具体过程如下：出发信息预约：通过车机或手机输入预约充电的出发地点和出发时间；第一预约记录获取：如果系统中用户预约充电记录小于n条，则系统计算出发点附近x km内的y个距离最近的充电站作为推荐充电站，并获取充电站信息；第二预约记录获取：如果系统中用户预约充电记录大于n条，首先对用户实际使用过的充电站进行使用次数排序，选取使用次数最多的z个充电站，计算出发地点与所选充电站的距离，若小于等于距离阈值则保留，作为推荐充电站，并获取充电站信息；大于距离阈值则去除；信息提取：从充电站历史数据系统中提取所推荐充电站过去m天的空闲充电枪数量信息。
在上述技术方案中，所述信息提取步骤包括以下过程：数据集合：将m天的推荐充电站快慢充空闲充电枪数量数据分为输入集和目标集，前m1天的数据作为输入数据集合，后m2天的数据作为目标数据集合，其中，m＝m1+m2，且m1>m2；快慢充空值填充：如果某个站m1天的快慢充数据存在空值，则采用m1天中的快充空闲数平均值μ1对快充空值进行填充，采用慢充空闲数平均值μ2对慢充空值进行填 充；归一化：对m1和m2天的快慢充数据分别进行归一化处理；时间序列分析：采用时间序列机器学习模型进行时间序列分析，采用均方根误差R2去评价时间序列模型，选择R2值最小的模型，预测驾驶员预约时间点某充电站快慢充空闲数，并作为首轮最终充电站推荐。
在上述技术方案中，所述归一化步骤就是min-max方法，归一化后的快充空闲数为：(fast–fastmin)/(fastmax–fastmin),同理归一化后的慢充空闲数为：(slow–slowfast)/(slowmax–slowmin),同理用目标集合m2的快充数平均值μ3和慢充数平均值μ4去填充目标数据集合的空值，同时采用目标集合的最大值fastTargetmax和fastTargetmin去归一化目标集。
在上述技术方案中，所述时间序列分析步骤中，预测驾驶员预约时间点某充电站快慢充空闲数的过程为：如果某站点最终预测快充空闲数量>fast0且慢充空闲数量>slow0，并且快充空闲数量与慢充空闲数量之和的总空闲数量>total0，则作为首轮最终充电站推荐。
在上述技术方案中，所述时间序列分析步骤中，所述时间序列机器学习模型包括但不限于LSTM\RNN模型。
在上述技术方案中，所述二轮推荐步骤的具体过程如下：地图信息获取：根据用户输入的出发点和首轮推荐的充电站，获取出发点到各充电站的地图信息；速度段图转换：根据实际地图路况信息，将路况信息转换成速度段图；剩余SOC计算：并根据车辆的实际SOC，结合纯电模式续驶里程标定表，获取实际电量消耗，则可计算车辆完全通过第一段路后的剩余SOC1；依次可计算通过第2段路、第3段路……以至第n端后的剩余SOCn；纯电模式选取：若在某段路后SOC小于0，则表明纯电模式无法到达推荐充电站，最终选择剩余SOCn>0即纯电模式可到达的充电站为第二轮推荐充电站，并提供可到达路线 信息；串联模式选取：如果最终SOCn<＝0,则提示该用户，需要采用串联模式，才能达到首轮推荐充电站中用作第二轮推荐的部分充电站。
在上述技术方案中，所述最终推荐步骤的具体过程如下：纯电模式SOC计算：当到达用户预约时间点时，从地图获取该时间点到达第二轮推荐充电站路线实际地图信息，按照二轮推荐步骤的方式重新计算纯电模式到达第二轮推荐充电站时的剩余SOC，如果计算得到剩余SOC<0，则提示用户到达该站需要使用串联模式；比较排序推荐：若剩余SOC>0，则作为推荐充电站，在充电站信息系统里查询推荐充电站的快充空闲数量、慢充空闲数量和总空闲数量，如果快充空闲数量大于fastLast，慢充空闲数量大于slowLast并且总空闲数量大于totalLast，则可作为最终推荐充电站，按照剩余SOC从大到小对最终推荐充电站排序，作为最终推荐充电站列表，并推荐对应行驶路线。
本发明又提供了一种增程式插电混合动力汽车预约充电智能装置，存储有计算机程序，所述计算机程序能够执行增程式插电混合动力汽车预约充电智能方法。
本发明还提供了一种计算机系统，该计算机系统包括增程式插电混合动力汽车预约充电智能装置。
本发明一种增程式插电混合动力汽车预约充电智能方法、装置及计算机系统，具有以下有益效果：
本发明主要针对增程式插电混合动力汽车，考虑实际路况、用户历史行为、车辆本身和充电站实际情况，基于云平台便宜、可靠、可扩展性好的优点，在云平台建立一套考虑车辆特性、用户历史充电行为、汽车前往充电站的路况信息及充电站信息等的增程式插电混合动力汽车预约充电智能系统和方法，可以为增程式插电混合动力汽车用 户提供最经济可用的预约充电站和行驶路线。
附图说明
图1为本发明增程式插电混合动力汽车的动力结构示意图；
图2为本发明增程式插电混合动力汽车预约充电智能方法的整体流程示意图；
图3为本发明增程式插电混合动力汽车预约充电智能方法中首轮推荐步骤的具体流程示意图；
图4为本发明增程式插电混合动力汽车预约充电智能方法中二轮推荐步骤的具体流程示意图；
图5为本发明增程式插电混合动力汽车预约充电智能方法中二轮推荐步骤第2.2子步骤的实际路况速度段图；
图6为本发明增程式插电混合动力汽车预约充电智能方法中最终推荐步骤的具体流程示意图；
图7为本发明增程式插电混合动力汽车预约充电智能装置的结构示意图；
图8为本发明计算机系统的结构示意图。
具体实施方式
下面结合附图及实施例对本发明作进一步的详细描述，但该实施例不应理解为对本发明的限制。
本发明涉及的增程式插电混合动力汽车动力结构如图1所示，其中发动机为汽油发动机。图中实线连接为机械连接，虚线连接为电气连接；存在两种驱动模式，电动模式和串联模式；1.当车辆处于电动模式时，此时发动机不工作，车辆依靠高压电池为驱动电机提供电能， 依靠驱动电机驱动车辆；2.当车辆处于串联模式时，发动机开始工作，一方面，发动机驱动发电机为高压电池充电，另一方面，发动机驱动发电机为驱动电机提供电能，驱动电机驱动车辆行驶。
参见图2，本发明增程式插电混合动力汽车预约充电智能方法设置在服务器、车辆的车机或控制器中，并与与车机或移动终端中的客户端连通；服务器、车辆的车机或控制器基于物联网获取充电站信息和地图信息，并从车辆中获取车辆剩余SOC等信息；车机或移动终端中的客户端用于供用户输入预约充电的出发地点和出发时间，显示地图、充电站位置信息等。本实施例中，服务器与充电站信息系统网络连接，从充电站信息系统中获取充电站的各项参数信息。充电站信息系统可以是外部已有系统，也可以作为本发明一部分。
本发明整体思路如下：
一、首轮推荐：根据预约充电记录数，选择具体方法选取首批推荐充电站，根据充电站历史空闲数据，对预约充电时间点的充电站空闲快慢充空闲数和总空闲数进行预测，并根据空闲数阈值，选取首轮最终推荐预约充电站；
参见图3，首轮预约充电推荐充电站逻辑图如下：
1.1.驾驶员通过车机或手机输入预约充电的出发地点和出发时间；
1.2.如果系统中用户预约充电记录小于n条(比如500，可配置)，则系统计算出发点附近x km(可设置，比如20km)内的y个(可设置，比如40)距离最近的充电站作为推荐充电站，并获取充电站信息；
1.3.如果系统中用户预约充电记录大于n条(比如500，可配置)，首先对用户实际使用过的充电站进行使用次数排序，选取使用次数最多的z个(比如50，可配置)充电站，计算出发地点与所选充电站 的距离，若小于等于距离阀值(可设置，比如20km)，则保留，作为推荐充电站，并获取充电站信息；若大于距离阀值则去除；
1.4.从充电站历史数据系统中提取所推荐充电站过去30天的空闲充电枪数量信息；
1.4.1.充电站信息系统中充电站空闲信息的采样频率为t小时(可设置，默认1h)，对30天的推荐充电站快慢充空闲充电枪数量数据进行以下处理：将30天的推荐充电站快慢充空闲充电枪数量数据分为输入集和目标集，前27天的数据作为输入数据集合，后3天的数据作为目标数据集合；
1.4.2.如果某个站27天的快慢充数据存在空值，则采用27天的快慢充空闲数平均值μ1(对应快充平均值)和μ2(对应慢充平均值)对快慢充空值分别进行填充；
1.4.3.对27天的快慢充数据分别进行归一化处理(min-max方法或者z-score方法)：
1.4.3.1.以min-max方法为例，归一化后的快充空闲数为：(fast–fastmin)/(fastmax–fastmin),同理归一化后的慢充空闲数为：(slow–slowfast)/(slowmax–slowmin),同理用目标集合(3天的数据)的快慢充数平均值μ3和μ4去填充目标数据集合(对应最后3天数据)的空值，同时采用目标集合的最大值fastTargetmax和fastTargetmin去归一化目标集；
1.4.4.采用时间序列机器学习模型(不局限于LSTM\RNN等模型)进行时间序列分析，采用均方根误差R2去评价时间序列模型，选择R2值最小的模型，预测驾驶员预约时间点(精确到h)某充电站快慢充空闲数。
1.4.4.1.如果某站点最终预测快充空闲数量>fast0(可设置，例如2) 且慢充空闲数量>slow0(可设置，例如2)且总空闲数量(快慢充空闲数量之和)>total0(可设置，例如2)，则作为首轮最终充电站推荐。
二、二轮推荐：根据地图信息，结合纯电模式下的耗电计算逻辑，计算到达首轮最终推荐预约充电站的剩余SOC，根据剩余SOC推荐第二轮推荐预约充电站；
参见图4，采用如下方法推荐第二轮预约充电充电站：
首先是计算汽车剩余SOC的技术性原理分析：其中纯电模式，实际纯电剩余SOC的计算逻辑在图4中有详细披露，表1为纯电模式电池消耗电量基础标定表，其中横坐标为高压电池剩余电量SOC，纵坐标是匀速车速，表中的数据表示当车速等于纵坐标车速时，横坐标SOC到0％时的每公里电量消耗百分比；表2表示环境温度修正系数，对表1电量消耗进行修正；表3表示功率修正系数，根据用户过去历史行为对不同对表1进行修正，具体的历史行为分析如下所述：1)当车辆行驶距离小于等于1000km时，采用默认功率修正表作为功率修正表，如表3中数值所示；2)当车辆行驶距离大于1000km时，根据用户历史行为，统计用户历史某车速(10km/h、20km/h、30km/h、40km/h、50km/h、60km/h、70km/h、80km/h、100km/h、120km/h、140km/h、160km/h等)下的功率，并求取平均值作为该车速下驱动需求功率，除以该车速匀速条件下的需求功率，作为该车速下的功率修正系数，其中匀速下的需求功率可通过实际道路试验获取，如果历史行为数据中无此速度，则采用表3默认值。

表1纯电模式续驶里程基础标定表
表2环境温度修正表
表3功率修正表
2.1.根据用户输入的出发点和首轮推荐的充电站，获取出发点到各充电站的地图信息(可有多条行驶路线)；
2.2.以某一推荐充电站为例，根据实际地图路况信息(车速等)，将路况信息转换成速度段图，如图5所示，该图中，第一段路最高车速为v1，如果该车行驶里程<50km，则设定该路段汽车行驶车速为v1，若该车行驶里程≥50km，则根据该客户历史通过该速度路段的平均车速为该路段的汽车行驶车速；
2.3.并根据车辆的实际SOC，结合纯电模式续驶里程标定表，获取实际电量消耗，则可计算车辆完全通过第一段路后的剩余SOC1；依次可计算通过第2段路、第3段路……第n端后的剩余SOCn；
2.4.若在某段路m后SOC小于0，则表明纯电模式无法到达推荐充电站，最终选择剩余SOCn>0(即纯电模式可到达)的充电站为第二轮推荐充电站，并提供可到达路线信息；
2.5.如果最终SOCn<＝0,则提示该用户，需要采用串联模式(发动机此时工作)，才能达到首轮推荐充电站中用作第二轮推荐的部分充电站。
三、最终推荐：当到达预约时间点时，根据地图实时路况信息和纯电模式耗电计算逻辑，对到达第二轮推荐预约充电站的SOC进行计算，根据SOC和实时充电站快慢充空闲信息进行最终充电站推荐。
参见图6，3.1.当到达用户预约时间点时，从地图获取该时间点到达第二轮推荐充电站路线实际地图信息，按照步骤4的方式重新计算纯电模式到达第二轮推荐充电站时的剩余SOC，如果计算得到剩余SOC<0，则提示用户到达该站需要使用串联模式；
3.2.若剩余SOC>0，则作为推荐充电站。在充电站信息系统里查询推荐充电站的快充空闲数、慢充空闲数和总空闲数，如果快充空闲数大于fastLast(可设置，比如2)且慢充空闲数大于slowLast(可设置，比如2)且总空闲数大于totalLast(可设置，比如2)，则可作为最终推荐充电站，按照剩余SOC从大到小对最终推荐充电站排序，作为最终推荐充电站列表，并推荐对应行驶路线。
参见图7，本发明增程式插电混合动力汽车预约充电智能装置，对预约充电站进行多轮推荐，包括如下内容：
首轮推荐模块：根据预约充电记录数，选择具体方法选取首批推荐充电站，根据充电站历史空闲数据，对预约充电时间点的充电站空闲快慢充空闲数和总空闲数进行预测，并根据空闲数阈值，选取首轮最终推荐预约充电站；
二轮推荐模块：根据地图信息，结合纯电模式下的耗电计算逻辑，计算到达首轮最终推荐预约充电站的剩余SOC，根据剩余SOC推荐第二轮推荐预约充电站；
最终推荐模块：当到达预约时间点时，根据地图实时路况信息和纯电模式耗电计算逻辑，对到达第二轮推荐预约充电站的SOC进行计算，根据SOC和实时充电站快慢充空闲信息进行最终充电站推荐。
参见图8，本发明计算机系统，该计算机系统包括增程式插电混合动力汽车预约充电智能装置。
本发明的技术原理和关键点：
一种增程式插电混合动力汽车预约充电智能方法及装置，对预约充电站进行多轮推荐，根据预约充电记录数，选择具体方法选取首批推荐充电站，根据充电站历史空闲数据，对预约充电时间点的充电站空闲快慢充空闲数和总空闲数进行预测，并根据空闲数阈值，选取首轮最终推荐预约充电站；根据地图信息，结合纯电模式下的耗电计算逻辑，计算到达首轮最终推荐预约充电站的剩余SOC，根据剩余SOC推荐第二轮推荐预约充电站；当到达预约时间点时，根据地图实时路况信息和纯电模式耗电计算逻辑，对到达第二轮推荐预约充电站的SOC进行计算，根据SOC和实时充电站快慢充空闲信息进行最终充电站推荐。其中，
1.如上所述首批推荐充电站具体方法，为当预约充电记录数小于某一阈值(如500条)，则系统计算出发点附近x km(可设置，比如20km)内的y个(可设置，比如40)距离最近的充电站并获取充电站信息；当大于阈值时，首先对用户实际使用过的充电站进行使用次数排序，选取使用次数最多的z个(比如50，可配置)充电站，计算预约充电出发地点与所选充电站的距离，若小于等于距离阀值(可 设置，比如20km)，则保留，作为首轮所推荐充电站；大于距离阀值，则去除。
2.如上所述，从充电站历史空闲数据里，对预约充电时间点的充电站空闲快慢充空闲数和总空闲数进行预测，此时间点精确到小时，对空闲数进行预测所采用的方法为时间序列预测，其使用的时间序列模型不局限于LSTM/RNN等机器学习模型，其采用的模型准确性评价标准为均方根误差(R2)标准，根据评价标准选择最终机器学习模型对预约时间充电站快慢充空闲数进行预测，根据预测快慢充空闲数选择最终首轮推荐充电站。
3.如上所述纯电模式耗电计算逻辑，考虑了电池基础消耗电量、环境温度影响和客户历史实际功率消耗影响，其中电池基础消耗电量考虑了车速和高压电池SOC的影响，客户历史实际功率，表示的是在特定车速下的客户历史实际需求驱动功率。
4.如上所述根据地图信息，可包含多条路径到达首轮最终推荐预约充电站，需将路径信息转换成速度段图，根据速度段图和耗电计算逻辑计算到达首轮最终推荐预约充电站的SOC。
5.如上所述到达预约时间点时，需根据地图实时路况信息和纯电模式耗电计算逻辑，对到达第二轮推荐预约充电站的剩余SOC再次进行计算，如果SOC小于等于0，则提示客户需要使用串联模式才能到达某预约充电站，如果剩余SOC大于0，则需获取第二轮推荐预约充电站实时快慢充空闲信息，若大于快慢充空闲数阈值，则按照剩余SOC进行从大到小排序，作为最终推荐充电站，并推荐对应行驶路线。
本发明技术方案带来的有益效果如下：
本发明针对增程式插电混合动力汽车预约充电问题，设计增程式 插电混合动力汽车预约充电智能系统及方法，该系统和方法考虑了汽车剩余SOC计算方法，考虑用户历史驾驶行为习惯，综合充电站的历史和实时使用信息，结合地图信息，为驾驶员智能推荐最优的可预约充电站和行驶路线，采用此系统，可为用户提供最优的可预约且可用的充电站信息及行驶路线信息。
缩略语和关键术语定义
VCU：整车控制器；
PDCU:动力域控制器
VIN：车辆识别码
SOC：电池电量
显然，本领域的技术人员可以对本发明进行各种改动和变型而不脱离本发明的精神和范围。这样，倘若本发明的这些修改和变型属于本发明权利要求及其等同技术的范围之内，则本发明也意图包含这些改动和变型在内。
本说明书中未作详细描述的内容属于本领域专业技术人员公知的现有技术。

Claims (10)

  1. 一种增程式插电混合动力汽车预约充电智能方法，其特征在于：对预约充电站进行多轮推荐，包括如下步骤：
    首轮推荐：根据预约充电记录数，选取首批推荐充电站，根据充电站历史空闲数据，对预约充电时间点的充电站空闲快慢充空闲数和总空闲数进行预测，并根据空闲数阈值，选取首轮最终推荐预约充电站；
    二轮推荐：根据地图信息，结合纯电模式下的耗电计算逻辑，计算到达首轮最终推荐预约充电站的剩余SOC，根据剩余SOC推荐第二轮推荐预约充电站；
    最终推荐：当到达预约时间点时，根据地图实时路况信息和纯电模式耗电计算逻辑，对到达第二轮推荐预约充电站的SOC进行计算，根据SOC和实时充电站快慢充空闲信息进行最终充电站推荐。
  2. 根据权利要求1所述的增程式插电混合动力汽车预约充电智能方法，其特征在于：所述首轮推荐步骤的具体过程如下：
    出发信息预约：通过车机或手机输入预约充电的出发地点和出发时间；
    第一预约记录获取：如果系统中用户预约充电记录小于n条，则系统计算出发点附近x km内的y个距离最近的充电站作为推荐充电站，并获取充电站信息；
    第二预约记录获取：如果系统中用户预约充电记录大于n条，首先对用户实际使用过的充电站进行使用次数排序，选取使用次数最多的z个充电站，计算出发地点与所选充电站的距离，若小于等于距离阈值则保留，作为推荐充电站，并获取充电站信息；大于距离阈值则去除；
    信息提取：从充电站历史数据系统中提取所推荐充电站过去m天的空闲充电枪数量信息。
  3. 根据权利要求2所述的增程式插电混合动力汽车预约充电智能方法，其特征在于：所述信息提取步骤包括以下过程：
    数据集合：将m天的推荐充电站快慢充空闲充电枪数量数据分为输入集和目标集，前m1天的数据作为输入数据集合，后m2天的数据作为目标数据集合，其中，m＝m1+m2，且m1>m2；
    快慢充空值填充：如果某个站m1天的快慢充数据存在空值，则采用m1天中的快充空闲数平均值μ1对快充空值进行填充，采用慢充空闲数平均值μ2对慢充空值进行填充；
    归一化：对m1和m2天的快慢充数据分别进行归一化处理；
    时间序列分析：采用时间序列机器学习模型进行时间序列分析，采用均方根误差R2去评价时间序列模型，选择R2值最小的模型，预测驾驶员预约时间点某充电站快慢充空闲数，并作为首轮最终充电站推荐。
  4. 根据权利要求3所述的增程式插电混合动力汽车预约充电智能方法，其特征在于：所述归一化步骤就是min-max方法，归一化后的快充空闲数为：(fast–fastmin)/(fastmax–fastmin),同理归一化后的慢充空闲数为：(slow–slowfast)/(slowmax–slowmin),同理用目标集合m2的快充数平均值μ3和慢充数平均值μ4去填充目标数据集合的空值，同时采用目标集合的最大值fastTargetmax和fastTargetmin去归一化目标集。
  5. 根据权利要求4所述的增程式插电混合动力汽车预约充电智能方法，其特征在于：所述时间序列分析步骤中，预测驾驶员预约时间点某充电站快慢充空闲数的过程为：
    如果某站点最终预测快充空闲数量>fast0且慢充空闲数量>slow0，并且快充空闲数量与慢充空闲数量之和的总空闲数量>total0，则作为首轮最终充电站推荐。
  6. 根据权利要求5所述的增程式插电混合动力汽车预约充电智能方法，其特征在于：所述时间序列分析步骤中，所述时间序列机器学习模型包括但不限于LSTM\RNN模型。
  7. 根据权利要求6所述的增程式插电混合动力汽车预约充电智能方法，其特征在于：所述二轮推荐步骤的具体过程如下：
    地图信息获取：根据用户输入的出发点和首轮推荐的充电站，获取出发点到各充电站的地图信息；
    速度段图转换：根据实际地图路况信息，将路况信息转换成速度段图；
    剩余SOC计算：并根据车辆的实际SOC，结合纯电模式续驶里程标定表，获取实际电量消耗，则可计算车辆完全通过第一段路后的剩余SOC1；依次可计算通过第2段路、第3段路……以至第n端后的剩余SOCn；
    纯电模式选取：若在某段路后SOC小于0，则表明纯电模式无法到达推荐充电站，最终选择剩余SOCn>0即纯电模式可到达的充电站为第二轮推荐充电站，并提供可到达路线信息；
    串联模式选取：如果最终SOCn<＝0,则提示该用户，需要采用串联模式，才能达到首轮推荐充电站中用作第二轮推荐的部分充电站。
  8. 根据权利要求7所述的增程式插电混合动力汽车预约充电智能方法，其特征在于：所述最终推荐步骤的具体过程如下：
    纯电模式SOC计算：当到达用户预约时间点时，从地图获取该时间点到达第二轮推荐充电站路线实际地图信息，按照二轮推荐步骤 的方式重新计算纯电模式到达第二轮推荐充电站时的剩余SOC，如果计算得到剩余SOC<0，则提示用户到达该站需要使用串联模式；
    比较排序推荐：若剩余SOC>0，则作为推荐充电站，在充电站信息系统里查询推荐充电站的快充空闲数量、慢充空闲数量和总空闲数量，如果快充空闲数量大于fastLast，慢充空闲数量大于slowLast并且总空闲数量大于totalLast，则可作为最终推荐充电站，按照剩余SOC从大到小对最终推荐充电站排序，作为最终推荐充电站列表，并推荐对应行驶路线。
  9. 一种增程式插电混合动力汽车预约充电智能装置，存储有计算机程序，其特征在于：所述计算机程序能够执行如权利要求1～8所述的增程式插电混合动力汽车预约充电智能方法。
  10. 一种计算机系统，其特征在于：该计算机系统包括如权利要求9所述的增程式插电混合动力汽车预约充电智能装置。
PCT/CN2023/118295 2023-05-25 2023-09-12 一种增程式插电混合动力汽车预约充电智能方法、装置及计算机系统 Ceased WO2024239494A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202310599400.8A CN116562405A (zh) 2023-05-25 2023-05-25 一种增程式插电混合动力汽车预约充电智能方法、装置及计算机系统
CN202310599400.8 2023-05-25

Publications (1)

Publication Number Publication Date
WO2024239494A1 true WO2024239494A1 (zh) 2024-11-28

Family

ID=87491426

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/118295 Ceased WO2024239494A1 (zh) 2023-05-25 2023-09-12 一种增程式插电混合动力汽车预约充电智能方法、装置及计算机系统

Country Status (2)

Country Link
CN (1) CN116562405A (zh)
WO (1) WO2024239494A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119737970A (zh) * 2025-03-04 2025-04-01 陕西科技大学 一种基于受控Petri网的新能源汽车充电引导方法及系统
CN120579800A (zh) * 2025-08-05 2025-09-02 合肥工业大学 基于驾驶员充电偏好的电动汽车充电站推荐方法、装置

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116562405A (zh) * 2023-05-25 2023-08-08 东风汽车集团股份有限公司 一种增程式插电混合动力汽车预约充电智能方法、装置及计算机系统
CN117172409B (zh) * 2023-09-05 2024-05-03 河海大学 基于光伏能源的电动汽车的智能充电方法
CN117284153B (zh) * 2023-09-28 2025-02-11 赛力斯汽车有限公司 一种里程预测方法、装置、电子设备及存储介质
CN117728589B (zh) * 2024-02-08 2024-04-26 山西同鑫达电气工程有限公司 配电箱用电监测方法、装置、设备及介质
CN119821354B (zh) * 2025-02-21 2025-10-17 赛力斯汽车有限公司 增程式电动汽车补能控制方法、装置和计算机设备
CN120196816B (zh) * 2025-05-27 2025-08-05 人民出行(南宁)科技有限公司 一种共享电单车与充换电一体化基站智能交互动态资源推荐方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112115350A (zh) * 2020-08-27 2020-12-22 上海电享信息科技有限公司 一种智慧城市充电智能推荐方法和系统
JP2021063766A (ja) * 2019-10-16 2021-04-22 アユダンテ株式会社 電気自動車用カーナビゲーションのシステム、方法、および、プログラム
CN115009073A (zh) * 2022-07-01 2022-09-06 苏州回归线信息科技有限公司 一种基于车路协同的自动驾驶车辆智能充电方法和系统
CN115293846A (zh) * 2022-07-28 2022-11-04 东风汽车集团股份有限公司 一种基于协同过滤的用户充电桩推荐方法及设备
CN115587246A (zh) * 2022-09-28 2023-01-10 东风汽车集团股份有限公司 充电站推荐方法、装置、设备及可读存储介质
CN116562405A (zh) * 2023-05-25 2023-08-08 东风汽车集团股份有限公司 一种增程式插电混合动力汽车预约充电智能方法、装置及计算机系统

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102024999B (zh) * 2010-11-16 2013-05-01 上海交通大学 电动车行动力管理系统
CN105730278A (zh) * 2016-03-16 2016-07-06 广州橙行智动汽车科技有限公司 一种电动汽车智能充电管理系统
CN108983638B (zh) * 2017-05-31 2023-06-16 国网江苏省电力公司常州供电公司 电动汽车充电推荐系统及方法
CN112874370B (zh) * 2021-01-18 2022-09-06 山东科技大学 一种电动汽车预约-违约充电方法及系统
CN115730145A (zh) * 2022-11-24 2023-03-03 重庆长安汽车股份有限公司 一种充电站推荐方法、系统、电子设备及存储介质
CN115860839A (zh) * 2022-12-15 2023-03-28 中国第一汽车股份有限公司 一种基于大数据分析的充电站推荐方法及装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2021063766A (ja) * 2019-10-16 2021-04-22 アユダンテ株式会社 電気自動車用カーナビゲーションのシステム、方法、および、プログラム
CN112115350A (zh) * 2020-08-27 2020-12-22 上海电享信息科技有限公司 一种智慧城市充电智能推荐方法和系统
CN115009073A (zh) * 2022-07-01 2022-09-06 苏州回归线信息科技有限公司 一种基于车路协同的自动驾驶车辆智能充电方法和系统
CN115293846A (zh) * 2022-07-28 2022-11-04 东风汽车集团股份有限公司 一种基于协同过滤的用户充电桩推荐方法及设备
CN115587246A (zh) * 2022-09-28 2023-01-10 东风汽车集团股份有限公司 充电站推荐方法、装置、设备及可读存储介质
CN116562405A (zh) * 2023-05-25 2023-08-08 东风汽车集团股份有限公司 一种增程式插电混合动力汽车预约充电智能方法、装置及计算机系统

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119737970A (zh) * 2025-03-04 2025-04-01 陕西科技大学 一种基于受控Petri网的新能源汽车充电引导方法及系统
CN120579800A (zh) * 2025-08-05 2025-09-02 合肥工业大学 基于驾驶员充电偏好的电动汽车充电站推荐方法、装置

Also Published As

Publication number Publication date
CN116562405A (zh) 2023-08-08

Similar Documents

Publication Publication Date Title
WO2024239494A1 (zh) 一种增程式插电混合动力汽车预约充电智能方法、装置及计算机系统
CN111452794B (zh) 一种确定能耗的方法及装置和确定驾驶策略的方法及装置
CN109808541B (zh) 一种电动汽车充电方法及系统
Bingham et al. Impact of driving characteristics on electric vehicle energy consumption and range
Zhang et al. Role of terrain preview in energy management of hybrid electric vehicles
Zhang et al. Route preview in energy management of plug-in hybrid vehicles
CN105095611B (zh) 一种高速公路电动汽车快速充电站排队方法
CN113085655B (zh) 一种车载电动汽车综合服务系统
CN102959418B (zh) 获取电池的劣化度的方法和系统
CN108773279A (zh) 一种电动汽车充电路径规划方法及装置
CN112319462B (zh) 一种插电式混合动力汽车能量管理方法
CN112950128A (zh) 一种基于大数据融合的智能物流运输系统及方法
CN114001989B (zh) 一种基于工况识别的单车空调能耗预测方法及预测装置
CN108955711A (zh) 一种应用于电动汽车智能充放电的导航方法
CN103049942A (zh) 车内传感器数据的获取和集合的平均性能指标的呈报
US20120010769A1 (en) Method For Optimizing The Power Consumption Of A Hybrid And Plug-In Vehicle, And Hybrid And Plug-In Vehicle Implementing Said Method
CN110716527A (zh) 一种基于运动学片段的车辆能耗分析方法及分析系统
CN114722595A (zh) 一种含有换电站的微电网优化运行方法
Karden Development trends for future automobiles and their demand on the battery
EP4390786A1 (en) Method for optimizing the energy management of a fleet of electric transportation vehicles, more particularly a fleet of electric buses
Bader An energy management strategy for plug-in hybrid electric vehicles
Payri et al. On a stochastic approach of the ECMS method for energy management in hybrid electric vehicles
CN117901708B (zh) 车辆充电方法、装置、电子设备和存储介质
CN119537790B (zh) 一种新能源汽车充放电策略优化方法
CN120403695B (zh) 电动车充电路径规划方法和装置

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: 23938163

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE