CN116572799B - Power battery charge duration prediction method, system and terminal based on deep learning - Google Patents
Power battery charge duration prediction method, system and terminal based on deep learning Download PDFInfo
- Publication number
- CN116572799B CN116572799B CN202310855033.3A CN202310855033A CN116572799B CN 116572799 B CN116572799 B CN 116572799B CN 202310855033 A CN202310855033 A CN 202310855033A CN 116572799 B CN116572799 B CN 116572799B
- Authority
- CN
- China
- Prior art keywords
- power consumption
- battery
- road section
- real
- electric quantity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000013135 deep learning Methods 0.000 title claims abstract description 22
- 230000008569 process Effects 0.000 claims abstract description 30
- 238000003062 neural network model Methods 0.000 claims abstract description 18
- 230000005611 electricity Effects 0.000 claims description 22
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000008859 change Effects 0.000 claims description 7
- 238000007599 discharging Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 2
- 238000005265 energy consumption Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
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
- 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]
-
- 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
-
- 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]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- 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]
- G01R31/382—Arrangements for monitoring battery or accumulator variables, e.g. SoC
-
- 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]
- G01R31/382—Arrangements for monitoring battery or accumulator variables, e.g. SoC
- G01R31/3842—Arrangements for monitoring battery or accumulator variables, e.g. SoC combining voltage and current measurements
-
- 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
- B60L2240/00—Control parameters of input or output; Target parameters
- B60L2240/40—Drive Train control parameters
- B60L2240/54—Drive Train control parameters related to batteries
-
- 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
Abstract
The application discloses a power battery charging and endurance prediction method, a system and a terminal based on deep learning, which relate to the technical field of power batteries and have the technical scheme that: according to the application, the historical state data of the target battery in the process of vehicle driving is directly collected and used as sample data to train and construct a deep neural network model, the influence of the vehicle driving habit caused by a driver on battery electric quantity condition estimation is not required to be considered, and the required sample data is relatively less; the prediction power consumption of each road section in the navigation path is obtained by prediction analysis based on the real-time power consumption obtained after the target vehicle travels a certain distance in the navigation path and the power consumption of the reference battery in other reference vehicles as reference data, and the prediction of the power battery charging and cruising aiming at the real-time navigation information is realized globally under the condition of considering the influence factors of road conditions and driving habits.
Description
Technical Field
The application relates to the technical field of power batteries, in particular to a power battery charging duration prediction method, a power battery charging duration prediction system and a power battery terminal based on deep learning.
Background
The battery state of charge refers to the ratio of the remaining capacity of the battery after a period of use to the capacity before the battery is not used, and because the remaining capacity of the battery cannot be directly measured, the battery can only be estimated through parameters such as the voltage and the discharge current of the battery, and the parameters are also influenced by various uncertain factors such as the surface temperature change of the battery and the running state of an automobile, so that the accurate estimation of the condition of the battery is the current research focus.
Therefore, in the prior art, it is described that state information of a vehicle battery under different driving habits of a vehicle is collected through simulation, and a prediction model based on deep learning is constructed according to the state information, so as to realize estimation of the battery power condition. However, the prediction model can only estimate the battery power condition at the current time, the power battery continuous voyage mileage of the new energy automobile needs to be calculated by combining the battery residual power and the standard energy consumption required by the unit mileage, and the standard energy consumption required by the unit mileage of the new energy automobile in the actual running process is influenced by road conditions in a navigation path, such as speed limit, traffic congestion, traffic lights and the like, so that the standard energy consumption required by the unit mileage is difficult to accurately obtain the power battery charge continuous voyage prediction result, reliable reference cannot be provided for the new energy automobile navigation driving, and the situation that the vehicle battery cannot be charged in time and cannot normally run exists.
Therefore, how to study and design a method, a system and a terminal for predicting the charge duration of a power battery based on deep learning, which can overcome the defects, is a problem which needs to be solved in the current state of the art.
Disclosure of Invention
In order to solve the defects in the prior art, the application aims to provide a power battery charging and cruising prediction method, a system and a terminal based on deep learning, which are based on real-time consumption electricity obtained after a target vehicle travels a certain distance in a navigation path, and further take the electricity consumption of a reference battery in other reference vehicles as reference data to predict and analyze to obtain predicted consumption electricity of each road section in the navigation path, and the power battery charging and cruising prediction for real-time navigation information is realized globally under the condition of considering influence factors of road conditions and driving habits.
The technical aim of the application is realized by the following technical scheme:
in a first aspect, a method for predicting the charging duration of a power battery based on deep learning is provided, including the following steps:
acquiring real-time navigation information of a target vehicle and initial residual electric quantity of a target battery configured by the target vehicle;
acquiring historical state data of discharging of a target battery in the running process of a vehicle, and training and constructing a deep neural network model according to the historical state data;
collecting real-time state data of a target battery in an initial stage of a navigation path corresponding to real-time navigation information, and inputting the real-time state data into a deep neural network model to estimate and obtain real-time power consumption of the target battery in the process that the target vehicle finishes driving in the initial stage;
screening reference batteries corresponding to the reference vehicles with the same navigation path as the real-time navigation information from the database, and determining electric quantity consumption difference parameters of all road sections in the navigation path according to historical electric quantity consumption of all the reference batteries along with mileage change in the navigation path;
and calculating according to the real-time power consumption and the power consumption difference parameters to obtain the predicted power consumption of the target battery in each road section in the navigation path, and obtaining the cruising result of the target battery for supplying the target vehicle for navigation driving by combining the initial residual power prediction.
Further, the historical state data comprises data of changes of battery current, battery voltage, battery temperature and battery consumption with time;
the battery current, the battery voltage and the battery temperature form an input vector, and the battery consumption is a label.
Further, the real-time consumption electricity estimating process specifically includes:
the real-time status data includes data of battery current, battery voltage and battery temperature over time;
after the real-time state data is input into the deep neural network model, outputting to obtain estimated power consumption at each moment in the initial stage;
and carrying out accumulated summation on the estimated consumed electric quantity at each moment to obtain the real-time consumed electric quantity of the target battery in the initial stage.
Further, the determining process of the electric quantity consumption difference parameter specifically includes:
determining the road section power consumption of each road section in the navigation path according to the historical power consumption aiming at a single reference battery;
calculating the power consumption difference ratio of each road section according to the ratio of the power consumption of each road section to the power consumption of the first road section;
and determining the power consumption difference parameters of the corresponding road sections according to the average value of the power consumption difference ratios of all the reference batteries in the same road section.
Further, the calculation formula of the electric quantity consumption difference parameter specifically includes:
;
wherein ,indicate->Road section electricity consumption of each road section; />Indicating a location in the historical power consumptionConsumption of electricity at mileage +.>The mileage is a single road section; />Indicating a location in the historical power consumptionThe power consumption at the mileage; />Indicate->Road section electricity consumption of each road section; />Indicate->The power consumption difference ratio of each road section; />Indicate->The electric quantity consumption difference parameters of the individual road sections; />Representing the number of reference cells; />Indicate->The first part of the reference cell>Power consumption difference ratio of each road section.
Further, the calculation formula of the electric quantity consumption difference parameter specifically includes:
;
wherein ,indicate->Road segment consumption of individual road segmentsAn electric quantity; />Indicating a location in the historical power consumptionConsumption of electricity at mileage +.>The mileage is a single road section; />Indicating a location in the historical power consumptionThe power consumption at the mileage; />Indicate->Road section electricity consumption of each road section; />Indicate->The power consumption difference ratio of each road section; />Representing the number of reference cells; />Indicate->The first part of the reference cell>The power consumption difference ratio of each road section; />Representing all reference cellsIn->Average value of electric quantity consumption difference ratio of each road section; />Indicate->The electric quantity consumption difference parameters of the individual road sections; />Representing a ratio fluctuation amplitude threshold; />Representing a reference number of batteries that meet a ratio fluctuation amplitude threshold; />Indicate->The first part of the reference cell>Power consumption difference ratio of each road section.
Further, the calculating process of the predicted power consumption specifically includes:
determining the number of sections of the covered sections in the initial stage, and determining the real-time power consumption of a single section in the initial stage according to the ratio of the real-time power consumption of the target battery to the number of sections;
carrying out weighted average calculation according to the electric quantity consumption difference parameters of the covered road sections in the initial stage to obtain electric quantity consumption difference parameters of the single road section in the initial stage;
calculating to obtain a parameter ratio by using the ratio of the electric quantity consumption difference parameters of each road section to the electric quantity consumption difference parameters of the single road section in the initial stage;
the predicted power consumption of each road section is calculated by the product of the power consumption difference parameter and the parameter ratio of the single road section in the initial stage.
Further, the prediction analysis process of the cruising result specifically includes:
if the sum of the predicted power consumption and the real-time power consumption of each road section is greater than or equal to the initial residual power, outputting a place which can be reached by the navigation running of the target battery supply target vehicle;
and if the sum of the predicted power consumption and the real-time power consumption of each road section is smaller than the initial residual power, outputting the final residual power of the target battery for supplying the target vehicle after navigation running is completed.
In a second aspect, a power battery charging duration prediction system based on deep learning is provided, including:
the information acquisition module is used for acquiring real-time navigation information of the target vehicle and initial residual electric quantity of a target battery configured by the target vehicle;
the model building module is used for acquiring historical state data of discharging of the target battery in the running process of the vehicle and training and building a deep neural network model according to the historical state data;
the data acquisition module is used for acquiring real-time state data of the target battery in an initial stage of a navigation path corresponding to the real-time navigation information, and inputting the real-time state data into the deep neural network model to estimate and obtain real-time consumption electric quantity of the target battery in a process that the target vehicle finishes driving in the initial stage;
the difference reference module is used for screening reference batteries corresponding to the reference vehicles with the same navigation path as the real-time navigation information from the database, and determining electric quantity consumption difference parameters of each road section in the navigation path according to the historical electric quantity consumption of all the reference batteries along with the mileage change in the navigation path;
and the cruising prediction module is used for calculating the predicted power consumption of each road section of the target battery in the navigation path according to the real-time power consumption and the power consumption difference parameter, and obtaining the cruising result of the target battery for supplying the target vehicle for navigation driving by combining the initial residual power prediction.
In a third aspect, a computer terminal is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the deep learning-based power battery charging duration prediction method according to any one of the first aspects when the program is executed.
Compared with the prior art, the application has the following beneficial effects:
1. according to the deep learning-based power battery charge duration prediction method, the real-time consumption obtained after a target vehicle travels a certain distance in a navigation path is used as a basis, the electric quantity consumption of a reference battery in other reference vehicles is used as reference data, the predicted consumption of each road section in the navigation path is obtained through prediction analysis, and the power battery charge duration prediction for real-time navigation information is realized globally under the condition of considering the influence factors of road conditions and driving habits;
2. according to the application, the historical state data of the target battery in the process of vehicle driving is directly collected and used as sample data to train and construct a deep neural network model, the influence of the vehicle driving habit caused by a driver on battery electric quantity condition estimation is not required to be considered, and the required sample data is relatively less;
3. in the calculation process of the electric quantity consumption difference parameters, the application filters the electric quantity consumption difference ratio with partial abnormal fluctuation according to the ratio fluctuation amplitude threshold, thereby improving the accuracy of the calculated electric quantity consumption difference parameters;
4. the application realizes the conversion of the real-time power consumption and the power consumption difference parameters between the initial stage and the road section according to the road section condition covered by the initial stage, and can dynamically predict the charging and the endurance of the power battery along with the update of the real-time navigation information.
Drawings
The accompanying drawings, which are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application. In the drawings:
FIG. 1 is a flow chart in embodiment 1 of the present application;
fig. 2 is a system block diagram in embodiment 2 of the present application.
Detailed Description
For the purpose of making apparent the objects, technical solutions and advantages of the present application, the present application will be further described in detail with reference to the following examples and the accompanying drawings, wherein the exemplary embodiments of the present application and the descriptions thereof are for illustrating the present application only and are not to be construed as limiting the present application.
Example 1: the power battery charge duration prediction method based on deep learning, as shown in fig. 1, comprises the following steps:
step S1: acquiring real-time navigation information of a target vehicle and initial residual electric quantity of a target battery configured by the target vehicle; the real-time navigation information comprises information such as a starting point, an intermediate path and the like;
step S2: acquiring historical state data of discharging of a target battery in the running process of a vehicle, and training and constructing a deep neural network model according to the historical state data;
step S3: collecting real-time state data of a target battery in an initial stage of a navigation path corresponding to real-time navigation information, and inputting the real-time state data into a deep neural network model to estimate and obtain real-time power consumption of the target battery in the process that the target vehicle finishes driving in the initial stage;
step S4: screening reference batteries corresponding to the reference vehicles with the same navigation path as the real-time navigation information from the database, and determining electric quantity consumption difference parameters of all road sections in the navigation path according to historical electric quantity consumption of all the reference batteries along with mileage change in the navigation path; the historical power consumption is an accumulated value that is 0 at the starting point and gradually accumulates over time;
step S5: and calculating according to the real-time power consumption and the power consumption difference parameters to obtain the predicted power consumption of the target battery in each road section in the navigation path, and obtaining the cruising result of the target battery for supplying the target vehicle for navigation driving by combining the initial residual power prediction.
In the present embodiment, the historical state data includes, but is not limited to, data of battery current, battery voltage, battery temperature, and battery consumption amount over time; the battery current, the battery voltage and the battery temperature form an input vector, and the battery consumption is a label. It should be noted that, the historical state data may be obtained by sampling in real time; historical state data may also be obtained using interval sampling, but fitting of the obtained data is required.
The real-time consumption electricity estimation process specifically comprises the following steps: the real-time status data includes data of battery current, battery voltage and battery temperature over time; after the real-time state data is input into the deep neural network model, outputting to obtain estimated power consumption at each moment in the initial stage; and carrying out accumulated summation on the estimated consumed electric quantity at each moment to obtain the real-time consumed electric quantity of the target battery in the initial stage.
In this embodiment, the determining process of the power consumption difference parameter specifically includes: determining the road section power consumption of each road section in the navigation path according to the historical power consumption aiming at a single reference battery; calculating the power consumption difference ratio of each road section according to the ratio of the power consumption of each road section to the power consumption of the first road section; and directly or indirectly determining the electric quantity consumption difference parameters of the corresponding road sections according to the average value of the electric quantity consumption difference ratios of all the reference batteries in the same road section.
If the electric quantity consumption difference parameters of the corresponding road sections are directly determined according to the average value of the electric quantity consumption difference ratios of all the reference batteries in the same road section, the calculation formula of the electric quantity consumption difference parameters is specifically as follows:
;
wherein ,indicate->Road section electricity consumption of each road section; />Indicating a location in the historical power consumptionConsumption of electricity at mileage +.>The mileage is a single road section; />Indicating a location in the historical power consumptionThe power consumption at the mileage; />Indicate->Road section electricity consumption of each road section; />Indicate->The power consumption difference ratio of each road section; />Indicate->The electric quantity consumption difference parameters of the individual road sections; />Representing the number of reference cells; />Indicate->The first part of the reference cell>Power consumption difference ratio of each road section.
If the electric quantity consumption difference parameters of the corresponding road sections are indirectly determined by the average value of the electric quantity consumption difference ratios of all the reference batteries in the same road section, the calculation formula of the electric quantity consumption difference parameters is specifically as follows:
;
wherein ,indicate->Road section electricity consumption of each road section; />Indicating a location in the historical power consumptionConsumption of electricity at mileage +.>The mileage is a single road section; />Indicating a location in the historical power consumptionThe power consumption at the mileage; />Indicate->Road section electricity consumption of each road section; />Indicate->The power consumption difference ratio of each road section; />Representing the number of reference cells; />Indicate->The first part of the reference cell>The power consumption difference ratio of each road section; />Indicating that all reference cells are at +.>Average value of electric quantity consumption difference ratio of each road section; />Indicate->The electric quantity consumption difference parameters of the individual road sections; />Representing a ratio fluctuation amplitude threshold; />Representing a reference number of batteries that meet a ratio fluctuation amplitude threshold; />Indicate->The first part of the reference cell>Power consumption difference ratio of each road section.
The calculation process of the predicted power consumption comprises the following steps: determining the number of sections of the covered sections in the initial stage, and determining the real-time power consumption of a single section in the initial stage according to the ratio of the real-time power consumption of the target battery to the number of sections; carrying out weighted average calculation according to the electric quantity consumption difference parameters of the covered road sections in the initial stage to obtain electric quantity consumption difference parameters of the single road section in the initial stage; calculating to obtain a parameter ratio by using the ratio of the electric quantity consumption difference parameters of each road section to the electric quantity consumption difference parameters of the single road section in the initial stage; the predicted power consumption of each road section is calculated by the product of the power consumption difference parameter and the parameter ratio of the single road section in the initial stage.
For example, the navigation path is divided into a plurality of sections each having a section of 10 km, and the power consumption difference parameters of the corresponding four sections are 1, 1.1, 1.0, and 0.9, respectively. If the total length of the initial stage is 25 km, the number of segments is 2.5, and the power consumption difference parameter of the single road segment in the initial stage is: (1×0.4+1.1×0.4+1.0×0.2) =1.04. It should be noted that the first road section can also be directly selected in the initial stage, and the calculation process is simpler.
The prediction analysis process of the endurance result specifically comprises the following steps: if the sum of the predicted power consumption and the real-time power consumption of each road section is greater than or equal to the initial residual power, outputting a place which can be reached by the navigation running of the target battery supply target vehicle; and if the sum of the predicted power consumption and the real-time power consumption of each road section is smaller than the initial residual power, outputting the final residual power of the target battery for supplying the target vehicle after navigation running is completed.
Example 2: the power battery charge duration prediction system based on deep learning, as shown in fig. 2, comprises an information acquisition module, a model construction module, a data acquisition module, a difference reference module and a duration prediction module.
The information acquisition module is used for acquiring real-time navigation information of the target vehicle and initial residual electric quantity of a target battery configured by the target vehicle; the model building module is used for acquiring historical state data of discharging of the target battery in the running process of the vehicle and training and building a deep neural network model according to the historical state data; the data acquisition module is used for acquiring real-time state data of the target battery in an initial stage of a navigation path corresponding to the real-time navigation information, and inputting the real-time state data into the deep neural network model to estimate and obtain real-time consumption electric quantity of the target battery in a process that the target vehicle finishes driving in the initial stage; the difference reference module is used for screening reference batteries corresponding to the reference vehicles with the same navigation path as the real-time navigation information from the database, and determining electric quantity consumption difference parameters of each road section in the navigation path according to the historical electric quantity consumption of all the reference batteries along with the mileage change in the navigation path; and the cruising prediction module is used for calculating the predicted power consumption of each road section of the target battery in the navigation path according to the real-time power consumption and the power consumption difference parameter, and obtaining the cruising result of the target battery for supplying the target vehicle for navigation driving by combining the initial residual power prediction.
Working principle: the application takes the real-time consumption obtained after the target vehicle travels a certain distance in the navigation path as the basis, and takes the electric quantity consumption of the reference battery in other reference vehicles as the reference data, so as to obtain the predicted consumption electric quantity of each road section in the navigation path by prediction analysis, and under the condition of considering the influence factors of road conditions and driving habits, the prediction of the charge and endurance of the power battery aiming at the real-time navigation information is realized globally; in addition, the application directly collects the historical state data of the target battery for discharging in the running process of the vehicle as sample data to train and construct the deep neural network model, the influence of the driving habit of the vehicle caused by a driver on the battery electric quantity condition estimation is not required to be considered, and the required sample data is relatively less.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the application, and is not meant to limit the scope of the application, but to limit the application to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the application are intended to be included within the scope of the application.
Claims (10)
1. The power battery charging endurance prediction method based on deep learning is characterized by comprising the following steps of:
acquiring real-time navigation information of a target vehicle and initial residual electric quantity of a target battery configured by the target vehicle;
acquiring historical state data of discharging of a target battery in the running process of a vehicle, and training and constructing a deep neural network model according to the historical state data;
collecting real-time state data of a target battery in an initial stage of a navigation path corresponding to real-time navigation information, and inputting the real-time state data into a deep neural network model to estimate and obtain real-time power consumption of the target battery in the process that the target vehicle finishes driving in the initial stage;
screening reference batteries corresponding to the reference vehicles with the same navigation path as the real-time navigation information from the database, and determining electric quantity consumption difference parameters of all road sections in the navigation path according to historical electric quantity consumption of all the reference batteries along with mileage change in the navigation path;
and calculating according to the real-time power consumption and the power consumption difference parameters to obtain the predicted power consumption of the target battery in each road section in the navigation path, and obtaining the cruising result of the target battery for supplying the target vehicle for navigation driving by combining the initial residual power prediction.
2. The deep learning-based power battery charge duration prediction method of claim 1, wherein the historical state data comprises data of battery current, battery voltage, battery temperature, and battery power consumption over time;
the battery current, the battery voltage and the battery temperature form an input vector, and the battery consumption is a label.
3. The deep learning-based power battery charge duration prediction method of claim 1, wherein the real-time consumption electricity estimation process specifically comprises:
the real-time status data includes data of battery current, battery voltage and battery temperature over time;
after the real-time state data is input into the deep neural network model, outputting to obtain estimated power consumption at each moment in the initial stage;
and carrying out accumulated summation on the estimated consumed electric quantity at each moment to obtain the real-time consumed electric quantity of the target battery in the initial stage.
4. The deep learning-based power battery charge duration prediction method according to claim 1, wherein the determining process of the power consumption difference parameter specifically comprises:
determining the road section power consumption of each road section in the navigation path according to the historical power consumption aiming at a single reference battery;
calculating the power consumption difference ratio of each road section according to the ratio of the power consumption of each road section to the power consumption of the first road section;
and determining the power consumption difference parameters of the corresponding road sections according to the average value of the power consumption difference ratios of all the reference batteries in the same road section.
5. The deep learning-based power battery charge duration prediction method of claim 4, wherein the calculation formula of the electric quantity consumption difference parameter is specifically as follows:
;
wherein ,indicate->Road section electricity consumption of each road section; />Representing the historical power consumption at +.>Power consumption at mileage,/>The mileage is a single road section; />Representing the historical power consumption at +.>The power consumption at the mileage; />Indicate->Road section electricity consumption of each road section; />Indicate->The power consumption difference ratio of each road section; />Indicate->The electric quantity consumption difference parameters of the individual road sections; />Representing the number of reference cells; />Indicate->The first part of the reference cell>Individual roadPower consumption difference ratio of the segments.
6. The deep learning-based power battery charge duration prediction method of claim 4, wherein the calculation formula of the electric quantity consumption difference parameter is specifically as follows:
;
wherein ,indicate->Road section electricity consumption of each road section; />Representing the historical power consumption at +.>Consumption of electricity at mileage +.>The mileage is a single road section; />Representing the historical power consumption at +.>The power consumption at the mileage; />Indicate->Road section electricity consumption of each road section; />Indicate->The power consumption difference ratio of each road section; />Representing the number of reference cells; />Indicate->The first part of the reference cell>The power consumption difference ratio of each road section; />Indicating that all reference cells are at +.>Average value of electric quantity consumption difference ratio of each road section; />Indicate->The electric quantity consumption difference parameters of the individual road sections; />Representing a ratio fluctuation amplitude threshold; />Representing a reference number of batteries that meet a ratio fluctuation amplitude threshold; />Indicate->The first part of the reference cell>Power consumption difference ratio of each road section.
7. The deep learning-based power battery charge duration prediction method according to claim 1, wherein the calculation process of the predicted power consumption is specifically as follows:
determining the number of sections of the covered sections in the initial stage, and determining the real-time power consumption of a single section in the initial stage according to the ratio of the real-time power consumption of the target battery to the number of sections;
carrying out weighted average calculation according to the electric quantity consumption difference parameters of the covered road sections in the initial stage to obtain electric quantity consumption difference parameters of the single road section in the initial stage;
calculating to obtain a parameter ratio by using the ratio of the electric quantity consumption difference parameters of each road section to the electric quantity consumption difference parameters of the single road section in the initial stage;
the predicted power consumption of each road section is calculated by the product of the power consumption difference parameter and the parameter ratio of the single road section in the initial stage.
8. The deep learning-based power battery charge duration prediction method of claim 1, wherein the duration result prediction analysis process specifically comprises:
if the sum of the predicted power consumption and the real-time power consumption of each road section is greater than or equal to the initial residual power, outputting a place which can be reached by the navigation running of the target battery supply target vehicle;
and if the sum of the predicted power consumption and the real-time power consumption of each road section is smaller than the initial residual power, outputting the final residual power of the target battery for supplying the target vehicle after navigation running is completed.
9. Power battery charges continuation of journey prediction system based on degree of depth study, characterized by includes:
the information acquisition module is used for acquiring real-time navigation information of the target vehicle and initial residual electric quantity of a target battery configured by the target vehicle;
the model building module is used for acquiring historical state data of discharging of the target battery in the running process of the vehicle and training and building a deep neural network model according to the historical state data;
the data acquisition module is used for acquiring real-time state data of the target battery in an initial stage of a navigation path corresponding to the real-time navigation information, and inputting the real-time state data into the deep neural network model to estimate and obtain real-time consumption electric quantity of the target battery in a process that the target vehicle finishes driving in the initial stage;
the difference reference module is used for screening reference batteries corresponding to the reference vehicles with the same navigation path as the real-time navigation information from the database, and determining electric quantity consumption difference parameters of each road section in the navigation path according to the historical electric quantity consumption of all the reference batteries along with the mileage change in the navigation path;
and the cruising prediction module is used for calculating the predicted power consumption of each road section of the target battery in the navigation path according to the real-time power consumption and the power consumption difference parameter, and obtaining the cruising result of the target battery for supplying the target vehicle for navigation driving by combining the initial residual power prediction.
10. A computer terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the deep learning-based power battery charge duration prediction method of any one of claims 1-8 when the program is executed by the processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310855033.3A CN116572799B (en) | 2023-07-13 | 2023-07-13 | Power battery charge duration prediction method, system and terminal based on deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310855033.3A CN116572799B (en) | 2023-07-13 | 2023-07-13 | Power battery charge duration prediction method, system and terminal based on deep learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116572799A CN116572799A (en) | 2023-08-11 |
CN116572799B true CN116572799B (en) | 2023-09-05 |
Family
ID=87538180
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310855033.3A Active CN116572799B (en) | 2023-07-13 | 2023-07-13 | Power battery charge duration prediction method, system and terminal based on deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116572799B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116989817B (en) * | 2023-09-26 | 2023-12-08 | 常州满旺半导体科技有限公司 | Energy equipment safety detection data transmission system and method based on data analysis |
Citations (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2013242198A (en) * | 2012-05-18 | 2013-12-05 | Sumitomo Electric System Solutions Co Ltd | Route search device and computer program |
JP2014202643A (en) * | 2013-04-05 | 2014-10-27 | 三菱自動車工業株式会社 | Destination arrival estimation device of vehicle |
CN104260724A (en) * | 2014-09-22 | 2015-01-07 | 李治良 | Vehicle intelligent predictive control system and method |
CN104867348A (en) * | 2014-02-24 | 2015-08-26 | 丰田自动车株式会社 | Travel Support Device, Travel Support Method, And Drive Support System |
CN107791854A (en) * | 2016-09-06 | 2018-03-13 | 现代自动车株式会社 | For the system and method for the available operating range for estimating electric vehicle |
CN109141455A (en) * | 2018-08-21 | 2019-01-04 | 上海博泰悦臻网络技术服务有限公司 | Navigation path planning method and server |
KR20190029875A (en) * | 2017-09-13 | 2019-03-21 | 현대자동차주식회사 | Electric vehicle and control method thereof |
CN110281812A (en) * | 2019-06-27 | 2019-09-27 | 一汽解放汽车有限公司 | A kind of course continuation mileage estimating system based on operating mode's switch |
CN110329266A (en) * | 2019-07-15 | 2019-10-15 | 腾讯科技(深圳)有限公司 | Can course continuation mileage determine method, apparatus, terminal and storage medium |
CN111452619A (en) * | 2020-01-22 | 2020-07-28 | 北京理工大学 | Online energy consumption prediction method and system for electric vehicle |
CN111582596A (en) * | 2020-05-14 | 2020-08-25 | 公安部交通管理科学研究所 | Pure electric vehicle endurance mileage risk early warning method integrating traffic state information |
CN111670340A (en) * | 2018-09-07 | 2020-09-15 | 深圳配天智能技术研究院有限公司 | Method for acquiring remaining driving mileage of vehicle, electronic equipment and vehicle |
CN112208338A (en) * | 2020-09-29 | 2021-01-12 | 广州小鹏自动驾驶科技有限公司 | Method and device for calculating remaining endurance mileage of destination |
CN113419123A (en) * | 2021-05-25 | 2021-09-21 | 四川轻化工大学 | Method for estimating state of charge of series super capacitor bank in variable temperature environment |
CN115146009A (en) * | 2021-03-29 | 2022-10-04 | 本田技研工业株式会社 | Information management apparatus, information management method, and storage medium |
CN115164922A (en) * | 2022-06-17 | 2022-10-11 | 上海钧正网络科技有限公司 | Path planning method, system, equipment and storage medium |
CN115230526A (en) * | 2022-04-28 | 2022-10-25 | 长城汽车股份有限公司 | Method and device for estimating remaining endurance mileage of automobile and automobile |
WO2022236751A1 (en) * | 2021-05-12 | 2022-11-17 | 华为技术有限公司 | Battery state of charge estimation method and device |
CN115660501A (en) * | 2022-11-08 | 2023-01-31 | 国网陕西省电力公司电力科学研究院 | Electric vehicle charging load adjustable margin evaluation method |
CN115817183A (en) * | 2022-12-02 | 2023-03-21 | 中汽研汽车检验中心(天津)有限公司 | Method and device for predicting driving range of pure electric vehicle |
-
2023
- 2023-07-13 CN CN202310855033.3A patent/CN116572799B/en active Active
Patent Citations (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2013242198A (en) * | 2012-05-18 | 2013-12-05 | Sumitomo Electric System Solutions Co Ltd | Route search device and computer program |
JP2014202643A (en) * | 2013-04-05 | 2014-10-27 | 三菱自動車工業株式会社 | Destination arrival estimation device of vehicle |
CN104867348A (en) * | 2014-02-24 | 2015-08-26 | 丰田自动车株式会社 | Travel Support Device, Travel Support Method, And Drive Support System |
CN104260724A (en) * | 2014-09-22 | 2015-01-07 | 李治良 | Vehicle intelligent predictive control system and method |
CN107791854A (en) * | 2016-09-06 | 2018-03-13 | 现代自动车株式会社 | For the system and method for the available operating range for estimating electric vehicle |
KR20190029875A (en) * | 2017-09-13 | 2019-03-21 | 현대자동차주식회사 | Electric vehicle and control method thereof |
CN109141455A (en) * | 2018-08-21 | 2019-01-04 | 上海博泰悦臻网络技术服务有限公司 | Navigation path planning method and server |
CN111670340A (en) * | 2018-09-07 | 2020-09-15 | 深圳配天智能技术研究院有限公司 | Method for acquiring remaining driving mileage of vehicle, electronic equipment and vehicle |
CN110281812A (en) * | 2019-06-27 | 2019-09-27 | 一汽解放汽车有限公司 | A kind of course continuation mileage estimating system based on operating mode's switch |
CN110329266A (en) * | 2019-07-15 | 2019-10-15 | 腾讯科技(深圳)有限公司 | Can course continuation mileage determine method, apparatus, terminal and storage medium |
CN111452619A (en) * | 2020-01-22 | 2020-07-28 | 北京理工大学 | Online energy consumption prediction method and system for electric vehicle |
CN111582596A (en) * | 2020-05-14 | 2020-08-25 | 公安部交通管理科学研究所 | Pure electric vehicle endurance mileage risk early warning method integrating traffic state information |
CN112208338A (en) * | 2020-09-29 | 2021-01-12 | 广州小鹏自动驾驶科技有限公司 | Method and device for calculating remaining endurance mileage of destination |
CN115146009A (en) * | 2021-03-29 | 2022-10-04 | 本田技研工业株式会社 | Information management apparatus, information management method, and storage medium |
WO2022236751A1 (en) * | 2021-05-12 | 2022-11-17 | 华为技术有限公司 | Battery state of charge estimation method and device |
CN113419123A (en) * | 2021-05-25 | 2021-09-21 | 四川轻化工大学 | Method for estimating state of charge of series super capacitor bank in variable temperature environment |
CN115230526A (en) * | 2022-04-28 | 2022-10-25 | 长城汽车股份有限公司 | Method and device for estimating remaining endurance mileage of automobile and automobile |
CN115164922A (en) * | 2022-06-17 | 2022-10-11 | 上海钧正网络科技有限公司 | Path planning method, system, equipment and storage medium |
CN115660501A (en) * | 2022-11-08 | 2023-01-31 | 国网陕西省电力公司电力科学研究院 | Electric vehicle charging load adjustable margin evaluation method |
CN115817183A (en) * | 2022-12-02 | 2023-03-21 | 中汽研汽车检验中心(天津)有限公司 | Method and device for predicting driving range of pure electric vehicle |
Non-Patent Citations (1)
Title |
---|
基于多层混合效应的电动汽车能耗估计模型;刘锴;王江波;陈晋;;武汉理工大学学报(交通科学与工程版)(第06期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN116572799A (en) | 2023-08-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109733248B (en) | Pure electric vehicle remaining mileage model prediction method based on path information | |
CN111497679B (en) | Pure electric vehicle energy consumption monitoring optimization method and system | |
CN109367433B (en) | Intelligent charging stake | |
Bi et al. | Estimating remaining driving range of battery electric vehicles based on real-world data: A case study of Beijing, China | |
CN109532556B (en) | Method and system for acquiring endurance mileage of pure electric vehicle | |
CN104442825B (en) | A kind of Forecasting Methodology and system of electric automobile remaining driving mileage | |
CN111670340B (en) | Method for acquiring remaining driving mileage of vehicle, electronic equipment and vehicle | |
CN106483470A (en) | Battery residual discharge energy prediction method based on future operation condition prediction | |
CN109784560A (en) | A kind of electric car course continuation mileage evaluation method and estimating system | |
CN112526351B (en) | Method for evaluating health state and residual life of power battery of electric automobile | |
CN116572799B (en) | Power battery charge duration prediction method, system and terminal based on deep learning | |
CN105128853A (en) | System used for calculating driving mileage of extended-range hybrid power automobile | |
CN113335131B (en) | Vehicle endurance mileage prediction method, device, equipment and storage medium | |
CN114274780A (en) | Vehicle driving mileage prediction method, device, equipment and storage medium | |
JP7413806B2 (en) | Battery deterioration determination device, battery deterioration determination method, and battery deterioration determination program | |
CN111191824A (en) | Power battery capacity attenuation prediction method and system | |
CN113642768A (en) | Vehicle running energy consumption prediction method based on working condition reconstruction | |
CN113665431A (en) | Method and device for estimating remaining endurance mileage of electric automobile | |
CN112083332A (en) | Pure electric vehicle driving range estimation method considering user experience | |
EP3875976A1 (en) | Electricity storage element evaluating device, computer program, electricity storage element evaluating method, learning method, and creation method | |
CN113159435B (en) | Method and system for predicting remaining driving mileage of new energy vehicle | |
US20230305073A1 (en) | Method and apparatus for providing a predicted aging state of a device battery based on a predicted usage pattern | |
CN112765726A (en) | Service life prediction method and device | |
CN116205370A (en) | Electric vehicle endurance mileage prediction method and device based on regional big data | |
CN115219913A (en) | Power battery full-life-cycle management system based on capacity increment method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |