BEV power consumption calculation method and device based on vehicle-mounted big data

Abstract

The invention relates to a BEV power consumption calculation method and device based on vehicle-mounted big data, and the method comprises the steps: obtaining the historical vehicle-mounted data of a target vehicle in a vehicle type development stage and a real vehicle operation stage, and fitting the BEV power consumption of the target vehicle through the historical vehicle-mounted data, so as to construct a power consumption model corresponding to the target vehicle; collecting current use data of a plurality of target controllers in the target vehicle, and inputting the current use data into the power consumption model to output a BEV power consumption prediction result of the target vehicle; and on the basis of the BEV power consumption prediction result, calculating the remaining power consumption time of the target vehicle, and generating a travel report of the target vehicle through the remaining power consumption time, so that the target user controls the target vehicle to execute corresponding driving operation according to the travel report. The calculation efficiency of the power consumption of each part of the vehicle can be effectively improved, the user experience is greatly improved, and the humanization degree and the intelligent level of the vehicle are improved.

Description

Technical Field

[0001] This application relates to the technical field of big data applications and data analysis in the Internet of Vehicles, and particularly relates to a BEV power consumption calculation method and device based on vehicle-mounted big data. Background Art

[0002] With the development of the application of Internet of Vehicles technology and big data technology, vehicle data has become more abundant, complete and comprehensive, providing more directions and possibilities for improving the product usability of vehicles and optimizing the driving experience of vehicle owners. At the same time, it also helps to promote product evolution, improve manufacturing quality and efficiency, and enhance product competitiveness.

[0003] With the emergence and popularization of new energy vehicles, vehicle owners are becoming more and more concerned about vehicle power consumption. However, due to the complexity of vehicles, accurately calculating the power consumption of each component of new energy vehicles has always been a rather difficult issue. Existing technologies can use sensors to record the power consumption of each controller, and accurately evaluate how long the current usage mode can continue by separately calculating the power consumption of each controller and the power consumption results of combinations of each controller, facilitating subsequent driving planning.

[0004] However, although the existing technology accurately records the power consumption of each controller through sensors, it increases the network burden and calculation burden, and at the same time has too high a demand for cloud computing resources, which urgently needs to be solved. Summary of the Invention

[0005] This application provides a BEV power consumption calculation method and device based on vehicle-mounted big data to solve the problems in the prior art that when calculating the power consumption of each component of new energy vehicles, the network burden and calculation burden are greatly increased, and at the same time, the demand for cloud computing resources is too high.

[0006] The first aspect of the embodiments of this application provides a BEV power consumption calculation method based on vehicle-mounted big data, including the following steps: obtaining historical vehicle-mounted data of a target vehicle in the vehicle model development stage and the actual vehicle operation stage, and fitting the BEV power consumption of the target vehicle through the historical vehicle-mounted data to construct a power consumption model corresponding to the target vehicle; collecting current usage data of multiple target controllers in the target vehicle, and inputting the current usage data into the power consumption model to output a BEV power consumption prediction result of the target vehicle; based on the BEV power consumption prediction result, calculating the remaining power consumption time of the target vehicle, and generating a driving report of the target vehicle through the remaining power consumption time, so that a target user can control the target vehicle to perform corresponding driving operations according to the driving report.

[0007] Optionally, in an embodiment of the present application, the method of obtaining the historical in-vehicle data of the target vehicle in the vehicle model development stage and the actual vehicle operation stage, and fitting the BEV power consumption of the target vehicle through the historical in-vehicle data to construct the power consumption model corresponding to the target vehicle includes: obtaining the corresponding buried point signals through the TBOX buried points and in-vehicle system buried points in the vehicle model development stage, and reporting the buried point signals to a preset TSP cloud system, so that the TSP cloud system analyzes the buried point signals according to the target protocol to obtain the corresponding buried point data; uploading the buried point data to a preset data middle platform, so that the data middle platform integrates the buried point data in the target space-time dimension to obtain the historical in-vehicle data.

[0008] Optionally, in an embodiment of the present application, the method of fitting the BEV power consumption of the target vehicle through the historical in-vehicle data to construct the power consumption model corresponding to the target vehicle includes: performing data cleaning and preprocessing operations on the historical in-vehicle data to generate corresponding standard data; obtaining the time series corresponding to the standard data, and performing sliding window statistics on the time series to obtain the derived variables corresponding to the standard data; determining the model prediction requirements of the target vehicle, and performing feature screening operations on the standard data according to the model prediction requirements to obtain the corresponding screened variables; determining the power consumption objective function corresponding to the target vehicle, and based on the power consumption objective function, constructing the target regression model corresponding to the target vehicle, and training the target regression model through the derived variables and the screened variables to generate the power consumption model.

[0009] Optionally, in an embodiment of the present application, after constructing the power consumption model corresponding to the target vehicle, it further includes: deploying the power consumption model in a preset data middle platform API, and monitoring the power consumption model through the data middle platform API to obtain the usage data corresponding to the power consumption model; determining the evaluation requirements and evaluation frequency of the power consumption model according to the usage data, and performing fitness and stability evaluations on the power consumption model through the evaluation requirements and the evaluation frequency to obtain the corresponding evaluation results, and fine-tuning the power consumption model through the evaluation results.

[0010] Optionally, in one embodiment of the present application, the trip report of the target vehicle is generated through the remaining power usage time, so that the target user can control the target vehicle to perform corresponding driving operations according to the trip report, including: based on a preset data middle platform API, the BEV power consumption prediction result and the remaining power usage time are sent to the target terminal, so that the target terminal determines the key power consumption controller among the multiple target controllers according to the BEV power consumption prediction result and the remaining power usage time; based on the usage needs of the target user, the key power consumption controller is adjusted or shut down to obtain the operation information corresponding to the target user, and a new remaining power usage time or route planning adjustment suggestion is generated according to the operation information, so as to generate and display the trip report through the new remaining power usage time or the route planning adjustment suggestion.

[0011] The second aspect of the present application provides a BEV power consumption calculation device based on on-board big data, including: a fitting module, used to obtain historical on-board data of a target vehicle during a vehicle model development stage and an actual vehicle operation stage, and fit the BEV power consumption of the target vehicle through the historical on-board data to construct a power consumption model corresponding to the target vehicle; a prediction module, used to collect current usage data of multiple target controllers in the target vehicle, and input the current usage data into the power consumption model to output a BEV power consumption prediction result of the target vehicle; a control module, used to calculate the remaining power consumption time of the target vehicle based on the BEV power consumption prediction result, and generate a travel report of the target vehicle through the remaining power consumption time, so that a target user can control the target vehicle to perform corresponding driving operations according to the travel report.

[0012] Optionally, in one embodiment of the present application, the fitting module includes: a parsing unit, used to obtain corresponding buried point signals through the TBOX buried points and the vehicle system buried points in the vehicle model development stage, and report the buried point signals to a preset TSP cloud system, so that the TSP cloud system parses the buried point signals according to the target protocol to obtain corresponding buried point data; an integration unit, used to upload the buried point data to a preset data middle station, so that the data middle station integrates the buried point data in the target space-time dimension to obtain the historical vehicle-mounted data.

[0013] Optionally, in one embodiment of the present application, the fitting module also includes: a data processing unit, used to perform data cleaning and preprocessing operations on the historical vehicle data to generate corresponding standard data; a statistical unit, used to obtain the time series corresponding to the standard data, and perform sliding window statistics on the time series to obtain the derived variables corresponding to the standard data; a screening unit, used to determine the model prediction requirements of the target vehicle, and perform feature screening operations on the standard data according to the model prediction requirements to obtain corresponding screening variables; a modeling unit, used to determine the power consumption target function corresponding to the target vehicle, and based on the power consumption target function, construct a target regression model corresponding to the target vehicle, and train the target regression model through the derived variables and the screening variables to generate the power consumption model.

[0014] Optionally, in one embodiment of the present application, it also includes: a monitoring module, which is used to deploy the power consumption model corresponding to the target vehicle in a preset data middle platform API after constructing the power consumption model, and monitor the power consumption model through the data middle platform API to obtain usage data corresponding to the power consumption model; a fine-tuning module, which is used to determine the evaluation requirements and evaluation frequency of the power consumption model based on the usage data, and perform fitness and stability evaluation on the power consumption model based on the evaluation requirements and the evaluation frequency to obtain corresponding evaluation results, and fine-tune the power consumption model based on the evaluation results.

[0015] Optionally, in one embodiment of the present application, the control module includes: a determination unit, used to send the BEV power consumption prediction result and the remaining power consumption time to the target terminal based on a preset data middle platform API, so that the target terminal determines the key power consumption controller among the multiple target controllers according to the BEV power consumption prediction result and the remaining power consumption time; an interaction unit, used to adjust or shut down the key power consumption controller based on the usage requirements of the target user, so as to obtain the operation information corresponding to the target user, and generate a new remaining power consumption time or route planning adjustment suggestion according to the operation information, so as to generate and display the trip report through the new remaining power consumption time or the route planning adjustment suggestion.

[0016] The third aspect of the present application provides a vehicle, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the BEV power consumption calculation method based on on-board big data as described in the above embodiment.

[0017] In the fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, which when executed by a processor, implements the above-mentioned method for calculating the BEV power consumption based on in-vehicle big data.

[0018] In the fifth aspect of the embodiments of the present application, a computer program product is provided, including a computer program, which is executed to implement the above-mentioned method for calculating the BEV power consumption based on in-vehicle big data.

[0019] Thus, the embodiments of the present application have the following beneficial effects:

[0020] The embodiments of the present application can obtain the historical in-vehicle data of the target vehicle in the vehicle model development stage and the actual vehicle operation stage, and fit the BEV power consumption of the target vehicle through the historical in-vehicle data to construct a power consumption model corresponding to the target vehicle; collect the current usage data of multiple target controllers in the target vehicle, and input the current usage data into the power consumption model to output the BEV power consumption prediction result of the target vehicle; based on the BEV power consumption prediction result, calculate the remaining power usage time of the target vehicle, and generate a trip report of the target vehicle through the remaining power usage time, so that the target user can control the target vehicle to perform corresponding driving operations according to the trip report. The present application fits the BEV power consumption according to the historical in-vehicle big data, and estimates the power consumption and available time according to the fitting result and the current opening conditions of each controller, so as to carry out trip notification and planning adjustment, thereby effectively improving the calculation efficiency of the power consumption of each vehicle component, greatly improving the user experience, and enhancing the humanization and intelligent level of the vehicle. Thus, the problems in the prior art that when calculating the power consumption of each component of a new energy vehicle, the network burden and calculation burden are greatly increased, and at the same time, the demand for cloud computing resources is too large are solved.

[0021] The additional aspects and advantages of the present application will be partially given in the following description, partially become obvious from the following description, or be understood through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above-mentioned and / or additional aspects and advantages of the present application will become obvious and easy to understand from the following description of the embodiments in conjunction with the drawings, where:

[0023] Figure 1 is a flowchart of a method for calculating the BEV power consumption based on in-vehicle big data according to an embodiment of the present application;

[0024] Figure 2 is a schematic diagram of the communication process of a method for calculating the BEV power consumption based on in-vehicle big data provided by an embodiment of the present application;

[0025] Figure 3Execution logic schematic diagram of a BEV power consumption calculation method based on in-vehicle big data provided by an embodiment of the present application;

[0026] Figure 4 Logical architecture schematic diagram of a BEV power consumption calculation method based on in-vehicle big data provided by an embodiment of the present application;

[0027] Figure 5 Example diagram of a BEV power consumption calculation device based on in-vehicle big data according to an embodiment of the present application;

[0028] Figure 6 Structural schematic diagram of a vehicle provided by an embodiment of the present application.

[0029] Among them, 10 - BEV power consumption calculation device based on in-vehicle big data; 100 - fitting module, 200 - prediction module, 300 - control module; 601 - memory, 602 - processor, 603 - communication interface. Detailed implementation manners

[0030] The embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals indicate the same or similar elements or elements with the same or similar functions from beginning to end. The embodiments described below by referring to the accompanying drawings are exemplary and are intended to explain the present application, and should not be construed as a limitation to the present application.

[0031] The BEV power consumption calculation method and device based on vehicle-mounted big data according to the embodiments of the present application will be described below with reference to the accompanying drawings. In view of the problems mentioned in the above background art, the present application provides a BEV power consumption calculation method based on vehicle-mounted big data. In this method, historical vehicle-mounted data of the target vehicle in the vehicle model development stage and the actual vehicle operation stage is obtained, and the BEV power consumption of the target vehicle is fitted through the historical vehicle-mounted data to construct a power consumption model corresponding to the target vehicle; the current usage data of multiple target controllers in the target vehicle is collected and input into the power consumption model to output the BEV power consumption prediction result of the target vehicle; based on the BEV power consumption prediction result, the remaining power usage time of the target vehicle is calculated, and a trip report of the target vehicle is generated through the remaining power usage time, so that the target user can control the target vehicle to perform corresponding driving operations according to the trip report. The present application fits the BEV power consumption according to the historical vehicle-mounted big data, and estimates the power consumption and available time according to the fitting result and the current opening status of each controller to perform trip notification and planning adjustment, thereby effectively improving the calculation efficiency of the power consumption of each vehicle component, greatly improving the user experience, and enhancing the humanization and intelligence level of the vehicle. Thereby, the problems in the prior art that when calculating the power consumption of each component of a new energy vehicle, the network burden and calculation burden are greatly increased, and at the same time, the demand for cloud computing resources is too large are solved.

[0032] Specifically, Figure 1 FIG. is a flowchart of a BEV power consumption calculation method based on vehicle-mounted big data provided by an embodiment of the present application.

[0033] As Figure 1 shown, the BEV power consumption calculation method based on vehicle-mounted big data includes the following steps:

[0034] In step S101, historical vehicle-mounted data of the target vehicle in the vehicle model development stage and the actual vehicle operation stage is obtained, and the BEV power consumption of the target vehicle is fitted through the historical vehicle-mounted data to construct a power consumption model corresponding to the target vehicle.

[0035] In the embodiment of the present application, first, through the buried point design in the vehicle model development stage and the data acquisition in the actual vehicle operation stage, the vehicle-mounted big data (i.e., historical vehicle-mounted big data) of user vehicle use is accumulated, and by correlating the power consumption (Y) in the vehicle-mounted big data with the usage status (X) of each controller, the BEV power consumption is fitted for regression modeling, thereby constructing a power consumption model corresponding to the target vehicle.

[0036] Optionally, in an embodiment of the present application, historical in-vehicle data of the target vehicle in the vehicle model development stage and the actual vehicle operation stage is obtained, and the BEV power consumption of the target vehicle is fitted through the historical in-vehicle data to construct a power consumption model corresponding to the target vehicle, including: obtaining corresponding buried point signals through TBOX buried points and in-vehicle system buried points in the vehicle model development stage, and reporting the buried point signals to a preset TSP cloud system, so that the TSP cloud system analyzes the buried point signals according to the target protocol to obtain corresponding buried point data; uploading the buried point data to a preset data middle platform, so that the data middle platform integrates the buried point data in the target space-time dimension to obtain historical in-vehicle data.

[0037] It should be noted that, in the embodiment of the present application, the prediction definition of BEV power consumption can be first defined according to the vehicle model configuration.

[0038] Among them, the vehicle model configuration includes power battery (brand, maximum capacity, supplier), automatic air conditioner (brand, temperature settable threshold, supplier), in-vehicle computer (chip, screen size, resolution, supplier, ecological configuration), seats (heating, ventilation), body (drive motor, intelligent driving), etc. Here, it is mainly to define the power consumption speed (N kwh per hour) of the BEV and the time consumed to continuously run to 10% of the power battery capacity when the current vehicle model maintains a certain function combination state.

[0039] It should be noted that the embodiments of the present application cannot use operations without a continuous state as a judgment basis, such as the instantaneous speed reaching 120 km / h, because it will generate a very large calculation pressure and is not the result that users hope to obtain at the same time.

[0040] Secondly, the embodiments of the present application can perform data collection and integration.

[0041] In the embodiment of the present application, data collection mainly refers to data buried points and data reporting; in the BEV intelligent cockpit, data buried points are mainly reflected in TBOX buried points and in-vehicle system buried points. Among them, TBOX buried points are that the component TBOX collects key signal data of each component through the CAN bus, which is divided into low frequency (collect once every ten seconds) and high frequency (collect once every second); in-vehicle system buried points are to collect the opening, closing and duration of applications in the in-vehicle computer, which is divided into local and online; and data reporting refers to the TBOX and the in-vehicle computer reporting the buried point signals to the TSP cloud system through the vehicle network. After the TSP cloud system receives the data reporting, it analyzes the signals of both according to the protocol and then uploads them to the data middle platform (data mart);

[0042] In addition, data integration mainly refers to integrating the logged data into a time / space dimension after acquisition. For example, aggregating TBOX data and in-vehicle infotainment (IVI) data together, using vehicle VIN and timestamp as unique identifiers to display the status of each controller and IVI application at each second, aiming to facilitate subsequent data processing and model operation, reduce intermediate processing time, and increase response speed.

[0043] It should be noted that there is basically a delay of about ten minutes from data logging, data reporting to data integration, which belongs to quasi-real-time, and still follows streaming processing in data processing. Therefore, the embodiments of this application also require that the subsequent model input parameters can reflect at least 10 minutes of data (mean, maximum, minimum, etc., designed according to the actual meaning of the field). The preliminary designed logging list is shown in the following table:

[0044] Table 1

[0045]

[0046] Thus, the embodiments of this application provide reliable data guidance and basis for the calculation of BEV power consumption by defining the prediction definition of BEV power consumption according to vehicle model configuration and performing data collection and integration operations.

[0047] Optionally, in an embodiment of this application, the BEV power consumption of the target vehicle is fitted through historical in-vehicle data to construct a power consumption model corresponding to the target vehicle, including: performing data cleaning and preprocessing operations on the historical in-vehicle data to generate corresponding standard data; obtaining the time series corresponding to the standard data, and performing sliding window statistics on the time series to obtain the derived variables corresponding to the standard data; determining the model prediction requirements of the target vehicle, and performing feature screening operations on the standard data according to the model prediction requirements to obtain the corresponding screening variables; determining the power consumption objective function corresponding to the target vehicle, and based on the power consumption objective function, constructing the target regression model corresponding to the target vehicle, and training the target regression model through the derived variables and screening variables to generate the power consumption model.

[0048] After that, the embodiments of this application also need to perform operations such as data cleaning, preprocessing, and feature engineering on the historical in-vehicle data, which are specifically described as follows:

[0049] 1. Data cleaning and preprocessing:

[0050] It can be understood that data cleaning and preprocessing generally refer to the processing of abnormal data and adaptation to subsequent programs; in the embodiment of the present application, the entire record can be directly deleted for unique signals that do not conform to the format, such as the vehicle VIN length <10 digits; for numerical signals that do not conform to the format and value range, the original value is replaced with an invalid identifier, for example, a character string appears in the remaining power signal or a negative value appears or > the battery calibration value; for enumeration signals that do not conform to the enumeration value, the original value is replaced with an invalid value, such as -1 appears in the ignition key state; the verification rules and cleaning methods for each signal need to be verified, and the verification rules of the signal need to be continuously maintained, and signals with practical meanings cannot be eliminated;

[0051] 2. Feature Engineering:

[0052] Feature engineering generally refers to the process of deriving variables and screening variables. In the embodiments of the present application, derived variables are mainly sliding window statistics of time series, such as the average vehicle speed, air-conditioning temperature, and ambient temperature in the past 30 minutes. They are often state variables that are easy to change, reflecting the cumulative state within a certain time window; screening variables control the number of variables according to the requirements of the model. Too many variables can easily cause the model to be underfit or overfit, and too many homogeneous variables can also cause model deviation. Common methods include Pearson coefficient, chi-square test, and principal component analysis.

[0053] Furthermore, the embodiments of the present application take fitting power consumption as the main goal, select regression models such as random forest or decision tree, construct a corresponding target regression model, and train the target regression model with derived variables and screening variables to generate a power consumption model, and compare the results with the actual power consumption in terms of mean absolute error and root mean square error, and optimize the model by adjusting parameters and selecting the model to meet actual requirements.

[0054] Therefore, the embodiments of the present application can obtain a power consumption model by performing data cleaning and preprocessing, feature engineering, model selection and training on historical vehicle data, thereby effectively ensuring the prediction efficiency and reliability of the BEV power consumption prediction results.

[0055] Optionally, in one embodiment of the present application, after constructing the power consumption model corresponding to the target vehicle, it also includes: deploying the power consumption model in a preset data middle platform API, and monitoring the power consumption model through the data middle platform API to obtain usage data corresponding to the power consumption model; determining the evaluation requirements and evaluation frequency of the power consumption model based on the usage data, and performing adaptability and stability evaluation on the power consumption model based on the evaluation requirements and evaluation frequency to obtain corresponding evaluation results, and fine-tuning the power consumption model based on the evaluation results.

[0056] In the actual execution process, after the model is trained, the embodiment of the present application can integrate the model into the data center API, such asFigure 2 As shown, the in-vehicle computer and the APP can obtain the corresponding prediction results through API requests.

[0057] It should be noted that since the user's habits and signal connotations may change with seasons and version updates, it is necessary to regularly evaluate the stability and adaptability of the model. The adaptability still uses the mean absolute error and the root mean square error, and the stability can use the KS test. The evaluation frequency can be set to monthly or quarterly to fine-tune the power consumption model.

[0058] In addition, in the embodiments of the present application, the implementation method of the model and the correlation between each signal and the power consumption are explained in terms of business logic. Among them, the correlation can refer to the contribution method or the Pearson coefficient. The program logic needs to meet the requirements from aspects such as detailed design, program source code, annotations, and maintenance manuals, so as to cope with internal and external audits and the inheritance of soft assets of the program logic.

[0059] In step S102, the current usage data of multiple target controllers in the target vehicle is collected, and the current usage data is input into the power consumption model to output the BEV power consumption prediction result of the target vehicle.

[0060] In step S103, based on the BEV power consumption prediction result, the remaining power usage time of the target vehicle is calculated, and a trip report of the target vehicle is generated through the remaining power usage time, so that the target user can control the target vehicle to perform corresponding driving operations according to the trip report.

[0061] Furthermore, the embodiments of the present application can also predict the power consumption of the current vehicle through the power consumption model according to the usage conditions (X) of each controller of the current vehicle, calculate the remaining power usage time according to the predicted power consumption, and provide display services and route planning suggestions to the user.

[0062] It should be noted that the embodiments of the present application mainly focus on data acquisition, data modeling, and data application, and the resource requirements mainly rely on data logging, data accumulation, and calculation in the early stage. It can be adjusted according to the vehicle model requirements. Each new vehicle model needs to be re-modeled and implemented according to its own configuration. Only when the configuration homogenization among vehicle models is high will there be a situation of direct reuse.

[0063] Optionally, in an embodiment of the present application, a trip report of the target vehicle is generated based on the remaining power consumption time, so that the target user controls the target vehicle to perform corresponding driving operations according to the trip report, including: based on a preset data middle platform API, sending the BEV power consumption prediction result and the remaining power consumption time to the target terminal, so that the target terminal determines the key power-consuming controller among multiple target controllers according to the BEV power consumption prediction result and the remaining power consumption time; based on the usage requirements of the target user, adjusting or turning off the key power-consuming controller to obtain the operation information corresponding to the target user, and generating a new remaining power consumption time or a route planning adjustment suggestion according to the operation information, so as to generate and display a trip report through the new remaining power consumption time or the route planning adjustment suggestion.

[0064] It can be understood that, as Figure 3 shown, the in-vehicle computer / APP in the embodiment of the present application can indirectly obtain the BEV power consumption prediction result through the middle platform API.

[0065] Among them, the usage scenarios of the in-vehicle computer focus on driving and in-vehicle applications. When the user is on a trip and the in-vehicle computer obtains the BEV power consumption prediction result, if the predicted remaining available duration is less than the subsequent navigation trip time, it reminds the user that the battery power may be insufficient. At this time, it prompts the user of the main power-consuming electrical appliances currently in use, such as air conditioning, seat heating, seat ventilation, and in-vehicle applications, and at the same time provides buttons for adjusting or turning off the electrical appliances for the convenience of the user's operation; if the user performs the corresponding operation, the predicted remaining available duration is immediately modified according to the historical data; if the user does not operate, the embodiment of the present application can also provide a route planning adjustment suggestion to navigate to the nearest charging station to the original plan before the battery runs out; when the user is in a parked state, the main power-consuming electrical appliances are generally air conditioning and in-vehicle applications. At this time, in addition to identifying whether the user has installed a charging pile at home, the rest of the logic is similar to the processing flow during the trip, but the charging route planning is preferred over closing the application because even if the application is closed, charging is still required the next time the vehicle is used.

[0066] The usage scenarios of the APP are generally in the off-vehicle state, such as when the user makes a reservation for a trip, a reservation for charging, or remotely borrows a vehicle, etc.; in this scenario, the user generally cannot perform a charging operation. The remaining available vehicle time can be prompted to the user, and buttons for turning off some functions that do not affect safety are provided, such as air conditioning, seat heating, videos, music, etc. in the in-vehicle application.

[0067] It should be noted that the embodiments of the present application are based on historical vehicle usage data, apply the vehicle-mounted big data based on the regression model algorithm, and analyze and evaluate the power consumption of BEV vehicles. It requires a matching relationship among a vehicle networking background, a big data cloud platform, and a vehicle-mounted communication module with 2G / 3G / 4G, as Figure 4 shown.

[0068] In summary, the embodiments of the present application fit the BEV power consumption through historical in-vehicle big data, estimate the power consumption and available time based on the fitting results and the current opening conditions of each controller, and perform trip notifications and planning adjustments according to the estimation results, thereby solving the problems of high cost and excessive resource requirements in power consumption evaluation in the related art, improving the calculation efficiency and quality of BEV power consumption, and enhancing the reliability and safety of driving.

[0069] According to the BEV power consumption calculation method based on in-vehicle big data proposed by the embodiments of the present application, historical in-vehicle data of the target vehicle in the vehicle model development stage and the actual vehicle operation stage is obtained, and the BEV power consumption of the target vehicle is fitted through the historical in-vehicle data to construct a power consumption model corresponding to the target vehicle; the current usage data of multiple target controllers in the target vehicle is collected, and the current usage data is input into the power consumption model to output the BEV power consumption prediction result of the target vehicle; based on the BEV power consumption prediction result, the remaining power usage time of the target vehicle is calculated, and a trip report of the target vehicle is generated through the remaining power usage time, so that the target user can control the target vehicle to perform corresponding driving operations according to the trip report. The present application fits the BEV power consumption according to historical in-vehicle big data, estimates the power consumption and available time based on the fitting results and the current opening conditions of each controller, and performs trip notifications and planning adjustments, thereby effectively improving the calculation efficiency of the power consumption of each vehicle component, greatly improving the user experience, and enhancing the humanization and intelligent level of the vehicle.

[0070] Secondly, a BEV power consumption calculation device based on in-vehicle big data proposed by the embodiments of the present application is described with reference to the accompanying drawings.

[0071] Figure 5 It is a block diagram of a BEV power consumption calculation device based on in-vehicle big data according to an embodiment of the present application.

[0072] As Figure 5 shown, the BEV power consumption calculation device 10 based on in-vehicle big data includes: a fitting module 100, a prediction module 200, and a control module 300.

[0073] Among them, the fitting module 100 is used to obtain historical in-vehicle data of the target vehicle in the vehicle model development stage and the actual vehicle operation stage, and fit the BEV power consumption of the target vehicle through the historical in-vehicle data to construct a power consumption model corresponding to the target vehicle.

[0074] The prediction module 200 is used to collect the current usage data of multiple target controllers in the target vehicle, and input the current usage data into the power consumption model to output the BEV power consumption prediction result of the target vehicle.

[0075] The control module 300 is configured to calculate the remaining power consumption time of the target vehicle based on the BEV power consumption prediction result, and generate a trip report of the target vehicle through the remaining power consumption time, so that the target user can control the target vehicle to perform corresponding driving operations according to the trip report.

[0076] Optionally, in an embodiment of the present application, the fitting module 100 includes: a parsing unit and an integration unit.

[0077] The parsing unit is configured to obtain corresponding buried point signals through TBOX buried points and in-vehicle system buried points in the vehicle model development stage, and report the buried point signals to a preset TSP cloud system, so that the TSP cloud system parses the buried point signals according to the target protocol to obtain corresponding buried point data.

[0078] The integration unit is configured to upload the buried point data to a preset data middle platform, so that the data middle platform integrates the buried point data in the target space-time dimension to obtain historical vehicle-mounted data.

[0079] Optionally, in an embodiment of the present application, the fitting module 100 further includes: a data processing unit, a statistics unit, a screening unit, and a modeling unit.

[0080] The data processing unit is configured to perform data cleaning and preprocessing operations on the historical vehicle-mounted data to generate corresponding standard data.

[0081] The statistics unit is configured to obtain the time series corresponding to the standard data, and perform sliding window statistics on the time series to obtain the derivative variables corresponding to the standard data.

[0082] The screening unit is configured to determine the model prediction requirements of the target vehicle, and perform feature screening operations on the standard data according to the model prediction requirements to obtain corresponding screening variables.

[0083] The modeling unit is configured to determine the power consumption objective function corresponding to the target vehicle, and based on the power consumption objective function, construct the target regression model corresponding to the target vehicle, and train the target regression model through the derivative variables and the screening variables to generate the power consumption model.

[0084] Optionally, in an embodiment of the present application, the BEV power consumption calculation device 10 based on vehicle-mounted big data of the present application embodiment further includes: a monitoring module and a fine-tuning module.

[0085] The monitoring module is configured to deploy the power consumption model in a preset data middle platform API after constructing the power consumption model corresponding to the target vehicle, and monitor the power consumption model through the data middle platform API to obtain the usage data corresponding to the power consumption model.

[0086] The fine-tuning module is used to determine the evaluation requirements and evaluation frequency of the power consumption model according to the usage data, and to evaluate the adaptability and stability of the power consumption model through the evaluation requirements and evaluation frequency to obtain the corresponding evaluation results, and to fine-tune the power consumption model through the evaluation results.

[0087] Optionally, in one embodiment of the present application, the control module 300 includes: a determination unit and an interaction unit.

[0088] Among them, the determination unit is used to send the BEV power consumption prediction result and the remaining power consumption time to the target terminal based on the preset data middle platform API, so that the target terminal determines the key power consumption controller among multiple target controllers according to the BEV power consumption prediction result and the remaining power consumption time.

[0089] The interactive unit is used to adjust or shut down key power consumption controllers based on the usage needs of the target users, so as to obtain the corresponding operation information of the target users, and generate new remaining power consumption time or route planning adjustment suggestions based on the operation information, so as to generate and display a travel report through the new remaining power consumption time or route planning adjustment suggestions.

[0090] It should be noted that the aforementioned explanation of the embodiment of the BEV power consumption calculation method based on vehicle-mounted big data is also applicable to the BEV power consumption calculation device based on vehicle-mounted big data of this embodiment, and will not be repeated here.

[0091] According to the BEV power consumption calculation device based on vehicle-mounted big data proposed in the embodiment of the present application, it includes a fitting module 100, which is used to obtain the historical vehicle-mounted data of the target vehicle in the vehicle model development stage and the actual vehicle operation stage, and fit the BEV power consumption of the target vehicle through the historical vehicle-mounted data to build a power consumption model corresponding to the target vehicle; a prediction module 200, which is used to collect the current usage data of multiple target controllers in the target vehicle, and input the current usage data into the power consumption model to output the BEV power consumption prediction result of the target vehicle; a control module 300, which is used to calculate the remaining power consumption time of the target vehicle based on the BEV power consumption prediction result, and generate a trip report of the target vehicle through the remaining power consumption time, so that the target user controls the target vehicle to perform corresponding driving operations according to the trip report. The present application fits the BEV power consumption according to the historical vehicle-mounted big data, and estimates the power consumption and available time according to the fitting results and the current opening status of each controller, so as to perform trip notification and planning adjustment, thereby effectively improving the calculation efficiency of the power consumption of each component of the vehicle, greatly improving the user experience, and improving the humanization and intelligence level of the vehicle.

[0092] Figure 6 A schematic diagram of the structure of a vehicle provided in an embodiment of the present application. The vehicle may include:

[0093] A memory 601, a processor 602, and a computer program stored in the memory 601 and executable on the processor 602.

[0094] When the processor 602 executes the program, it implements the BEV power consumption calculation method based on vehicle-mounted big data provided in the above embodiments.

[0095] Furthermore, the vehicle further includes:

[0096] A communication interface 603 for communication between the memory 601 and the processor 602.

[0097] The memory 601 is used to store a computer program executable on the processor 602.

[0098] The memory 601 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory.

[0099] If the memory 601, the processor 602, and the communication interface 603 are implemented independently, the communication interface 603, the memory 601, and the processor 602 can be interconnected through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 6 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0100] Optionally, in a specific implementation, if the memory 601, the processor 602, and the communication interface 603 are integrated on a chip, the memory 601, the processor 602, and the communication interface 603 can communicate with each other through an internal interface.

[0101] The processor 602 may be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0102] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned BEV power consumption calculation method based on vehicle-mounted big data is implemented.

[0103] An embodiment of the present application also provides a computer program product, including a computer program, which is used to implement the above-mentioned BEV power consumption calculation method based on vehicle-mounted big data when executed.

[0104] In the description of this specification, the descriptions referring to terms such as "an embodiment", "some embodiments", "examples", "specific examples", or "some examples" etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0105] In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0106] Any process or method description shown in the flowchart or described in other ways herein can be understood as representing a module, segment, or part of the code including one or N executable instructions for implementing a customized logic function or process, and the scope of the preferred embodiment of the present application includes additional implementations, where the functions can be executed in a substantially simultaneous manner or in a reverse order according to the functions involved, rather than in the order shown or discussed, and this should be understood by those skilled in the art of the embodiments of the present application.

[0107] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in conjunction with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion (electronic device) having one or N wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then stored in a computer memory.

[0108] It should be understood that various parts of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above-described embodiments, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), and the like.

[0109] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the method of the above-described embodiments can be completed by a program instructing relevant hardware, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0110] In addition, each functional unit in various embodiments of the present application may be integrated into one processing module, or each unit may exist physically alone, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0111] The above-mentioned storage medium may be a read-only memory, a magnetic disk, an optical disc, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A method for calculating the BEV power consumption based on vehicle-mounted big data, characterized in that, Including the following steps: Obtain the historical in-vehicle data of the target vehicle during the vehicle model development stage and the actual vehicle operation stage, and fit the BEV power consumption of the target vehicle through the historical in-vehicle data to construct a power consumption model corresponding to the target vehicle; Collect the current usage data of multiple target controllers in the target vehicle, and input the current usage data into the power consumption model to output the BEV power consumption prediction result of the target vehicle; Based on the BEV power consumption prediction result, calculate the remaining power usage time of the target vehicle, and generate a trip report for the target vehicle through the remaining power usage time, so that the target user can control the target vehicle to perform corresponding driving operations according to the trip report.

2. The method according to claim 1, wherein The obtaining the historical in-vehicle data of the target vehicle during the vehicle model development stage and the actual vehicle operation stage, and fitting the BEV power consumption of the target vehicle through the historical in-vehicle data to construct a power consumption model corresponding to the target vehicle includes: Obtain the corresponding buried point signals through the TBOX buried points and in-vehicle system buried points during the vehicle model development stage, and report the buried point signals to a preset TSP cloud system, so that the TSP cloud system can parse the buried point signals according to the target protocol to obtain the corresponding buried point data; Upload the buried point data to a preset data middle platform, so that the data middle platform integrates the buried point data in the target space-time dimension to obtain the historical in-vehicle data.

3. The method according to claim 2, wherein The fitting the BEV power consumption of the target vehicle through the historical in-vehicle data to construct a power consumption model corresponding to the target vehicle includes: Perform data cleaning and preprocessing operations on the historical in-vehicle data to generate corresponding standard data; Obtain the time series corresponding to the standard data, and perform sliding window statistics on the time series to obtain the derivative variables corresponding to the standard data; Determine the model prediction requirements of the target vehicle, and perform feature screening operations on the standard data according to the model prediction requirements to obtain the corresponding screening variables; Determine the power consumption objective function corresponding to the target vehicle, and based on the power consumption objective function, construct a target regression model corresponding to the target vehicle, and train the target regression model through the derivative variables and the screening variables to generate the power consumption model.

4. The method according to claim 3, wherein After constructing the power consumption model corresponding to the target vehicle, it further includes: Deploy the power consumption model in a preset data middle platform API, and monitor the power consumption model through the data middle platform API to obtain the usage data corresponding to the power consumption model; Determine the evaluation requirements and evaluation frequency of the power consumption model according to the usage data, and perform adaptability and stability evaluations on the power consumption model through the evaluation requirements and the evaluation frequency to obtain the corresponding evaluation results, and fine-tune the power consumption model through the evaluation results.

5. The method according to claim 1, wherein The generating a trip report for the target vehicle through the remaining power usage time, so that the target user can control the target vehicle to perform corresponding driving operations according to the trip report includes: Based on a preset data middleware API, send the BEV power consumption prediction result and the remaining power consumption time to a target terminal, so that the target terminal determines a key power-consuming controller among the multiple target controllers according to the BEV power consumption prediction result and the remaining power consumption time; Based on the usage requirements of the target user, perform an adjustment or shutdown operation on the key power-consuming controller to obtain operation information corresponding to the target user, and generate a new remaining power consumption time or a route planning adjustment suggestion according to the operation information, so as to generate and display a trip report through the new remaining power consumption time or the route planning adjustment suggestion.

6. A BEV power consumption calculation device based on vehicle-mounted big data, characterized in that, Comprising: A fitting module, configured to obtain historical in-vehicle data of a target vehicle in the vehicle model development stage and the actual vehicle operation stage, and fit the BEV power consumption of the target vehicle through the historical in-vehicle data, so as to construct a power consumption model corresponding to the target vehicle; A prediction module, configured to collect current usage data of multiple target controllers in the target vehicle, and input the current usage data into the power consumption model to output a BEV power consumption prediction result of the target vehicle; A control module, configured to calculate the remaining power consumption time of the target vehicle based on the BEV power consumption prediction result, and generate a trip report of the target vehicle through the remaining power consumption time, so that a target user controls the target vehicle to perform corresponding driving operations according to the trip report.

7. The device according to claim 6, characterized in that, The fitting module includes: An analysis unit, configured to obtain corresponding buried point signals through TBOX buried points and in-vehicle system buried points in the vehicle model development stage, and report the buried point signals to a preset TSP cloud system, so that the TSP cloud system analyzes the buried point signals according to a target protocol to obtain corresponding buried point data; An integration unit, configured to upload the buried point data to a preset data middleware, so that the data middleware integrates the buried point data in a target space-time dimension to obtain the historical in-vehicle data.

8. A vehicle, characterized in that, Comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the BEV power consumption calculation method based on in-vehicle big data according to any one of claims 1-5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to be used for implementing the BEV power consumption calculation method based on in-vehicle big data according to any one of claims 1-5.

10. A computer program product, comprising a computer program, characterized in that, The computer program is executed to be used for implementing the BEV power consumption calculation method based on in-vehicle big data according to any one of claims 1-5.

Images