Method, device, storage medium and vehicle for determining vehicle energy management mode
By analyzing driving segment data of electric vehicles, the driver's needs and style can be determined, and the optimal energy management mode can be selected. This solves the problem of the lack of flexibility and adaptability of energy management modes in existing technologies, and improves the user experience.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA FAW CO LTD
- Filing Date
- 2023-05-26
- Publication Date
- 2026-05-29
AI Technical Summary
Existing electric vehicle energy management models lack flexibility and adaptability, resulting in a poor user experience.
By calculating driving and comfort data from multiple vehicle driving segments, dimensionality reduction clustering analysis is used to determine the driver's driving and comfort needs, thereby selecting the optimal energy management mode.
It improves the adaptability and flexibility of vehicle energy management, enhancing the user experience.
Smart Images
Figure CN116653966B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of vehicle energy management, and more specifically, to a method, apparatus, storage medium, and vehicle for determining a vehicle energy management mode. Background Technology
[0002] Energy management is an important research direction for electric vehicles. Currently, the energy management modes of electric vehicles are either fixed or require manual selection by the driver. Furthermore, existing technologies provide energy management modes based on fixed rules. For example, energy-saving mode limits the driver's driving energy output and also restricts the operating power or maximum capacity of comfort systems such as air conditioning; comfort mode ensures the maximum output capacity of comfort systems such as air conditioning. It is understandable that existing technologies provide uniform energy management modes that, once set for a specific vehicle, will not change. This results in poor flexibility in vehicle energy management methods, poor adaptability to driving behavior, and a poor user experience.
[0003] As the above analysis shows, there is currently no effective solution to the problems of poor adaptability, poor flexibility, and poor user experience of the vehicle energy management methods provided by the aforementioned technologies. Summary of the Invention
[0004] This invention provides a method, apparatus, storage medium, and vehicle for determining a vehicle energy management mode, to at least solve the technical problems of poor adaptability, poor flexibility, and poor user experience of vehicle energy management methods provided by related technologies.
[0005] According to one aspect of the present invention, a method for determining a vehicle energy management mode is provided, comprising:
[0006] Driving and comfort data from multiple vehicle driving segments are calculated to obtain data feature values. Dimensionality reduction and clustering analysis are then performed based on these feature values to obtain analysis results. These results include a first demand style and a second demand style. The first demand style determines the driver's driving demand style, and the second demand style determines the driver's comfort demand style. Based on the first and second demand styles, a target energy management mode is determined from multiple candidate energy management modes. This target energy management mode is used to assist in the energy management of the vehicle.
[0007] Optionally, the driving data includes driving behavior data and intelligent driving data. The data feature values include multiple first feature values, multiple second feature values, and multiple third feature values. The data feature values are calculated by analyzing the driving behavior data and comfort data of multiple driving segments of the vehicle, and the results include: calculating the first feature values from the driving behavior data of multiple driving segments of the vehicle, wherein the multiple first feature values are used to characterize the driver's driving behavior preferences; calculating the second feature values from the intelligent driving data of multiple driving segments of the vehicle, wherein the multiple second feature values are used to characterize the driver's preference for the assisted driving of the vehicle's intelligent driving system; and calculating the third feature values from the comfort data of multiple driving segments of the vehicle, wherein the multiple third feature values are used to characterize the driver's cabin comfort preferences.
[0008] Optionally, the first characteristic value of each driving segment in the multiple driving segments includes at least: maximum vehicle speed, maximum acceleration, maximum deceleration, maximum accelerator pedal opening, and maximum brake pedal opening; the second characteristic value of each driving segment in the multiple driving segments includes at least: number of times fatigued driving occurred, minimum following distance, number of times following warnings were issued, number of times lane departure occurred, and number of times active braking occurred; the third characteristic value of each driving segment in the multiple driving segments includes at least: air conditioning operating duration, cabin temperature difference, maximum air conditioning fan speed, maximum seat heating level, and maximum seat ventilation level, wherein the cabin temperature difference is the difference between the cabin temperature and the ambient temperature.
[0009] Optionally, dimensionality reduction and clustering analysis based on data feature values are performed to obtain the analysis results, including: using a target data dimensionality reduction algorithm to reduce the dimensionality of the data feature values corresponding to multiple driving segments, generating multiple target feature values corresponding to multiple driving segments; and using a target clustering algorithm to perform clustering analysis on the multiple target feature values to obtain the analysis results.
[0010] Optionally, the multiple target feature values include: a first target value and a second target value. Generating multiple target feature values corresponding to multiple driving segments by performing dimensionality reduction processing on the data feature values corresponding to multiple driving segments includes: performing dimensionality reduction processing on multiple first feature values and multiple second feature values corresponding to multiple driving segments to generate at least one first target value for each driving segment; and performing dimensionality reduction processing on multiple third feature values corresponding to multiple driving segments to generate at least one second target value for each driving segment.
[0011] Optionally, cluster analysis is performed on multiple target feature values to obtain the analysis results, including: cluster analysis based on the first target value corresponding to multiple driving segments to obtain the first demand style in the analysis results; and cluster analysis based on the second target value corresponding to multiple driving segments to obtain the second demand style in the analysis results.
[0012] Optionally, determining the target energy management mode from multiple candidate energy management modes based on the first demand style and the second demand style includes: determining the target energy management mode from multiple candidate energy management modes based on the first demand style, the second demand style, multiple driving style categories, and multiple comfort style categories, wherein the multiple driving style categories are used to characterize the driver's driving smoothness level, the multiple comfort style categories are used to characterize the driver's comfort demand level, and the multiple candidate energy management modes are used to characterize multiple power limitation levels of the vehicle's drive system and cabin temperature management system.
[0013] According to another aspect of the present invention, an apparatus for determining a vehicle energy management mode is also provided, comprising:
[0014] The calculation module is used to calculate driving data and comfort data from multiple driving segments of the vehicle to obtain data feature values; the analysis module is used to perform dimensionality reduction and clustering analysis based on the data feature values to obtain analysis results, including a first demand style and a second demand style. The first demand style is used to determine the driver's driving demand style for the vehicle, and the second demand style is used to determine the driver's comfort demand style for the vehicle; the determination module is used to determine the target energy management mode from multiple candidate energy management modes based on the first and second demand styles. The target energy management mode is used to assist in the energy management of the vehicle.
[0015] Optionally, the above calculation module is further configured to: calculate driving data including driving behavior data and intelligent driving data, and data feature values including multiple first feature values, multiple second feature values, and multiple third feature values; calculate driving data and comfort data for multiple driving segments of the vehicle to obtain data feature values including: calculating driving behavior data for multiple driving segments of the vehicle to obtain first feature values, wherein multiple first feature values are used to characterize the driver's driving behavior preferences; calculating intelligent driving data for multiple driving segments of the vehicle to obtain multiple second feature values, wherein multiple second feature values are used to characterize the driver's preference for assisted driving by the vehicle's intelligent driving system; and calculating comfort data for multiple driving segments of the vehicle to obtain multiple third feature values, wherein multiple third feature values are used to characterize the driver's cabin comfort preferences.
[0016] Optionally, the above calculation module is also used to: include at least the following as the first characteristic value of each driving segment in the multiple driving segments: maximum vehicle speed, maximum acceleration, maximum deceleration, maximum accelerator pedal opening, and maximum brake pedal opening; include at least the following as the second characteristic value of each driving segment in the multiple driving segments: number of times fatigued driving, minimum following distance, number of following warnings, number of lane departures, and number of times active braking is used; and include at least the following as the third characteristic value of each driving segment in the multiple driving segments: air conditioning operating time, cabin temperature difference, maximum air conditioning air volume, maximum seat heating level, and maximum seat ventilation level, wherein the cabin temperature difference is the difference between the cabin temperature and the ambient temperature.
[0017] Optionally, the above analysis module is also used for: performing dimensionality reduction and clustering analysis based on data feature values to obtain analysis results including: using a target data dimensionality reduction algorithm to reduce the dimensionality of data feature values corresponding to multiple driving segments to generate multiple target feature values corresponding to multiple driving segments; and using a target clustering algorithm to perform clustering analysis on multiple target feature values to obtain analysis results.
[0018] Optionally, the analysis module is further configured to: perform dimensionality reduction processing on the data feature values corresponding to the multiple driving segments, including a first target value and a second target value, to generate multiple target feature values corresponding to the multiple driving segments, including: performing dimensionality reduction processing on the multiple first feature values and multiple second feature values corresponding to the multiple driving segments to generate at least one first target value for each driving segment; and performing dimensionality reduction processing on the multiple third feature values corresponding to the multiple driving segments to generate at least one second target value for each driving segment.
[0019] Optionally, the above analysis module is further configured to: perform cluster analysis on multiple target feature values to obtain analysis results including: performing cluster analysis based on the first target values corresponding to multiple driving segments to obtain the first demand style in the analysis results; and performing cluster analysis based on the second target values corresponding to multiple driving segments to obtain the second demand style in the analysis results.
[0020] Optionally, the aforementioned determining module is further configured to: determine a target energy management mode from multiple candidate energy management modes based on a first demand style and a second demand style, including: determining the target energy management mode from multiple candidate energy management modes based on a first demand style, a second demand style, multiple driving style categories, and multiple comfort style categories, wherein the multiple driving style categories are used to characterize the driver's driving smoothness level, the multiple comfort style categories are used to characterize the driver's comfort demand level, and the multiple candidate energy management modes are used to characterize multiple power limiting levels for the vehicle's drive system and cabin temperature management system.
[0021] According to another aspect of the present invention, a storage medium is also provided, the storage medium including a stored program, wherein, when the program is running, the device where the storage medium is located executes the method for determining a vehicle energy management mode as described above.
[0022] According to another aspect of the present invention, a vehicle is also provided, including an on-board memory and an on-board processor, wherein the on-board memory stores a computer program, and the on-board processor is configured to run the computer program to perform the method for determining a vehicle energy management mode as described above.
[0023] In this embodiment of the invention, driving data and comfort data of multiple driving segments of the vehicle are first calculated to obtain data feature values. Then, dimensionality reduction clustering analysis is performed based on the data feature values to obtain analysis results. The analysis results include a first demand style and a second demand style. The first demand style is used to determine the driver's driving demand style for the vehicle, and the second demand style is used to determine the driver's comfort demand style for the vehicle. Finally, based on the first demand style and the second demand style, a target energy management mode is determined from multiple candidate energy management modes. The target energy management mode is used to assist in the energy management of the vehicle.
[0024] It is easy to understand that the method provided by the present invention calculates and analyzes driving data and comfort data from multiple driving segments of the vehicle to obtain the driver's driving style and comfort style. Then, based on the driver's driving style and comfort style, the method performs energy management on the vehicle, thereby improving the adaptability of vehicle energy management to the driver's driving style and comfort style. This improves the adaptability of vehicle energy management to driving behavior, increases the flexibility of vehicle energy management methods, and enhances the user experience. In turn, it solves the technical problems of poor adaptability, poor flexibility, and poor user experience of vehicle energy management methods provided by related technologies. Attached Figure Description
[0025] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this invention, illustrate exemplary embodiments of the invention and are used to explain the invention, but do not constitute an undue limitation of the invention. In the drawings:
[0026] Figure 1 This is a structural block diagram of a vehicle terminal for determining a vehicle energy management mode according to an embodiment of the present invention;
[0027] Figure 2 This is a flowchart of a method for determining a vehicle energy management mode according to an embodiment of the present invention;
[0028] Figure 3This is a structural block diagram of a device for determining a vehicle energy management mode according to an embodiment of the present invention. Detailed Implementation
[0029] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.
[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0031] According to an embodiment of the present invention, a method embodiment for determining a vehicle energy management mode is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.
[0032] Figure 1 This is a structural block diagram of a vehicle terminal for an optional method of determining a vehicle energy management mode according to an embodiment of the present invention, such as... Figure 1As shown, the vehicle terminal 10 (or a mobile device 10 that communicates with the vehicle) may include one or more processors 102 (processors 102 may include, but are not limited to, processing devices such as microprocessors (MCUs) or field-programmable gate arrays (FPGAs),) a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display device 110, an input / output device 108 (i.e., I / O devices), a Universal Serial Bus (USB) port (which may be included as one of the ports of a computer bus, not shown in the figure), a network interface (not shown in the figure), a power supply (not shown in the figure), and / or a camera (not shown in the figure). Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the vehicle terminal 1 described above. For example, the vehicle terminal 10 may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.
[0033] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits may be embodied, in whole or in part, as software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuitry may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the vehicle terminal 10 (or mobile device).
[0034] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the method for determining the vehicle energy management mode in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned method for determining the vehicle energy management mode. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the vehicle terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
[0035] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the vehicle terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.
[0036] Under the above operating environment, the embodiments of the present invention provide as follows: Figure 2 The method shown is for determining the vehicle energy management mode. Figure 2 This is a flowchart of a method for determining a vehicle energy management mode according to an embodiment of the present invention, such as... Figure 2 As shown above, Figure 2 The embodiments shown may include at least the following implementation steps, namely, the technical solutions implemented by steps S21 to S23.
[0037] Step S21: Calculate the driving data and comfort data of multiple driving segments of the vehicle to obtain data feature values;
[0038] In one optional solution provided by step S21 above, the aforementioned multiple driving segments can be multiple segments from the start to the shutdown of the vehicle's historical driving process. It should also be noted that these multiple driving segments can be acquired and segmented from monitoring equipment capable of monitoring the vehicle's driving process. This monitoring equipment may include, but is not limited to, a driving recorder, a road surveillance camera, or a camera installed externally to the vehicle. The aforementioned driving data can be used to characterize the driver's driving behavior. This driving data may include, but is not limited to, vehicle speed, acceleration, deceleration, accelerator pedal opening, brake pedal opening, number of instances of fatigued driving, following distance, lane change frequency, and active braking system operation frequency.
[0039] In one optional solution provided by step S21 above, the aforementioned comfort data can be used to characterize the comfort level of the vehicle equipment as perceived by the driver. This comfort data may include, but is not limited to: air conditioning operating time, the difference between the set temperature inside the vehicle and the ambient temperature, airflow volume, and frequency of seat heating use. These data characteristics can be used to characterize the driver's driving habits and usage habits of the vehicle's comfort system during vehicle operation.
[0040] Step S22: Perform dimensionality reduction clustering analysis based on data feature values to obtain analysis results. The analysis results include a first demand style and a second demand style. The first demand style is used to determine the driver's driving demand style for the vehicle, and the second demand style is used to determine the driver's comfort demand style for the vehicle.
[0041] In one optional solution provided by step S22 above, the analysis results may include driving demand style corresponding to driving data of multiple driving segments and comfort demand style corresponding to comfort data of multiple driving segments. Specifically, for example, if the vehicle speed is too fast and the following distance is too small based on the data feature values of multiple driving segments, it can indicate that the driver is more aggressive in controlling the vehicle. And if the driver does not turn on the air conditioner or turns on the air conditioner for a short time during the driving process based on the data feature values of multiple driving segments, it can indicate that the driver thinks the in-vehicle environment is more comfortable when the vehicle comfort system is running.
[0042] In the technical solution provided by this invention, dimensionality reduction and clustering analysis are performed based on data feature values to obtain analysis results. Specifically, the method can be as follows: for driving data and comfort data of multiple current driving segments, dimensionality reduction algorithm and clustering algorithm are used for analysis in sequence to determine the driver's driving style corresponding to the driving data of the current multiple driving segments and the driver's comfort style corresponding to the comfort data.
[0043] Step S23: Based on the first demand style and the second demand style, determine the target energy management mode from multiple candidate energy management modes, wherein the target energy management mode is used to assist in the energy management of the vehicle.
[0044] In one optional solution provided by step S23 above, the aforementioned multiple candidate energy management modes can be energy management modes preset by technicians based on popular driving data and / or comfort data. These multiple candidate energy management modes may include, but are not limited to: optimal driving capability mode, optimal comfort mode, and driving capability and comfort coordination mode.
[0045] In the optional solution provided by the present invention, a target energy management mode is determined from multiple candidate energy management modes according to a first demand style and a second demand style. Specifically, if the driver's current first demand style is aggressive and the second demand style is less comfortable, the best driving capability mode can be selected from multiple candidate energy management modes stored in the vehicle storage device as the target energy management mode, so that the vehicle energy management meets the current user's high demand for vehicle driving capability.
[0046] In this embodiment of the invention, driving data and comfort data of multiple driving segments of the vehicle are first calculated to obtain data feature values. Then, dimensionality reduction clustering analysis is performed based on the data feature values to obtain analysis results. The analysis results include a first demand style and a second demand style. The first demand style is used to determine the driver's driving demand style for the vehicle, and the second demand style is used to determine the driver's comfort demand style for the vehicle. Finally, based on the first demand style and the second demand style, a target energy management mode is determined from multiple candidate energy management modes. The target energy management mode is used to assist in the energy management of the vehicle.
[0047] It is easy to understand that the method provided by the present invention calculates and analyzes driving data and comfort data from multiple driving segments of the vehicle to obtain the driver's driving style and comfort style. Then, based on the driver's driving style and comfort style, the method performs energy management on the vehicle, thereby improving the adaptability of vehicle energy management to the driver's driving style and comfort style. This improves the adaptability of vehicle energy management to driving behavior, increases the flexibility of vehicle energy management methods, and enhances the user experience. In turn, it solves the technical problems of poor adaptability, poor flexibility, and poor user experience of vehicle energy management methods provided by related technologies.
[0048] The methods described in the embodiments of the present invention will be further described below.
[0049] In an optional embodiment, in step S21, the driving data includes: driving behavior data and intelligent driving data, and the data feature values include: multiple first feature values, multiple second feature values, and multiple third feature values. The driving data and comfort data for multiple driving segments of the vehicle are calculated to obtain the following data feature values:
[0050] Step S211: Calculate the driving behavior data of multiple driving segments of the vehicle to obtain first feature values, wherein multiple first feature values are used to characterize the driver's driving behavior preferences.
[0051] Step S212: Calculate the intelligent driving data of multiple driving segments of the vehicle to obtain multiple second feature values, wherein the multiple second feature values are used to characterize the driver's preference for the vehicle's intelligent driving system.
[0052] Step S213: Calculate the comfort data of multiple driving segments of the vehicle to obtain multiple third feature values, wherein the multiple third feature values are used to characterize the driver's cabin comfort preference.
[0053] In one optional solution provided by steps S211 to S213 above, the driving behavior data can be stored in the vehicle's driving database or a cloud-based driving database that communicates with the vehicle. This driving behavior data may include, but is not limited to, vehicle speed, acceleration, deceleration, accelerator pedal opening, and brake pedal opening. The intelligent driving data can be stored in the vehicle's intelligent driving database or a cloud-based intelligent driving database that communicates with the vehicle. This intelligent driving data may include, but is not limited to, air conditioning activation signals, in-vehicle set temperature, ambient temperature, fan speed level, and seat heating signals. The comfort data can be stored in the vehicle's comfort database or a cloud-based comfort database that communicates with the vehicle. This comfort data may include, but is not limited to, driver fatigue signals, following distance signals, lane keeping signals, and active braking system operating signals.
[0054] In the technical solution provided by this invention, before calculating the data feature values from driving data and comfort data of multiple driving segments of a vehicle, the acquired driving data and comfort data of multiple driving segments are preprocessed, including but not limited to: filtering out abnormal data and supplementing missing data through interpolation and other methods. It should also be noted that in the technical solution provided by this invention, the process of storing and processing driving behavior data, intelligent driving data, and comfort data of multiple driving segments of a vehicle can be completed by the vehicle itself, or it can be completed in an enterprise backend database capable of data communication with the vehicle.
[0055] The technical solution provided by this invention also reveals that, in the vehicle or cloud, the database used for storing data can be divided into two layers: a Data Warehouse (DW) layer, including basic data layers such as driving signal database, comfort signal database, and intelligent driving database; and an Operational Data Store (ODS) layer, used to store calculated data values (including but not limited to the aforementioned first feature value, second feature value, and third feature value). It should be noted that multiple signals are extracted from the vehicle network signals, divided into two categories, and stored separately in the driving signal database and comfort signal database. When the vehicle's intelligence level is high, an intelligent driving database can also be added.
[0056] In the above optional embodiments, the technical effect that can be achieved is: to acquire multiple types of vehicle data (including the above-mentioned driving behavior data, intelligent driving data, and comfort data) and perform preprocessing and calculation to obtain the feature values (including the above-mentioned first feature value, second feature value, and third feature value) corresponding to each type of vehicle data, thereby improving the accuracy of the feature values, which helps to obtain accurate driving demand style and comfort demand style in subsequent dimensionality reduction clustering analysis.
[0057] In an optional embodiment, in step S21, the first characteristic value of each driving segment in the plurality of driving segments includes at least: maximum vehicle speed, maximum acceleration, maximum deceleration, maximum accelerator pedal opening, and maximum brake pedal opening; the second characteristic value of each driving segment in the plurality of driving segments includes at least: number of times fatigue driving occurs, minimum following distance, number of times following warning occurs, number of times lane departure occurs, and number of times active braking occurs; the third characteristic value of each driving segment in the plurality of driving segments includes at least: air conditioning operating time, cabin temperature difference, maximum air conditioning airflow, maximum seat heating level, and maximum seat ventilation level, wherein the cabin temperature difference is the difference between the cabin temperature and the ambient temperature.
[0058] In one optional solution provided by step S21 above, the first characteristic value may further include: the rate of change of accelerator pedal opening (which can be used to characterize the speed of accelerator pedal depressing) and the rate of change of brake drum pedal opening (which can be used to characterize the speed of brake pedal depressing). The third characteristic value may further include: the ratio of air conditioning on duration to the total duration of the corresponding driving segment, the ratio of seat heating duration to the total duration of the corresponding driving segment, and the ratio of seat ventilation duration to the total duration of the corresponding driving segment.
[0059] In the technical solution provided by this invention, it should also be noted that when the driver selects the air conditioner to operate in automatic mode, the maximum air volume of the air conditioner can be calculated based on the actual windshield value.
[0060] In an optional embodiment, in step S22, dimensionality reduction clustering analysis is performed based on data feature values to obtain the analysis results, including:
[0061] Step S221: Using a target data dimensionality reduction algorithm, the data feature values corresponding to multiple driving segments are dimensionality reduced to generate multiple target feature values corresponding to multiple driving segments.
[0062] Step S222: Use the target clustering algorithm to perform clustering analysis on multiple target feature values to obtain the analysis results.
[0063] In one optional scheme provided by steps S221 to S222 above, the target data dimensionality reduction algorithm can be one of a variety of data dimensionality reduction algorithms, including but not limited to: Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), t-SNE, and Non-negative Matrix Factorization (NMF). Similarly, the target clustering algorithm can be one of a variety of clustering algorithms, including but not limited to: K-means clustering, Hierarchical Clustering, Density Peak Clustering, and Gaussian Mixture Model (GMM).
[0064] In the technical solution provided by this invention, it should be noted that, since there are a large number of the first, second, and third feature values, when classifying them, the target data dimensionality reduction algorithm can be used to reduce the dimensionality of the three features while retaining their original information and meaning, thereby obtaining new feature values. This reduces the computational load and saves data space when processing the new feature values, thus improving the processing efficiency of the three features. Furthermore, since the new feature values retain the original information and meaning of the first, second, and third feature values, the driving demand style in the analysis results corresponds to the driving data of the corresponding driving segment, and the comfort demand style corresponds to the comfort data of the corresponding driving segment, thus ensuring the accuracy of the analysis results.
[0065] In an optional embodiment, in step S221, the multiple target feature values include: a first target value and a second target value. Dimensionality reduction processing is performed on the data feature values corresponding to the multiple driving segments to generate the multiple target feature values corresponding to the multiple driving segments, including:
[0066] Step S2211: Perform data dimensionality reduction processing on multiple first feature values and multiple second feature values corresponding to multiple driving segments to generate at least one first target value for each driving segment in the multiple driving segments;
[0067] Step S2212: Perform data dimensionality reduction processing on multiple third feature values corresponding to multiple driving segments to generate at least one second target value for each driving segment.
[0068] In one optional solution provided by steps S2211 to S2212 above, the first target value may include, but is not limited to: the dimensionality reduction feature corresponding to the first feature value of driving behavior data, and the dimensionality reduction feature corresponding to the first feature value of intelligent driving data. The second target value may include, but is not limited to: the dimensionality reduction feature corresponding to the first feature value of comfort data. It should be noted here that the first target value retains the information and meaning of the original feature values (the aforementioned first feature value, second feature value, and third feature value).
[0069] As an optional implementation method, taking comfort data as an example, the principal component analysis algorithm is used to perform data dimensionality reduction on the first feature values of the comfort data corresponding to multiple driving segments, generating multiple target feature values corresponding to multiple driving segments. Specifically, the method can be as follows: based on the first feature value of the comfort data of each driving segment in multiple driving segments, the covariance matrix C corresponding to the first feature value of the comfort data of multiple driving segments is calculated. Further, k features are selected from the covariance matrix H as new features (i.e., the second target value mentioned above), and the feature vectors corresponding to the k features are combined into a k-order matrix. Then, the k-order matrix and the first feature value matrix of the comfort data of multiple driving segments are calculated to obtain the dimensionality-reduced data.
[0070] In the above optional implementation, it should also be noted that selecting k features from the covariance matrix C as new features can be achieved by calculating the eigenvalue λ of the first eigenvalue of each driving segment according to the method shown in formula (1) below. i Contribution m i :
[0071]
[0072] Furthermore, the eigenvalue λ of the first eigenvalue of each driving segment is... i Contribution m i Compared with a preset contribution threshold (e.g., 0.95), when the feature value λ of the first feature value of the f-th driving segment... f Contribution m f Satisfy m f When ≥0.95, the eigenvalue λ of the first eigenvalue of this driving segment is... f As a new feature after dimensionality reduction.
[0073] In the above optional embodiments, the technical effect that can be achieved is: dimensionality reduction processing of the corresponding data feature values of multiple driving segments to obtain multiple target feature values. While retaining the original information and meaning of the data feature values, the dimensionality of the data in the subsequent processing process is reduced, thereby ensuring the accuracy of the processing results obtained in the subsequent processing process, reducing the amount of computation in the subsequent processing process, and improving the processing efficiency.
[0074] In an optional embodiment, in step S222, cluster analysis is performed on multiple target feature values to obtain the analysis results, including:
[0075] Step S2221: Perform cluster analysis based on the first target value corresponding to multiple driving segments to obtain the first demand style in the analysis results;
[0076] Step S2222: Perform cluster analysis based on the second target values corresponding to multiple driving segments to obtain the second demand style in the analysis results.
[0077] As an optional implementation, still using comfort data as an example, the K-means algorithm is used to perform cluster analysis on the k-order matrix corresponding to the second target value of multiple driving segments. Specifically, this can be done as follows: select N samples from the k-order matrix for clustering, and define the cluster as G classes; randomly select T objects from the N samples as the initial cluster centers; then calculate the distance from each sample to the initial center, and add samples that meet the distance condition to the initial center's class according to the principle of minimum distance; recalculate the center of each class, which can be done by using the mean of all samples in a class set as the center point for the second iteration; repeat the sample classification and calculation of class centers until convergence, at which point the clustering calculation is considered complete. It should be noted that convergence can include, but is not limited to, the following: the number of iterations reaches a preset threshold, and the cluster centers no longer change. It is understandable that when the rate of change of comfort data is large (i.e., indicating that the driver frequently adjusts the vehicle comfort control system), it can be determined that the driver's comfort needs are high. During the subsequent driving process, the vehicle comfort control system can be adjusted in a timely manner based on the automatically detected comfort data inside and outside the vehicle (e.g., automatically controlling the air conditioning to turn off when the outside temperature is detected to be low).
[0078] In the above optional embodiments, the technical effects that can be achieved are: by performing calculation and dimensionality reduction clustering analysis on driving data and driving data of multiple historical driving segments of the vehicle, the driver's various driving styles and comfort styles for the vehicle are obtained, improving the accuracy of driving style and comfort style. Thus, in the subsequent driving process of the vehicle, one or more control systems of the vehicle can be controlled according to the driver's driving style and comfort style. The control system may include, but is not limited to: drive control, body comfort control system, and safety system, thereby improving the flexibility of the vehicle control process, improving its adaptability to the driver's driving behavior, and enhancing the user experience.
[0079] In an optional embodiment, in step S23, determining the target energy management mode from multiple candidate energy management modes based on the first demand style and the second demand style includes:
[0080] Based on the first demand style, the second demand style, multiple driving style categories, and multiple comfort style categories, a target energy management mode is determined from multiple candidate energy management modes. Among them, multiple driving style categories are used to characterize the driver's driving smoothness level, multiple comfort style categories are used to characterize the driver's comfort demand level, and multiple candidate energy management modes are used to characterize multiple power limitation levels of the vehicle's drive system and cabin temperature management system.
[0081] In one optional solution provided by step S23 above, the cabin temperature management system may include, but is not limited to: an air conditioning system, a ventilation system, and a seat heating system.
[0082] As an optional implementation, various driving style categories may include, but are not limited to: Type A, Type B, and Type C. It should be noted that the three driving style categories can represent the driver's driving style from smooth to aggressive. Specifically, Type A can represent the smoothest driving style, and Type C can represent the most aggressive driving style.
[0083] As another optional implementation, various comfort style categories may include, but are not limited to: Type I, Type II, and Type III. It should be noted that the three comfort style categories can represent the driver's level of comfort pursuit increasing in sequence. Specifically, Type I can represent the driver's lowest comfort requirement, and Type III can represent the driver's highest comfort requirement.
[0084] As another optional implementation, the various candidate energy management modes corresponding to the various driving style categories and various comfort style categories can be shown in Table 1 below:
[0085] Table 1
[0086]
[0087] In the technical solution provided by this invention, it is understood that when it is determined, based on driving data and comfort data, that the driver has extremely high comfort requirements and moderate driving requirements (e.g., comfort style type III, driving style type A or B), the rate of power output of the drive system should be appropriately limited during subsequent vehicle control (i.e., limiting vehicle acceleration and other driving capabilities), while ensuring the vehicle has maximum comfort system capability. Conversely, when it is determined, based on driving data and comfort data, that the driver has extremely high driving requirements and moderate comfort requirements (e.g., comfort style type I or II, driving style type C), the comfort system capability should be appropriately limited during subsequent vehicle control to reserve energy for the vehicle's drive end, thereby facilitating the driver's ability to perform tasks at any time. The system provides reserve power for rapid acceleration. When driving and comfort data indicate that the driver's requirements for comfort and drivability are moderate (e.g., comfort style type I or II, driving style type A or B), energy is allocated to the comfort and drive systems according to the driver's needs during subsequent vehicle control. When driving and comfort data indicate that the driver's requirements for comfort and drivability are extremely high (e.g., comfort style type III, driving style type C), due to the limited capabilities of the vehicle's comfort and drive systems, the rate of power output from the drive system should be appropriately limited during subsequent vehicle control (i.e., limiting vehicle acceleration and other driving capabilities), and energy should be allocated to the comfort and drive systems according to the driver's needs.
[0088] In the above optional embodiments, the technical effects that can be achieved are as follows: during the actual driving process of the vehicle, the driver's driving style and comfort style can be determined based on the real-time collected vehicle data (including but not limited to: real-time driving data and real-time comfort data). Subsequently, when the driver drives the vehicle, the target energy management mode can be selected to manage the vehicle's energy based on the driver's driving style and comfort style, thereby improving the flexibility of vehicle energy management, improving the adaptability of vehicle energy management to the driver's driving behavior, and enhancing the user experience.
[0089] In this embodiment, a device for determining a vehicle energy management mode is also provided. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, a "module" is a combination of software and / or hardware that can perform a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.
[0090] Figure 3 This is a structural block diagram of a device for determining a vehicle energy management mode according to an embodiment of the present invention, such as... Figure 3 As shown, the device includes:
[0091] According to another aspect of the present invention, an apparatus for determining a vehicle energy management mode is also provided, comprising:
[0092] The calculation module 301 is used to calculate driving data and comfort data of multiple driving segments of the vehicle to obtain data feature values;
[0093] Analysis module 302 is used to perform dimensionality reduction clustering analysis based on data feature values to obtain analysis results. The analysis results include a first demand style and a second demand style. The first demand style is used to determine the driver's driving demand style for the vehicle, and the second demand style is used to determine the driver's comfort demand style for the vehicle.
[0094] The determination module 303 is used to determine a target energy management mode from multiple candidate energy management modes based on a first demand style and a second demand style, wherein the target energy management mode is used to assist in the energy management of the vehicle.
[0095] Optionally, the calculation module 301 is further configured to: calculate driving data including driving behavior data and intelligent driving data, and data feature values including multiple first feature values, multiple second feature values, and multiple third feature values; calculate driving data and comfort data for multiple driving segments of the vehicle to obtain data feature values including: calculating driving behavior data for multiple driving segments of the vehicle to obtain first feature values, wherein multiple first feature values are used to characterize the driver's driving behavior preferences; calculating intelligent driving data for multiple driving segments of the vehicle to obtain multiple second feature values, wherein multiple second feature values are used to characterize the driver's preference for assisted driving by the vehicle's intelligent driving system; and calculating comfort data for multiple driving segments of the vehicle to obtain multiple third feature values, wherein multiple third feature values are used to characterize the driver's cabin comfort preferences.
[0096] Optionally, the calculation module 301 is further configured to: include at least the following as the first characteristic value of each driving segment in the plurality of driving segments: maximum vehicle speed, maximum acceleration, maximum deceleration, maximum accelerator pedal opening and maximum brake pedal opening; include at least the following as the second characteristic value of each driving segment in the plurality of driving segments: number of times fatigue driving occurs, minimum following distance, number of times following warning occurs, number of times lane departure occurs and number of times active braking occurs; and include at least the following as the third characteristic value of each driving segment in the plurality of driving segments: air conditioning duration, cabin temperature difference, maximum air conditioning airflow, maximum seat heating level and maximum seat ventilation level, wherein the cabin temperature difference is the difference between the cabin temperature and the ambient temperature.
[0097] Optionally, the analysis module 302 is further configured to: perform dimensionality reduction and clustering analysis based on data feature values to obtain analysis results including: using a target data dimensionality reduction algorithm to perform dimensionality reduction processing on the data feature values corresponding to multiple driving segments to generate multiple target feature values corresponding to multiple driving segments; and using a target clustering algorithm to perform clustering analysis on the multiple target feature values to obtain analysis results.
[0098] Optionally, the analysis module 302 is further configured to: perform dimensionality reduction processing on the data feature values corresponding to the multiple driving segments, including a first target value and a second target value, to generate multiple target feature values corresponding to the multiple driving segments, including: performing dimensionality reduction processing on the multiple first feature values and multiple second feature values corresponding to the multiple driving segments to generate at least one first target value for each of the multiple driving segments; and performing dimensionality reduction processing on the multiple third feature values corresponding to the multiple driving segments to generate at least one second target value for each of the multiple driving segments.
[0099] Optionally, the analysis module 302 is further configured to: perform cluster analysis on multiple target feature values to obtain analysis results including: performing cluster analysis based on the first target values corresponding to multiple driving segments to obtain the first demand style in the analysis results; and performing cluster analysis based on the second target values corresponding to multiple driving segments to obtain the second demand style in the analysis results.
[0100] Optionally, the determining module 303 is further configured to: determine a target energy management mode from multiple candidate energy management modes based on a first demand style and a second demand style, including: determining the target energy management mode from multiple candidate energy management modes based on a first demand style, a second demand style, multiple driving style categories, and multiple comfort style categories, wherein the multiple driving style categories are used to characterize the driver's driving smoothness level, the multiple comfort style categories are used to characterize the driver's comfort demand level, and the multiple candidate energy management modes are used to characterize multiple power limitation levels of the vehicle's drive system and cabin temperature management system.
[0101] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.
[0102] In this embodiment, a storage medium is also provided, the storage medium including a stored program, wherein, when the program is running, the device where the storage medium is located executes any of the aforementioned methods for determining a vehicle energy management mode.
[0103] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:
[0104] Step S1: Calculate the driving data and comfort data of multiple driving segments of the vehicle to obtain data feature values;
[0105] Step S2: Perform dimensionality reduction clustering analysis based on data feature values to obtain analysis results. The analysis results include a first demand style and a second demand style. The first demand style is used to determine the driver's driving demand style for the vehicle, and the second demand style is used to determine the driver's comfort demand style for the vehicle.
[0106] Step S3: Based on the first demand style and the second demand style, determine the target energy management mode from multiple candidate energy management modes, wherein the target energy management mode is used to assist in the energy management of the vehicle.
[0107] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.
[0108] In this embodiment, a vehicle is also provided, including an on-board memory and an on-board processor. The on-board memory stores a computer program, and the on-board processor is configured to run the computer program to execute the method for determining a vehicle energy management mode as described above.
[0109] Optionally, in this embodiment, the on-board processor can be configured to perform the following steps via a computer program:
[0110] Step S1: Calculate the driving data and comfort data of multiple driving segments of the vehicle to obtain data feature values;
[0111] Step S2: Perform dimensionality reduction clustering analysis based on data feature values to obtain analysis results. The analysis results include a first demand style and a second demand style. The first demand style is used to determine the driver's driving demand style for the vehicle, and the second demand style is used to determine the driver's comfort demand style for the vehicle.
[0112] Step S3: Based on the first demand style and the second demand style, determine the target energy management mode from multiple candidate energy management modes, wherein the target energy management mode is used to assist in the energy management of the vehicle.
[0113] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and their optional implementations, which will not be repeated here.
[0114] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0115] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.
[0116] In the several embodiments provided by this invention, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection can be through some interfaces; the indirect coupling or communication connection of units or modules can be electrical or other forms.
[0117] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0118] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0119] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.
[0120] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.
Claims
1. A method for determining a vehicle energy management mode, characterized in that, include: The driving data and comfort data of multiple driving segments of the vehicle are calculated to obtain data feature values; Dimensionality reduction clustering analysis is performed based on the data feature values to obtain analysis results, wherein the analysis results include a first demand style and a second demand style. The first demand style is used to determine the driver's driving demand style for the vehicle, and the second demand style is used to determine the driver's comfort demand style for the vehicle. Based on the first demand style and the second demand style, a target energy management mode is determined from multiple candidate energy management modes, wherein the target energy management mode is used to assist in the energy management of the vehicle; The driving data includes driving behavior data and intelligent driving data. The data feature values include multiple first feature values, multiple second feature values, and multiple third feature values. The data feature values are calculated by analyzing the driving data and comfort data for multiple driving segments of the vehicle. Specifically, the calculations include: calculating the first feature values from the driving behavior data for the multiple driving segments of the vehicle, where the multiple first feature values characterize the driver's driving behavior preferences; calculating the multiple second feature values from the intelligent driving data for the multiple driving segments of the vehicle, where the multiple second feature values characterize the driver's preference for the vehicle's intelligent driving system's assisted driving; and calculating the multiple third feature values from the comfort data for the multiple driving segments of the vehicle, where the multiple third feature values characterize the driver's cabin comfort preferences.
2. The method according to claim 1, characterized in that, The first characteristic value of each of the plurality of driving segments includes at least: maximum vehicle speed, maximum acceleration, maximum deceleration, maximum accelerator pedal opening, and maximum brake pedal opening; The second characteristic value of each of the multiple driving segments includes at least: number of times fatigued driving occurred, minimum following distance, number of times following warning was issued, number of times lane departure occurred, and number of times active braking was performed; The third characteristic value of each of the multiple driving segments includes at least: air conditioning on duration, cabin temperature difference, maximum air conditioning air volume, maximum seat heating level, and maximum seat ventilation level, wherein the cabin temperature difference is the difference between the cabin temperature and the ambient temperature.
3. The method according to claim 1, characterized in that, Dimensionality reduction and clustering analysis were performed based on the data feature values, and the analysis results include: A target data dimensionality reduction algorithm is used to reduce the dimensionality of the data feature values corresponding to the multiple driving segments, thereby generating multiple target feature values corresponding to the multiple driving segments. The target clustering algorithm is used to perform cluster analysis on the multiple target feature values to obtain the analysis results.
4. The method according to claim 3, characterized in that, The plurality of target feature values include: a first target value and a second target value. The data feature value data corresponding to the plurality of driving segments undergoes dimensionality reduction processing to generate the plurality of target feature values corresponding to the plurality of driving segments, including: Data dimensionality reduction processing is performed on the plurality of first feature values and the plurality of second feature values corresponding to the plurality of driving segments to generate at least one first target value for each of the plurality of driving segments; Data dimensionality reduction processing is performed on the multiple third feature values corresponding to the multiple driving segments to generate at least one second target value for each of the multiple driving segments.
5. The method according to claim 4, characterized in that, Cluster analysis is performed on the multiple target feature values to obtain the analysis results, including: Cluster analysis is performed based on the first target value corresponding to the multiple driving segments to obtain the first demand style in the analysis results; Cluster analysis is performed based on the second target value corresponding to the multiple driving segments to obtain the second demand style in the analysis results.
6. The method according to claim 1, characterized in that, Based on the first demand style and the second demand style, the target energy management mode is determined from multiple candidate energy management modes, including: Based on the first demand style, the second demand style, multiple driving style categories, and multiple comfort style categories, the target energy management mode is determined from multiple candidate energy management modes. The multiple driving style categories are used to characterize the driver's driving smoothness level, the multiple comfort style categories are used to characterize the driver's comfort demand level, and the multiple candidate energy management modes are used to characterize multiple power limitation levels for the vehicle's drive system and cabin temperature management system.
7. A device for determining a vehicle energy management mode, characterized in that, include: The calculation module is used to calculate driving data and comfort data from multiple driving segments of the vehicle to obtain data feature values; An analysis module is used to perform dimensionality reduction clustering analysis based on the data feature values to obtain analysis results, wherein the analysis results include a first demand style and a second demand style, the first demand style is used to determine the driver's driving demand style for the vehicle, and the second demand style is used to determine the driver's comfort demand style for the vehicle. The determination module is used to determine a target energy management mode from multiple candidate energy management modes based on the first demand style and the second demand style, wherein the target energy management mode is used to assist in energy management of the vehicle; The driving data includes driving behavior data and intelligent driving data. The data feature values include multiple first feature values, multiple second feature values, and multiple third feature values. The calculation module is further configured to calculate the driving behavior data of the multiple driving segments of the vehicle to obtain the first feature values, wherein the multiple first feature values are used to characterize the driver's driving behavior preferences; calculate the intelligent driving data of the multiple driving segments of the vehicle to obtain the multiple second feature values, wherein the multiple second feature values are used to characterize the driver's preference for assisted driving by the vehicle's intelligent driving system; and calculate the comfort data of the multiple driving segments of the vehicle to obtain the multiple third feature values, wherein the multiple third feature values are used to characterize the driver's cabin comfort preferences.
8. A storage medium, characterized in that, The storage medium includes a stored program, wherein, when the program is executed, the device containing the storage medium is controlled to perform the method for determining a vehicle energy management mode according to any one of claims 1 to 6.
9. A vehicle, characterized in that, The device includes an on-board memory and an on-board processor, characterized in that the on-board memory stores a computer program, and the on-board processor is configured to run the computer program to perform the method for determining a vehicle energy management mode according to any one of claims 1 to 6.