Vehicle energy management system and method

Abstract

A vehicle energy management system is presented. The system comprises a receiving unit configured to receive data related to a motion state of a vehicle, and a determining unit configured to determine an equivalent fuel factor based on the data using a machine learning model. The machine learning model is trained based on known data related to a motion state of a vehicle and corresponding equivalent fuel factors. By determining the equivalent fuel factor using data related to a motion state of a vehicle, the equivalent fuel factor can be determined without knowing the driving cycle, which simplifies the system and improves the accuracy of determining the equivalent fuel factor.

Description

TECHNICAL FIELD

[0001] The present application relates to vehicles, and more particularly to management of energy of a vehicle. BACKGROUND

[0002] Currently, for the purpose of protecting the environment and saving energy, hybrid vehicles using new energy have been widely developed and applied, including hybrid electric vehicles (HEV), fuel cell electric vehicles (FCEV) and fuel cell hybrid electric vehicles (FCHEV) etc. Energy management strategy is a key technology for hybrid vehicles, which plays an important role in saving cost and increasing the range.

[0003] One of the energy management strategies that has been proposed is the equivalent fuel consumption minimization strategy (ECMS), and determining the optimal equivalent fuel factor is a key technology therein, through which fuel consumption minimization in a hybrid vehicle can be achieved. Currently, the equivalent fuel factor is determined based on identification of the driving condition of the vehicle. The driving condition can include: city driving, country driving and high-speed driving, etc. After the driving condition is identified, based on the determined current driving condition, a lookup table in which various driving conditions and corresponding equivalent fuel factors are stored is used to look up the equivalent fuel factor corresponding to the current driving condition.

[0004] In actual driving process, the condition of the vehicle is complex, and it can be difficult to meet the needs of complex conditions by determining the corresponding equivalent fuel factor through table lookup only for predetermined driving conditions. For example, although city driving involves complex driving situations, it is usually only assigned one specific equivalent fuel factor. If the needs of complex conditions are to be met, in the case of a large variety of driving conditions, the storage resources occupied by the lookup table are considerable. This is particularly problematic for vehicle-mounted systems with limited storage capacity.

[0005] Therefore, it is desirable to provide improved management of energy of a vehicle. SUMMARY

[0006] An improved vehicle energy management system and method are provided, which can directly obtain the equivalent fuel factor according to data related to the motion state of the vehicle without knowing the driving condition of the vehicle in advance.

[0007] According to one aspect of the present application, a vehicle energy management system is provided. The system comprises: a receiving unit configured to receive data related to the motion state of the vehicle; and a determining unit configured to determine an equivalent fuel factor based on the data using a machine learning model; wherein the machine learning model is trained based on known data related to the motion state of the vehicle and corresponding equivalent fuel factors.

[0008] According to another aspect of the present invention, a vehicle energy management method is provided. The method includes: receiving data related to the vehicle's motion state; and determining an equivalent fuel factor based on the data using a machine learning model; wherein the machine learning model is trained based on known data related to the vehicle's motion state and corresponding equivalent fuel factors.

[0009] According to another aspect of the present invention, a vehicle energy management device is provided. The device includes: a memory storing computer-readable instructions; and a processor, which, when executed by the computer-readable instructions, causes the processor to perform methods according to various embodiments of the present invention.

[0010] According to another aspect of the present invention, a computer storage medium is provided having computer-readable instructions stored thereon, which, when executed by a processor, cause the processor to perform the methods described according to various embodiments of the present invention.

[0011] According to various embodiments of the present invention, the equivalent fuel factor can be obtained directly from data related to the vehicle's motion state without prior knowledge of the vehicle's driving conditions. Therefore, there is no need to store a lookup table containing specific vehicle driving conditions and corresponding equivalent fuel factors, thus saving system storage space. Furthermore, determining the equivalent fuel factor based on data related to the vehicle's motion state makes the determined equivalent fuel factor more applicable to the current actual driving conditions, thereby improving the accuracy of the equivalent fuel factor determination.

[0012] Those skilled in the art will recognize other advantages of the invention after reading and understanding the following detailed description. Attached Figure Description

[0013] Figure 1 A block diagram of a vehicle energy management system according to an embodiment of the present invention is shown.

[0014] Figure 2 An exemplary neural network model for determining the equivalent fuel factor is shown according to an embodiment of the present invention.

[0015] Figure 3 A flowchart of a vehicle energy management method according to an embodiment of the present invention is shown. Detailed Implementation

[0016] Figure 1A block diagram of a vehicle energy management system 100 according to an embodiment of the present invention is shown. The system 100 includes at least a receiving unit 101 and a determining unit 102. The receiving unit 101 receives data related to the vehicle's motion state, particularly data related to the vehicle's speed, acceleration, and zero-speed time. The determining unit 102 utilizes, for example... Figure 2 The machine learning model 10 shown determines the equivalent fuel factor based on the data received by the receiving unit 10. The machine learning model 10 is, for example, a feedforward neural network regression model.

[0017] Figure 2 An exemplary machine learning model 10 according to an embodiment of the present invention is shown, which receives data D related to the motion state of a vehicle. in As input to the model, it outputs an equivalent fuel factor E. Therefore, it is easy to understand that the machine learning model 10 is trained using a large amount of known data related to the vehicle's motion state and the corresponding optimal equivalent fuel factor through machine learning methods. Those skilled in the art will understand that the model's hyperparameters and hidden units (e.g., number of iterations, expected error, etc.) can be adjusted before training to minimize overfitting and underfitting, thereby meeting the requirements for model accuracy.

[0018] For example, for a specific vehicle configuration, the optimal equivalent fuel factor can be determined based on specific data related to the vehicle's motion state, minimizing fuel consumption. Ultimately, the machine learning model 10 is trained using a large amount of specific data and the corresponding known optimal equivalent fuel factor.

[0019] The aforementioned data related to the vehicle's motion state can be obtained by the corresponding sensors 20, which include, but are not limited to, speed sensors, acceleration sensors, and timers.

[0020] It is understood that sensor 20 can be included in system 100 as part of system 100. Alternatively, sensor 20 can be a component of system 100 independently; for example, sensor 20 can be an in-vehicle sensor, or sensor 20 can be integrated into a smart mobile device. Sensor 20, independent of system 100, can use a communication module to transmit acquired data to receiving unit 101 of system 100.

[0021] In a preferred embodiment, the determining unit 102 first derives at least one feature data based on data related to the vehicle's motion state. For example, it derives feature data related to speed statistics based on received speed data and feature data related to acceleration statistics based on received acceleration data. Then, it uses a machine learning model to determine the equivalent fuel factor based on the at least one feature data.

[0022] The inventors of this invention have discovered that preferred feature data that can be received as input by a machine learning model 10 to accurately determine the equivalent fuel factor includes the following feature data over a predetermined time period, such as a driving cycle: maximum speed V MAX Average velocity V avg Standard deviation of velocity V std Zero velocity time ratio (Idle), average positive acceleration (a) + avg and the average negative acceleration a - avg Among them, the maximum speed V MAX The average speed V is determined to be the speed at which the vehicle travels fastest throughout the entire driving cycle. avg The speed is defined as the average speed of the vehicle over the entire driving cycle, with the standard deviation V being the speed. std The standard deviation of the vehicle's speed over the entire driving cycle is defined as the zero-speed time proportion (Idle), which is the proportion of the time the vehicle is stationary (e.g., due to waiting at a red light) over the entire driving cycle. The mean positive acceleration (a) is also defined as... + avg It was determined to be any speed greater than 0.1 m / s throughout the entire driving cycle. 2 The average value of the acceleration, and the average negative acceleration a - avg It was determined to be all speeds less than 0.1 m / s throughout the entire driving cycle. 2 The average value of acceleration.

[0023] In other embodiments, those skilled in the art will understand that, depending on the different requirements for determining accuracy, one or more of the above features may be reduced; or other features may be added, such as the standard deviation of acceleration or the proportion of time the velocity is within a specific range.

[0024] In one embodiment, at least one of the aforementioned feature data can be obtained by other processing units outside of system 100, and receiving unit 101 directly receives at least one of the aforementioned feature data as data related to the vehicle's motion state.

[0025] Following one embodiment, the machine learning model 10 can be continuously trained in real time during vehicle use. For example, the machine learning model 10 can be further trained based on the vehicle's historical driving data. For instance, in a historical driving session, the vehicle consumed less fuel, thus a better equivalent fuel factor can be calculated based on the fuel consumption. The machine learning model 10 can be further adaptively trained using data related to the vehicle's motion state recorded during this driving session and the calculated better equivalent fuel factor, allowing the accuracy of the machine learning model 10 to gradually improve as the vehicle is used over time.

[0026] During vehicle operation, the receiving unit 101 of system 100 can receive data related to the vehicle's motion state over a predetermined time period, for example, from sensor 20. In response to receiving data over the predetermined time period, the determining unit 102 updates the equivalent fuel factor based on the received data. In a preferred embodiment, the receiving unit receives the data for the predetermined time period at a predetermined frequency; for example, the predetermined frequency could be 1 second, and the predetermined time period could be 1 minute. Thus, the receiving unit receives data related to the vehicle's motion state from the previous minute every second for use by the determining unit. The determining unit updates the equivalent fuel factor at a corresponding predetermined frequency based on the data received from the receiving unit over the predetermined time period.

[0027] Unlike existing technologies that determine an equivalent fuel factor for a single driving condition, this invention updates the equivalent fuel factor in real time. For example, even if the vehicle is continuously used in urban driving conditions, according to this invention, the equivalent fuel factor can be updated in real time at a predetermined frequency, adapting to the vehicle's changing conditions. Compared to updating the equivalent fuel factor only when driving conditions change, this allows for finer adjustment of the equivalent fuel factor, thereby achieving improved management of vehicle energy consumption.

[0028] Those skilled in the art will understand that the predetermined frequency and / or predetermined time period can be manually set. Alternatively, the predetermined frequency and / or predetermined time period can be automatically adjusted based on data sensed by sensor 20. For example, if speed sensor data and / or acceleration sensor data indicate that the vehicle's driving conditions change little over a long period, the predetermined frequency can be adjusted to be lower. However, in situations such as complex urban driving, where vehicle speed and / or acceleration may change frequently, the predetermined frequency can be adjusted to be higher, and the predetermined time period set to be relatively short, so that the determined equivalent fuel factor adapts to frequent changes.

[0029] In one embodiment, such as Figure 1As shown, the system 100 also includes a prediction unit 103, which is used to predict the vehicle's next driving speed and / or route based on data related to vehicle driving.

[0030] In a simple example, data related to vehicle driving may include navigation data used to guide driving. For instance, prediction unit 103 may receive navigation data set by a user on an in-vehicle navigation system and predict the vehicle's next speed and / or route based on the destination location indicated by the navigation data and current traffic conditions.

[0031] Alternatively, the data related to vehicle driving may include data collected by sensor 20, or feature data derived from the data collected by sensor 20 as described above. The prediction unit 103 can predict the vehicle's next driving speed and / or route based on the aforementioned sensor data or feature data. For example, for a particular vehicle, it may exhibit similar feature data on the same frequently traveled route; therefore, the prediction unit 103 can predict, based on specific feature data, that the vehicle will subsequently travel along a frequently traveled route at its usual speed.

[0032] In this embodiment, system 100 further includes an adjustment unit 104. The adjustment unit 104 is capable of adjusting or correcting the equivalent fuel factor determined by the determination unit 102 based on the predicted driving speed and / or route.

[0033] If the determined equivalent fuel factor is significantly inconsistent with the predicted driving conditions, the adjustment unit 104 can adjust the determined equivalent fuel factor to a range consistent with the predicted driving conditions. This is because the driving speed and / or route predicted by the prediction unit 103 can actually reflect the vehicle's subsequent driving conditions. Although the model of the present invention can determine the equivalent fuel factor without knowing the driving conditions, when there is a deviation between the determined equivalent fuel factor and the predicted conditions, the predicted conditions can serve as the basis for adjusting the equivalent fuel factor, thereby maximizing the accuracy of the finally determined equivalent fuel factor.

[0034] Those skilled in the art will understand that although the vehicle energy management system is described with reference to the above-described receiving unit 101, determining unit 102, predicting unit 103, and adjusting unit 104, these units are merely illustrative and not restrictive, and they can be combined / split / partially combined to achieve the corresponding functions.

[0035] Furthermore, one or more of the aforementioned receiving unit 101, determining unit 102, predicting unit 103, and adjusting unit 104 can also be implemented as computer-readable instructions, which are stored on a computer-readable medium. Alternatively, the corresponding computer-readable instructions can be stored in a memory, and the functions of each of the aforementioned units can be implemented by a processor executing the corresponding instructions. Such a memory and processor can constitute a vehicle energy management device. This vehicle energy management device can be part of a vehicle control system.

[0036] Those skilled in the art will understand that the system 100 according to one or more embodiments can be integrated into a vehicle to form part of an in-vehicle system. Alternatively, the system 100 according to one or more embodiments can be a standalone system capable of communicating with the in-vehicle system via, for example, a data interface.

[0037] Alternatively, it can be envisioned that the functions of each unit in the aforementioned vehicle energy management system are implemented on the server side. The server receives data from the vehicles, determines the corresponding equivalent fuel factor, and then distributes it to the appropriate vehicles. A single server may monitor multiple vehicles simultaneously.

[0038] Figure 3 A flowchart of a vehicle energy management method 300 according to an embodiment of the present invention is shown.

[0039] In 310, one or more sensors are used to obtain data related to the vehicle's motion state.

[0040] In 320, data related to the vehicle's motion status is received.

[0041] In 330, an equivalent fuel factor is determined based on the data using a machine learning model, wherein the machine learning model is trained based on known data related to the vehicle's motion state and the corresponding equivalent fuel factor.

[0042] In 340, the data for a predetermined time period is received at a predetermined frequency.

[0043] In 350, the determined equivalent fuel factor is updated at the predetermined frequency based on the data over the predetermined time period.

[0044] It is understood that the method according to this application has the same or similar embodiments as the system according to this application.

[0045] Figure 3 The processing described herein can be implemented by a processor executing corresponding instructions. These instructions can be stored on any suitable computer-readable medium.

[0046] The above is for reference only. Figure 3The embodiments shown describe the method of the present invention. It is understood that the various operations included in the above embodiments are not limiting and can be deleted, combined, changed, split and / or recombined as needed to add / modify / delete the corresponding functions.

[0047] The systems and methods of the present invention have been described above with reference to various embodiments, wherein the embodiments mentioned may include specific features, structures, or characteristics, but not every embodiment necessarily includes that specific feature, structure, or characteristic. Furthermore, some embodiments may have some or all of the features described in other embodiments, or may not have the features described in other embodiments.

[0048] Various features of different embodiments or examples can be combined in various ways with some included features and others excluded features to adapt to a variety of different applications. The accompanying drawings and the foregoing description provide examples of embodiments. Those skilled in the art will understand that one or more of the described elements can be combined into a single functional element. Alternatively, certain elements can be divided into multiple functional elements. Elements from one embodiment can be added to another embodiment. For example, the order of processes described herein can be changed and is not limited to the manner described herein. Furthermore, the operations of any flowchart need not be performed in the order shown; nor is it necessary to perform all operations. Moreover, those operations that do not depend on other operations can be performed in parallel with other operations. The scope of the embodiments is by no means limited to these specific examples. Many variations, such as differences in the order of operations, product composition, and structure, are possible, whether or not explicitly stated in the specification.

Claims

1. A vehicle energy management system, comprising: A receiving unit, which is used to receive data related to the vehicle's motion state; as well as A determining unit is used to determine the equivalent fuel factor based on the data using a machine learning model under uncertain vehicle driving conditions. The machine learning model is trained based on known data related to the vehicle's motion state and the corresponding equivalent fuel factor.

2. The vehicle energy management system according to claim 1, wherein, The determining unit is further configured to derive at least one feature data based on the data; and to determine the equivalent fuel factor based on the at least one feature data.

3. The vehicle energy management system according to claim 2, in, The at least one feature data includes the following feature data within a predetermined time period: maximum speed, average speed, standard deviation of speed, zero speed time ratio, average positive acceleration, and average negative acceleration.

4. The vehicle energy management system according to any one of claims 1-3, in, The machine learning model is further adaptively trained based on the vehicle's historical driving data, which includes data related to the vehicle's motion state recorded in the vehicle's past driving and an equivalent fuel factor calculated based on the fuel consumption of the past driving.

5. The vehicle energy management system according to any one of claims 1-3, in, The receiving unit is configured to receive the data for a predetermined time period at a predetermined frequency; and the determining unit is further configured to update the determined equivalent fuel factor at the predetermined frequency based on the data for the predetermined time period.

6. The vehicle energy management system according to any one of claims 1-3, further comprising: A prediction unit for predicting the vehicle's speed and / or route; as well as An adjustment unit is used to adjust the equivalent fuel factor determined by the determining unit based on the predicted driving speed and / or route.

7. A vehicle energy management method, comprising: Receive data related to the vehicle's motion status; as well as Under uncertain vehicle driving conditions, an equivalent fuel factor is determined based on the data using a machine learning model. The machine learning model is trained based on known data related to the vehicle's motion state and the corresponding equivalent fuel factor.

8. The vehicle energy management method according to claim 7, further comprising: Derive at least one feature data based on the data; and The equivalent fuel factor is determined based on the at least one of the characteristic data.

9. The vehicle energy management method according to claim 8, wherein, The at least one feature data includes the following feature data within a predetermined time period: maximum speed, average speed, standard deviation of speed, zero speed time ratio, average positive acceleration, and average negative acceleration.

10. The vehicle energy management method according to any one of claims 7-9, further comprising: The machine learning model is further trained adaptively based on the vehicle's historical driving data, which includes data related to the vehicle's motion state recorded in the vehicle's past driving and an equivalent fuel factor calculated based on the fuel consumption of the past driving.

11. The vehicle energy management method according to any one of claims 7-9, further comprising: The data is received at a predetermined frequency for a predetermined time period; as well as The determined equivalent fuel factor is updated at the predetermined frequency based on the data within the predetermined time period.

12. The vehicle energy management method according to any one of claims 7-9, further comprising: Predict the vehicle's speed and / or route; as well as The determined equivalent fuel factor is adjusted based on the predicted driving speed and / or route.

13. A vehicle energy management device, comprising: Memory on which computer-readable instructions are stored; as well as A processor, when the computer-readable instructions are executed by the processor, causes the processor to perform the vehicle energy management method according to any one of claims 7-12.

14. A computer-readable medium having stored thereon computer-readable instructions that, when executed by a processor, cause the processor to perform the method according to any one of claims 7-12.

Images