Vehicle travel energy consumption prediction method, system and device and storage medium

Abstract

The invention discloses a vehicle travel energy consumption prediction method, system and device and a storage medium, and relates to the technical field of vehicle energy consumption control, and the method comprises the steps: obtaining travel segment data and vehicle state data corresponding to a plurality of travel segments of a vehicle in a target travel; for each travel segment, obtaining a basic energy consumption value of the vehicle based on the travel segment data and preset vehicle kinetic parameters; for each travel segment, obtaining a load power demand value of the vehicle based on the travel segment data and the vehicle state data; for each travel segment, correcting the basic energy consumption value based on the load power demand value and the vehicle state data to obtain an energy consumption correction value of the vehicle; and accumulating the energy consumption correction values of the vehicle in all the travel segments to obtain the total energy consumption value of the vehicle.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automobile energy consumption control, and in particular to a vehicle trip energy consumption prediction method, system, device and storage medium. BACKGROUND

[0002] When analyzing the energy consumption of a vehicle's future trip based on map navigation information, accurately calculating the total energy consumption is crucial for achieving optimal energy distribution. Related technologies mainly rely on vehicle dynamics traction physical models and combine real-time loads (such as air conditioning, accessory power) to calculate the steady-state energy consumption of each navigation segment. However, this method has significant drawbacks: the calculated results only represent the ideal steady-state energy consumption of the segment under constant conditions, and do not truly reflect the instantaneous energy consumption fluctuations and their cumulative effects caused by factors such as speed fluctuations, acceleration / deceleration characteristics, environmental temperature changes, and differences in traffic light waiting strategies during actual vehicle operation. This results in a large deviation in the calculated total energy consumption, directly affecting the accuracy of subsequent energy distribution strategies and vehicle energy efficiency performance. SUMMARY

[0003] Embodiments of the present application provide a vehicle trip energy consumption prediction method, system, device and storage medium, which can at least to some extent improve the prediction accuracy of the total energy consumption of a vehicle's future trip based on the real-time state of the vehicle during actual vehicle operation.

[0004] A series of simplified concepts are introduced in the summary section, which will be further described in detail in the specific embodiments section. The summary section of the present application does not mean to attempt to limit the key features and necessary technical features of the claimed technical solutions, nor does it attempt to determine the protection scope of the claimed technical solutions.

[0005] The present application specifically includes the following aspects: In a first aspect, the present application provides a vehicle trip energy consumption prediction method, which comprises: obtaining vehicle state data and trip segment data corresponding to a plurality of trip segments of a vehicle within a target trip; for each trip segment, obtaining a basic energy consumption value of the vehicle based on the trip segment data and preset vehicle dynamics parameters; for each trip segment, obtaining a load power demand value of the vehicle based on the trip segment data and the vehicle state data; for each trip segment, correcting the basic energy consumption value based on the load power demand value and the vehicle state data to obtain an energy consumption correction value of the vehicle; accumulating the energy consumption correction values of the vehicle in all trip segments to obtain a total energy consumption value of the vehicle.

[0006] In an implementation, the trip segment data comprises segment mileage, vehicle estimated passing time and number of traffic lights; and the vehicle state data comprises battery data, current load power and driving data of the vehicle.

[0007] In an implementation, the obtaining the basic energy consumption value of the vehicle based on the trip segment data and preset vehicle dynamics parameters comprises: determining average vehicle speed of the vehicle based on the segment mileage and the vehicle estimated passing time; determining driving time of the vehicle based on the vehicle estimated passing time, the number of traffic lights and preset traffic light waiting time compensation coefficient; determining basic power of the vehicle based on the average vehicle speed and the preset vehicle dynamics parameters; obtaining the basic energy consumption value of the vehicle based on the basic power and the driving time.

[0008] In an implementation, the obtaining the load power demand value of the vehicle based on the trip segment data and the vehicle state data comprises: predicting the load power demand value of the vehicle based on current ambient temperature, the current load power and the average vehicle speed by a first sub-model of a target machine learning model.

[0009] In an implementation, the trip segment data further comprises number of stops of the vehicle, and after the obtaining the basic energy consumption value of the vehicle based on the trip segment data and preset vehicle dynamics parameters, the method further comprises: determining traffic light waiting time of the vehicle based on the number of stops and preset traffic light waiting time compensation coefficient.

[0010] In an implementation, the correcting the basic energy consumption value based on the load power demand value and the vehicle state data to obtain energy consumption correction value of the vehicle comprises: predicting the energy consumption correction value of the vehicle based on the basic energy consumption value, the load power demand value, the battery data, the driving data and the traffic light waiting time by a second sub-model of the target machine learning model.

[0011] In an implementation, the target machine learning model is trained by a leaf growing algorithm, and in the training process: the maximum depth of a tree is controlled to be no more than a first preset level; the maximum number of leaf nodes of each tree is limited to be no more than a second preset number; A minimum data volume limit of leaf nodes is set, and gradient-based one-sided sampling is used in training.

[0012] In a second aspect, the present application provides a vehicle trip energy consumption prediction system for performing the vehicle trip energy consumption prediction method of any one of the above embodiments, the system comprising: a data collection unit configured to obtain trip segment data and vehicle state data corresponding to a plurality of trip segments of a target trip of a vehicle; a basic energy consumption calculation unit configured to obtain, for each trip segment, a basic energy consumption value of the vehicle based on the trip segment data and preset vehicle dynamics parameters; a first machine learning unit configured to obtain, for each trip segment, a load power demand value of the vehicle based on the trip segment data and the vehicle state data; a second machine learning unit configured to correct the basic energy consumption value based on the load power demand value and the vehicle state data to obtain an energy consumption correction value of the vehicle for each trip segment; a total energy consumption prediction unit configured to accumulate the energy consumption correction values of the vehicle in all trip segments to obtain a total energy consumption value of the vehicle.

[0013] In a third aspect, a vehicle comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is configured to implement the steps of the vehicle trip energy consumption prediction method of any one of the first aspect when executing the computer program stored in the memory.

[0014] In a fourth aspect, the present application further provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executable by a processor to implement the steps of the vehicle trip energy consumption prediction method of any one of the first aspect.

[0015] The vehicle trip energy consumption prediction method provided in the application first splits the target trip into multiple segments and collects corresponding data respectively, breaking the limitation of traditional whole-trip unified prediction that cannot adapt to different road segment characteristics, and can accurately capture the differences in mileage, time, traffic light state and real-time vehicle state of each segment, laying a precise data foundation for subsequent segment-by-segment energy consumption calculation, effectively avoiding prediction deviation caused by single data dimension and homogeneous trip characteristics; secondly, the calculation of the basic energy consumption value relies on vehicle dynamics parameters, ensuring the physical rationality and reliability of the energy consumption benchmark under ideal working conditions, providing a stable reference for subsequent correction, while avoiding the calculation redundancy caused by direct dependence on complex models, and taking into account the calculation efficiency; thirdly, the basic energy consumption value is corrected by introducing the load power demand value, fully considering the influence of dynamic factors such as environmental temperature, current load and vehicle speed on energy consumption in actual vehicle driving, making up for the defects of traditional methods that only calculate steady-state energy consumption while ignoring instantaneous energy consumption fluctuations, and greatly improving the accuracy of single-segment energy consumption correction value; finally, the total energy consumption value is obtained by accumulating all segment energy consumption correction values, avoiding the problem of error accumulation in whole-trip prediction, and the errors of each segment are independent of each other, making the final total energy consumption prediction result closer to the actual vehicle driving energy consumption, and significantly reducing the prediction deviation. Overall, this method builds a complete prediction framework of segmented processing, basic calculation, dynamic correction and cumulative summation, which not only guarantees the prediction accuracy to meet the demand of vehicle energy distribution strategy for accurate energy consumption data and improves the vehicle energy efficiency performance, but also optimizes the calculation process through reasonable process design, adapts to the scene of limited vehicle-mounted computing resources, and has strong practical application value and technical innovation.

[0016] The vehicle trip energy consumption prediction method, system, device and storage medium provided in the application, other advantages, objects and features of the application will be embodied in part through the following description, and will be understood by those skilled in the art through research and practice of the application. BRIEF DESCRIPTION OF DRAWINGS

[0017] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The accompanying drawings are intended to only illustrate preferred embodiments and are not considered limiting of the present description. Moreover, like reference numerals designate similar parts throughout the several views in the drawings. In the drawings: Figure 1 A flowchart of a vehicle trip energy consumption prediction method provided by an embodiment of the application is shown in the figure; Figure 2 A structure diagram of a target machine learning model provided by an embodiment of the application is shown in the figure; Figure 3 A functional module diagram of a vehicle trip energy consumption prediction system provided by an embodiment of the application is shown in the figure; Figure 4 A structural schematic diagram of a vehicle trip energy consumption prediction control device provided by an embodiment of the present application is provided. DETAILED DESCRIPTION

[0018] In order to better understand the technical solutions provided by the embodiments of the present application, the technical solutions of the embodiments of the present application will be described in detail below with the aid of the accompanying drawings and specific embodiments. It should be understood that the specific features in the embodiments of the present application and the embodiments are detailed descriptions of the technical solutions of the embodiments of the present application, and are not limitations of the technical solutions of the present application. In the case of no conflict, the technical features in the embodiments of the present application and the embodiments can be combined with each other.

[0019] In this document, relational terms such as first and second and the like can be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element preceded by "comprises... a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or apparatus that comprises the recited element. The term "two or more" includes two or more than two.

[0020] Please refer to Figure 1 A flowchart of a vehicle trip energy consumption prediction method provided by an embodiment of the present application is provided, which can specifically include: S110, obtaining trip segment data and vehicle state data corresponding to a plurality of trip segments of a vehicle in a target trip.

[0021] For example, first, the target trip is split into a plurality of trip segments according to road segment characteristics; then, for each segment, two types of key data are synchronously collected: trip segment data reflecting the objective characteristics of the road segment, and vehicle state data reflecting the real-time running state of the vehicle. Data collection is completed through the cooperation of multiple modules such as the in-vehicle information entertainment system (IVI, In-Vehicle Infotainment) and the vehicle electronic control unit (VECU, Vehicle Electronic Control Unit), ensuring the real-time and integrity of the data. Through segmented collection, the differentiated characteristics of different road segments can be accurately captured, laying a data foundation for subsequent segment-by-segment energy consumption calculation; multi-dimensional data fusion avoids the limitations of a single data source, improving the data source reliability of the prediction.

[0022] In some examples, the trip segment data includes segment mileage, vehicle estimated passing time, and number of traffic lights; the vehicle state data includes battery data, current load power, and driving data of the vehicle.

[0023] For example, the trip segment data focuses on the objective characteristics of road segments, reflecting the external environmental conditions of vehicle driving; the vehicle state data focuses on the running state of the vehicle itself, reflecting the internal energy consumption basis of the vehicle. The two types of data complement each other and constitute a complete data support system for energy consumption prediction. For example, the trip segment data: 50 kilometers are divided into 5 segments, each segment has segment mileage (such as 10 kilometers / segment), vehicle estimated passing time (such as 15 minutes for the first segment and 20 minutes for the second segment), and number of traffic lights (such as 2 for the first segment and 3 for the second segment); the vehicle state data: battery data (battery remaining capacity 90%, battery temperature 25°C, cycle number 500 times), current load power (25kW, including cargo load 20kW, air conditioner 2kW, and other equipment 3kW), and driving data (current speed 40km / h, number of sudden accelerations 1, and number of brakes 3).

[0024] S120, for each trip segment, based on the trip segment data and the preset vehicle dynamics parameters, obtaining a basic energy consumption value of the vehicle.

[0025] For example, the vehicle dynamics parameters are preset vehicle inherent properties (such as vehicle curb weight, rolling resistance coefficient A, speed-dependent resistance coefficient B, air resistance coefficient C, etc.), which are provided by the vehicle manufacturer and calibrated by the system, reflecting the basic energy consumption characteristics of the vehicle. By combining the trip segment data (such as segment mileage and estimated time) with the dynamics parameters, dynamic interference factors (such as temporary load, traffic light waiting, etc.) can be excluded, and the basic energy consumption value of the vehicle under the ideal working conditions of uniform speed driving, no additional load, and no waiting time is obtained as the basis for subsequent correction. In some examples, based on the trip segment data and the preset vehicle dynamics parameters, the basic energy consumption value of the vehicle is obtained, including: determining the average speed of the vehicle based on the segment mileage and the vehicle estimated passing time; determining the driving time of the vehicle based on the vehicle estimated passing time, the number of traffic lights, and a preset traffic light waiting time compensation coefficient; determining the basic power of the vehicle based on the average speed and the preset vehicle dynamics parameters; obtaining the basic energy consumption value of the vehicle based on the basic power and the driving time.

[0026] For each trip segment, the average vehicle speed is calculated: v = segment mileage ÷ vehicle estimated passing time; the vehicle travel time is calculated: t net = vehicle estimated passing time - number of traffic lights × preset traffic light waiting time compensation coefficient; the vehicle's base power is calculated: total travel resistance F = A + B × v + C × v 2, and the vehicle's base power P = (F × v) ÷ 1000; and the vehicle's base energy consumption value in the current trip segment is calculated: P base = P × (t net ÷ 3600).

[0027] In S130, for each trip segment, a load power demand value of the vehicle is obtained based on the trip segment data and the vehicle state data.

[0028] For example, in actual driving, the vehicle needs to overcome not only its own resistance (which has been taken into account in the base energy consumption) but also dynamic loads (such as the influence of ambient temperature on battery efficiency, the additional consumption of electrical equipment such as vehicle-mounted air conditioners, and the increase in load when climbing a slope). By fusing the trip segment data (such as the road segment slope, which is implied in the trip characteristics) and the vehicle state data (such as the current load power), the additional load power required by the vehicle in the current segment can be accurately calculated, providing a key basis for subsequent correction of the base energy consumption value.

[0029] In some examples, obtaining the load power demand value of the vehicle based on the trip segment data and the vehicle state data includes: Through a first sub-model of the target machine learning model, the load power demand value of the vehicle is predicted based on the current ambient temperature, the current load power, and the average vehicle speed.

[0030] For example, as shown in Figure 2 An efficient target machine learning model (preferably LightGBM) is used for predictive compensation calculation. The first sub-model does not directly calculate the total energy consumption value, but applies the LightGBM model in stages. The first sub-model is trained through a large amount of historical data (such as measured load power data), which can learn the nonlinear relationship between various factors and load power, thereby achieving more accurate prediction. In the first sub-model, the current ambient temperature T, the current load power L 0 (including air conditioners, accessories, etc.), the average vehicle speed V, and the measured load power data are combined to map and predict the future load power demand value P load through the LightGBM model.

[0031] In S140, for each trip segment, the base energy consumption value is corrected based on the load power demand value and the vehicle state data to obtain an energy consumption correction value of the vehicle.

[0032] For example, the base energy consumption value reflects an ideal working condition, while the actual energy consumption is affected by factors such as load, vehicle state, etc., and needs to be corrected to eliminate deviations. In the correction process, the additional energy consumption is quantified by the load power demand value, and the influence of the vehicle's own state on the energy consumption (such as a 5% decrease in discharge efficiency when the remaining battery capacity is less than 30%, which requires a corresponding increase in energy consumption correction) is reflected by vehicle state data (such as battery data, driving data), and finally the actual energy consumption correction value of each segment is obtained.

[0033] In some examples, the trip segment data further includes the number of stops of the vehicle, and after obtaining the base energy consumption value of the vehicle based on the trip segment data and the preset vehicle dynamics parameters, the method further includes: Based on the number of stops and a preset red light waiting time compensation coefficient, a red light waiting time of the vehicle is determined.

[0034] For example, in actual driving, the number of stops includes not only red light waiting, but also intersection yielding, temporary parking, etc., and these static time consumptions will all cause the vehicle to be in an idle state (still consuming base energy consumption), which needs to be quantified and included separately. By combining the number of stops with the red light waiting time compensation coefficient, the total static waiting time of the vehicle in the segment can be more accurately calculated, providing more comprehensive time dimension data support for subsequent energy consumption correction. Specifically, the red light waiting time = the number of stops x the red light waiting time compensation coefficient.

[0035] In some examples, the base energy consumption value is corrected based on the load power demand value and the vehicle state data to obtain an energy consumption correction value of the vehicle, including: The second sub-model of the target machine learning model is used to predict the energy consumption correction value of the vehicle based on the base energy consumption value, the load power demand value, the battery data, the driving data, and the red light waiting time.

[0036] For example, in the second sub-model, the base energy consumption value P_base, the load power demand value P_load, the battery data SOC, the driving data (including but not limited to acceleration average a_ave, acceleration standard deviation a_std, and other parameters reflecting acceleration characteristics), and the red light waiting time are used to calculate the final predicted energy consumption correction value E_pred of the vehicle through a LightGBM model. This energy consumption correction value comprehensively compensates for dynamic fluctuations and nonlinear effects that cannot be captured by the physical model layer.

[0037] S150, accumulate the energy consumption correction values of the vehicle in all trip segments to obtain a total energy consumption value of the vehicle.

[0038] Exemplarily, since the energy consumption correction value of each trip segment accurately reflects the actual energy consumption of the segment, the total energy consumption of the entire target trip, i.e., the total energy consumption value P_pred of the vehicle, can be obtained by accumulating the correction values of all segments. This aggregation method avoids the problem of error accumulation in whole-segment prediction, and the errors of each segment are independent of each other, resulting in a smaller final total error.

[0039] In some examples, the target machine learning model is trained using a leaf growth algorithm, and during the training process: the maximum depth of the control tree is not more than a first preset level; the maximum number of leaf nodes of each tree is limited to not more than a second preset number; a minimum data amount limit for leaf nodes is set, and a gradient-based one-sided sampling is used in the training.

[0040] Exemplarily, in the model tuning and verification process, the model training stage first needs to collect a historical driving data set covering multiple seasons and multiple road conditions, and based on this, the data set is divided into a training set and a verification set in a ratio of 70% and 30%, providing data support for subsequent model training and performance verification. In the resource-limited parameter debugging link, considering that the target machine learning model needs to be trained using a leaf growth algorithm and needs to meet specific training constraints, first, the basic constraints are set, the maximum depth of the tree is strictly controlled to not more than 7 levels (i.e., the first preset level), the maximum number of leaf nodes of each tree is limited to not more than 63 (i.e., the second preset number), and the model feature sampling ratio is controlled between 0.6 and 0.8, which ensures that the model structure is reasonable and avoids excessive complexity. Subsequently, light-weight model debugging is carried out, using a hierarchical and step-by-step deepening strategy, with an initial depth of 3, and increasing by 1 layer each iteration until the maximum depth of the tree is not more than 7 levels, while applying a histogram bin limit (max_bin=128) to reduce memory usage, setting a sample data subsampling rate (bagging_fraction=0.6) to improve training speed, optimizing resource adaptability in a vehicle-mounted environment while ensuring model performance. In the Leaf-wise strategy optimization aspect, the Leaf-wise tree growth algorithm is enabled instead of the traditional Level-wise algorithm, which is the core growth method used in the training of the target machine learning model, and a minimum data amount limit for leaf nodes (min_data_in_leaf=20) is set to prevent overfitting of the model, and a gradient-based one-sided sampling (GOSS) is used to reduce the participation of small gradient samples, further improving training efficiency and model generalization ability.

[0041] During the debugging and monitoring phase, the error curves between the training and validation sets are recorded for each iteration to track the model's learning performance in real time. Simultaneously, resource consumption metrics such as CPU utilization, memory usage, and prediction time per cycle are closely monitored. When the validation error converges and all resource metrics meet the targets, the current model parameters are locked to ensure a balance between performance and resource consumption. Model tuning terminates only if three conditions are met: the mean absolute error of the validation set decreases by less than 0.5% over five consecutive iterations; the prediction time per cycle remains stable below 100ms; and the model's memory usage meets the vehicle's hardware limitations. Only when all these conditions are met can the tuning work during the model training phase be completed.

[0042] During the model deployment and verification phase, the model needs to be verified in real-world scenarios through real-vehicle road tests. The road tests need to cover typical operating conditions such as urban congestion and highway cruising to comprehensively test the model's prediction performance under different real-world driving scenarios. When the model's prediction error stabilizes within a predetermined threshold, the model is deemed to have the conditions for practical application and can be officially put into use.

[0043] Furthermore, this application also proposes a vehicle trip energy consumption prediction system, an embodiment for executing any of the above-mentioned vehicle trip energy consumption prediction methods, specifically as follows: Figure 3 The diagram shown is a functional module schematic of a vehicle trip energy consumption prediction system proposed in this application. The system includes: Data acquisition unit 21 is used to acquire trip segment data and vehicle status data corresponding to multiple trip segments within the target trip; The basic energy consumption calculation unit 22 is used to obtain the basic energy consumption value of the vehicle for each trip segment based on the trip segment data and preset vehicle dynamic parameters; The first machine learning unit 23 is used to obtain the load power requirement value of the vehicle for each trip segment based on the trip segment data and vehicle status data; The second machine learning unit 24 is used to correct the basic energy consumption value based on the load power demand value and vehicle status data for each trip segment, so as to obtain the vehicle's energy consumption correction value. The total energy consumption prediction unit 25 is used to accumulate the energy consumption correction values ​​of the vehicle within all travel segments to obtain the total energy consumption value of the vehicle.

[0044] It should be noted that the above embodiments are merely best examples and are not intended to limit the implementation of this application.

[0045] Furthermore, such as Figure 4As shown, the embodiment of the present application further provides an electronic device 300, comprising a processor 310, a memory 320, and a computer program 321 stored in the memory 320 and capable of running on the processor, wherein the processor 310 implements the steps of any of the vehicle trip energy consumption prediction methods described above when executing the computer program 321.

[0046] Since the electronic device described in the embodiment is the device used to implement the vehicle trip energy consumption prediction method in the embodiment of the present application, and can be a vehicle specifically, based on the method described in the embodiment of the present application, those skilled in the art can understand the specific implementation of the electronic device in the embodiment and its various forms of change, so here the electronic device how to implement the method in the embodiment of the present application will not be described in detail, as long as the device used to implement the method in the embodiment of the present application by those skilled in the art belongs to the scope of the present application.

[0047] In the specific implementation process, the computer program 321 can implement the steps of any of the embodiments of the corresponding embodiments when executed by the processor. Figure 1 The steps of any of the embodiments of the corresponding embodiments.

[0048] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0049] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer readable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer readable program code.

[0050] The present application is described with reference to flowcharts and / or block diagrams according to the method, device (system), and computer program product of the embodiment of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one flow or multiple flows and / or blocks Figure 1 The device that implements the functions specified in one block or multiple blocks.

[0051] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the flow Figure 1 The flow or flows and / or blocks Figure 1 The flow or flows and / or blocks

[0052] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions that are executed on the computer or other programmable apparatus provide steps for implementing the flow Figure 1 The flow or flows and / or blocks ​ The flow or flows and / or blocks

[0053] The embodiments of the present application also provide a computer program product, which comprises computer software instructions, when the computer software instructions are run on a processing device, the processing device executes the flow of the vehicle trip energy consumption prediction method.

[0054] The computer program product comprises one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of the present application is produced. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer readable storage medium, or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (for example, coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (for example, infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that the computer can store or the data storage device such as server, data center, etc. integrated with one or more available media sets. The available media can be magnetic media (for example, floppy disk, hard disk, magnetic tape), optical media (for example, DVD), or semiconductor media (for example, solid state disk (SSD)) and the like.

[0055] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0056] In several embodiments provided in the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other manners. For example, the embodiments of the apparatus described above are merely schematic. For example, the division of the units is only a logical function division. There can be another division manner for the actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between the units can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical, mechanical or in other forms.

[0057] The units described as separated components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments.

[0058] In addition, each functional unit in the embodiments of the present application can be integrated in a processing unit, or each unit can exist physically as a separate unit, or two or more units can be integrated in one unit. The integrated unit can be implemented in the form of hardware, or in the form of software functional units.

[0059] If the integrated unit is implemented in the form of software functional units and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such an understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions that cause a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in the embodiments of the present application. The foregoing storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, and various media that can store program codes.

[0060] The above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for some technical features; and these modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

[0061] While the preferred embodiments of the application have been described, additional variations and modifications can be made to the preferred embodiments by those skilled in the art once they learn of the basic inventive concepts. Therefore, the appended claims are intended to encompass within their scope all such alternatives, modifications and variations as fall within the scope of the present application. One skilled in the art will readily recognize from the prior art teachings that numerous changes and modifications can be made to the preferred embodiments of the present application without departing from the spirit and scope of the application. It is therefore intended that such changes and modifications be included within the scope of the application as measured by the claims.

[0062] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A method for predicting vehicle travel energy consumption, characterized in that, The method includes: Acquire trip segment data and vehicle status data corresponding to multiple trip segments within the target trip; For each trip segment, the basic energy consumption value of the vehicle is obtained based on the trip segment data and preset vehicle dynamics parameters; For each trip segment, the load power requirement of the vehicle is obtained based on the trip segment data and the vehicle status data; For each trip segment, the base energy consumption value is corrected based on the load power demand value and the vehicle status data to obtain the vehicle's corrected energy consumption value; The total energy consumption of the vehicle is obtained by accumulating the energy consumption correction values ​​of the vehicle across all trip segments.

2. The vehicle trip energy consumption prediction method according to claim 1, characterized in that, The trip segment data includes segment mileage, estimated vehicle transit time, and number of traffic lights; the vehicle status data includes the vehicle's battery data, current load power, and driving data.

3. The vehicle trip energy consumption prediction method according to claim 2, characterized in that, The process of obtaining the vehicle's basic energy consumption value based on the trip segment data and preset vehicle dynamics parameters includes: The average speed of the vehicle is determined based on the segment mileage and the estimated transit time of the vehicle. The vehicle's travel time is determined based on the estimated vehicle transit time, the number of traffic lights, and the preset traffic light waiting time compensation coefficient. The base power of the vehicle is determined based on the average vehicle speed and the preset vehicle dynamics parameters. Based on the base power and the driving time, the basic energy consumption value of the vehicle is obtained.

4. The vehicle trip energy consumption prediction method according to claim 3, characterized in that, The process of obtaining the vehicle's load power requirement based on the trip segment data and the vehicle status data includes: Using the first sub-model of the target machine learning model, the load power requirement of the vehicle is predicted based on the current ambient temperature, the current load power, and the average vehicle speed.

5. The vehicle trip energy consumption prediction method according to claim 4, characterized in that, The trip segment data also includes the number of times the vehicle stops. After obtaining the vehicle's basic energy consumption value based on the trip segment data and preset vehicle dynamic parameters, the data further includes: The traffic light waiting time of the vehicle is determined based on the number of stops and the preset traffic light waiting time compensation coefficient.

6. The vehicle trip energy consumption prediction method according to claim 5, characterized in that, The step of correcting the base energy consumption value based on the load power demand value and the vehicle status data to obtain the corrected energy consumption value for the vehicle includes: The second sub-model of the target machine learning model predicts the energy consumption correction value of the vehicle based on the base energy consumption value, the load power demand value, the battery data, the driving data, and the traffic light waiting time.

7. The vehicle trip energy consumption prediction method according to claim 4, characterized in that, The target machine learning model is trained using a leaf growth algorithm. During the training process: The maximum depth of the tree is controlled to not exceed the first preset level; The maximum number of leaf nodes in each tree is limited to a second preset number; Set a minimum data limit for leaf nodes and use gradient-based one-sided sampling during training.

8. A vehicle trip energy consumption prediction system, used to execute the vehicle trip energy consumption prediction method according to any one of claims 1 to 7, characterized in that, The system includes: The data acquisition unit is used to acquire trip segment data and vehicle status data corresponding to multiple trip segments within the target trip. The basic energy consumption calculation unit is used to obtain the basic energy consumption value of the vehicle for each trip segment based on the trip segment data and preset vehicle dynamic parameters; The first machine learning unit is used to obtain the load power requirement value of the vehicle for each trip segment based on the trip segment data and the vehicle status data; The second machine learning unit is used to correct the basic energy consumption value based on the load power demand value and the vehicle status data for each trip segment, so as to obtain the energy consumption correction value of the vehicle. The total energy consumption prediction unit is used to accumulate the energy consumption correction values ​​of the vehicle in all travel segments to obtain the total energy consumption value of the vehicle.

9. A vehicle comprising: The memory and processor are characterized in that the processor is used to implement the steps of the vehicle trip energy consumption prediction method as described in any one of claims 1 to 7 when executing a computer program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the vehicle trip energy consumption prediction method as described in any one of claims 1 to 7.

Images