Method, device, equipment and medium for determining driving conditions of new energy vehicles

Abstract

The embodiment of the present invention discloses a method, device, equipment and medium for determining the driving condition of a new energy vehicle. The method includes: obtaining a kinematic segment of the vehicle; determining the type of driving road based on the kinematic segment; determining the proportion of the vehicle's total mileage in each type of driving road; and determining the driving condition of the vehicle on each type of driving road based on the total mileage proportion and the clustering results of the kinematic segments associated with each type of driving road. By executing the technical solution provided by the embodiment of the present invention, it is possible to scientifically and objectively characterize the driving conditions of new energy vehicles on different types of roads, providing a reliable data source for subsequent bench tests.

Description

Technical Field

[0001] Embodiments of the present invention relate to the technical field of new energy vehicles, and in particular to a method, device, equipment and medium for determining a driving condition of a new energy vehicle. Background Art

[0002] The driving cycle, also known as the vehicle test cycle, is a speed-time curve that describes the driving of a vehicle. As the basis of the vehicle energy consumption / emission test method and limit standard, the driving cycle reflects the kinematic characteristics of the vehicle on the road. It is an important and common basic technology in the automotive industry and the main benchmark for the calibration and optimization of various performance indicators of the vehicle.

[0003] The design of vehicle, new energy system and assembly performance requirements in related technologies is mainly based on international standard working conditions or actual collected working conditions of a few experimental vehicles as design input reference, lacking actual user usage conditions as input. In the assembly design process, the input of energy consumption, cruising range and reliability design indicators is too single, and it is impossible to restore the actual user usage, resulting in a large gap between the actual user's energy consumption and cruising range and the cruising range announced in the product design, and many user complaints. Summary of the invention

[0004] The embodiments of the present invention provide a method, device, equipment and medium for determining the driving conditions of new energy vehicles, which can scientifically and objectively characterize the driving conditions of new energy vehicles on different types of roads and provide a reliable data source for subsequent bench tests.

[0005] In a first aspect, an embodiment of the present invention provides a method for determining a driving condition of a new energy vehicle, the method comprising:

[0006] Obtaining a kinematic segment of a vehicle; the vehicle model is one of a pure electric four-wheel drive model, a pure electric two-wheel drive model, and a hybrid model;

[0007] Determine the type of driving road according to the kinematic segment; the driving road type includes urban roads, mountain roads, expressways and suburban roads;

[0008] Determining the proportion of the total mileage of the vehicle on each of the driving road types;

[0009] The driving condition of the vehicle on each of the driving road types is determined according to the total running mileage ratio and the clustering results of the kinematic segments associated with each of the driving road types.

[0010] In a second aspect, an embodiment of the present invention further provides a driving condition determination device for a new energy vehicle, the device comprising: a kinematic segment determination module, for obtaining a kinematic segment of a vehicle; the vehicle model belongs to one of a pure electric four-wheel drive model, a pure electric two-wheel drive model and a hybrid model;

[0011] A driving road type determination module, used to determine the driving road type according to the kinematic segment; the driving road type includes urban roads, mountain roads, expressways and suburban roads;

[0012] A total mileage ratio determination module, used to determine the total mileage ratio of the vehicle on each of the driving road types;

[0013] The driving condition determination module is used to determine the driving condition of the vehicle on each of the driving road types according to the total mileage ratio and the clustering results of the kinematic segments associated with each of the driving road types.

[0014] In a third aspect, an embodiment of the present invention further provides an electronic device, the device comprising:

[0015] one or more processors;

[0016] a storage device for storing one or more programs,

[0017] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining the driving condition of a new energy vehicle as described in any one of the embodiments of the present invention.

[0018] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for determining a driving condition of a new energy vehicle as described in any one of the embodiments of the present invention.

[0019] The technical solution provided by the embodiment of the present invention obtains the kinematic fragment of the vehicle; the vehicle model belongs to one of the pure electric four-wheel drive model, the pure electric two-wheel drive model and the hybrid model; the driving road type is determined according to the kinematic fragment; the driving road type includes urban roads, mountain roads, highways and suburban roads; the total mileage ratio of the vehicle in each driving road type is determined; according to the total mileage ratio and the clustering results of the kinematic fragments associated with each driving road type, the driving condition of the vehicle on each driving road type is determined. By executing the technical solution provided by the embodiment of the present invention, it is possible to scientifically and objectively characterize the driving conditions of new energy vehicles on different types of roads, providing a reliable data source for subsequent bench tests. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a flow chart of a method for determining a driving condition of a new energy vehicle provided by an embodiment of the present invention;

[0021] Figure 2 is a schematic diagram of a kinematic segment provided by an embodiment of the present invention;

[0022] Figure 3 is a flow chart of another method for determining a driving condition of a new energy vehicle provided by an embodiment of the present invention;

[0023] Figure 4 is a flow chart of another method for determining a driving condition of a new energy vehicle provided by an embodiment of the present invention;

[0024] Figure 5 It is a schematic diagram of the structure of a driving condition determination device for a new energy vehicle provided by an embodiment of the present invention;

[0025] Figure 6 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0027] Figure 1 This is a flow chart of a method for determining the driving condition of a new energy vehicle provided by an embodiment of the present invention. The method can be executed by a driving condition determination device for a new energy vehicle. The device can be implemented by software and / or hardware. The device can be configured in an electronic device for determining the driving condition of a new energy vehicle. The method is applied to the scenario of determining the driving condition of a new energy vehicle on different road types. Figure 1 As shown, the technical solution provided by the embodiment of the present invention specifically includes:

[0028] S110: Obtain the kinematic fragment of the vehicle.

[0029] Among them, the vehicle model is one of a pure electric four-wheel drive model, a pure electric two-wheel drive model and a hybrid model.

[0030] For example, new energy vehicles can be divided into pure electric four-wheel drive models, pure electric two-wheel drive models or hybrid models according to their working modes. This solution can obtain all kinematic segments of all vehicles of a certain model.

[0031] Specifically, the vehicle's driving data can be regarded as consisting of multiple continuous kinematic segments. This solution can clean the vehicle's driving data and eliminate invalid data, over-limit data, control data and abnormal data. The data between two adjacent idle points is then used as a kinematic segment. A complete kinematic segment includes an idle segment and a motion segment, and a complete kinematic segment should include an idle state segment, an acceleration state segment, a uniform speed state segment, and a deceleration state segment. The high-voltage power-on signal must remain valid during the duration of the kinematic segment. Among them, the idle state can be a segment where the speed is zero but the high-voltage power-on signal remains valid. The acceleration state can be a segment where the speed is not equal to zero and the acceleration is greater than or equal to 0.15m / s 2 The deceleration state can be that the speed is not equal to zero and the acceleration is less than or equal to -0.15m / s 2 The uniform speed state can be when the speed is not equal to zero and the absolute value of the acceleration is less than or equal to 0.15m / s 2 Fragment of .

[0032] Figure 2 Schematic diagram of kinematic segments provided by an embodiment of the present invention. Figure 2 As shown in the figure, during the vehicle driving process, when the high-voltage power-on signal HVPowerO is 1, it indicates that the vehicle enters the driving condition. At this time, the interval with zero vehicle speed, that is, the time segment from t1 to t2, is the idle state segment, and the remaining segments 1 to 3 are driving segments, which will be subdivided into acceleration state segments, deceleration state segments, and uniform speed state segments according to the acceleration situation. In the time period from 0 to t1 and t5 to t6, since the high-voltage signal HVPowerOn is 0, the segment is eliminated as an invalid segment.

[0033] S120: Determine the driving road type according to the kinematic segment.

[0034] The types of driving roads include urban roads, mountain roads, expressways and suburban roads.

[0035] Specifically, the present solution can determine at least one motion characteristic parameter according to the kinematic segment. For example, the present solution can determine the vehicle speed, running time, temperature, torque, throttle state, brake state, acceleration ratio, deceleration ratio, uniform acceleration ratio, uniform deceleration ratio, uniform speed ratio, idle speed ratio, maximum speed, average speed, average acceleration, relative positive acceleration, speed standard deviation, acceleration standard deviation and other motion characteristic parameters in the time period corresponding to the kinematic segment according to the kinematic segment. Then, all the motion characteristic parameters are input into the pre-trained road type recognition model to obtain the driving road type to which the kinematic segment belongs.

[0036] The road type recognition model may be trained by inputting kinematic segments of user vehicles with high mileage activity in a historical period and the types of driving roads to which the kinematic segments belong as training samples into a decision tree algorithm.

[0037] S130: Determine the proportion of the total mileage of the vehicle on each of the driving road types.

[0038] Among them, after determining the type of driving road to which each kinematic segment of all vehicles of a certain model belongs, this solution can determine the total mileage of all vehicles in each type of driving road. For example, assuming that the driving road type is an urban road, then this solution can determine the kinematic segment of each vehicle of this model on the urban road, and then the sum of the mileage in each kinematic segment can be determined as the total mileage of each vehicle on the urban road, thereby determining the total mileage of all vehicles of this model on the urban road. Then, the ratio between the total mileage of vehicles of this model on urban roads, the total mileage of mountain roads, the total mileage of highways, and the total mileage of suburban roads is determined as the ratio of the total mileage of vehicles in each type of driving road, such as 1:2:3:4.

[0039] S140: Determine the driving condition of the vehicle on each of the driving road types based on the total mileage ratio and the clustering results of the kinematic segments associated with each of the driving road types.

[0040] For example, assuming that the total mileage ratio of vehicles on urban roads, mountain roads, highways and suburban roads is 1:2:3:4, then the time length ratio corresponding to the urban road driving conditions, mountain road driving conditions, highway driving conditions and suburban road driving conditions is also 1:2:3:4. If the total time length of all conditions is 1000s, the time lengths corresponding to the urban road driving conditions, mountain road driving conditions, highway driving conditions and suburban road driving conditions are 100s, 200s, 300s and 400s respectively. In the above steps, the kinematic segments of all vehicles of a certain model on each driving road type have been determined. This solution can cluster all kinematic segments on the driving road type using a clustering algorithm. The clustering time length is the time length corresponding to the driving conditions on the driving road type, and the corresponding relationship between the vehicle driving time and the driving speed within the corresponding time length is obtained. That is, the driving conditions on each driving road type.

[0041] In addition, after determining the driving conditions of a certain vehicle model on each type of road, this solution can also splice the driving conditions on each type of road to obtain the driving conditions of a certain vehicle model on all types of roads, which can provide a reliable data source for subsequent bench tests.

[0042] The technical solution provided by the embodiment of the present invention obtains the kinematic fragment of the vehicle; the vehicle model belongs to one of the pure electric four-wheel drive model, the pure electric two-wheel drive model and the hybrid model; the driving road type is determined according to the kinematic fragment; the driving road type includes urban roads, mountain roads, highways and suburban roads; the total mileage ratio of the vehicle in each driving road type is determined; according to the total mileage ratio and the clustering results of the kinematic fragments associated with each driving road type, the driving condition of the vehicle on each driving road type is determined. By executing the technical solution provided by the embodiment of the present invention, it is possible to scientifically and objectively characterize the driving conditions of new energy vehicles on different types of roads, providing a reliable data source for subsequent bench tests.

[0043] Figure 3 1 is a flow chart of a method for determining a driving condition of a new energy vehicle provided by an embodiment of the present invention. This embodiment is optimized on the basis of the above embodiment. Figure 3 As shown, the method for determining the driving condition of a new energy vehicle in an embodiment of the present invention may include:

[0044] S210: Obtain the kinematic fragment of the vehicle.

[0045] S220: Determine at least one motion characteristic parameter based on the kinematic segment.

[0046] Among them, this scheme can determine the time period corresponding to the kinematic segment according to the kinematic segment of the vehicle, and then determine at least one operating characteristic parameter of the vehicle within the time period, including the speed, running time, temperature, torque, throttle state, brake state, acceleration ratio, deceleration ratio, uniform acceleration ratio, uniform deceleration ratio, uniform speed ratio, idle ratio, maximum speed, average speed, average acceleration, relative positive acceleration, speed standard deviation, and acceleration standard deviation.

[0047] Therefore, by determining multiple motion feature parameters of the kinematic segment, the kinematic segment can be described, providing a reliable data source for subsequent steps, thereby improving the recognition accuracy of the road type recognition model.

[0048] S230: Input each of the motion feature parameters into the trained road type recognition model to determine the driving road type.

[0049] Among them, this solution can input all the motion feature parameters of the kinematic segment into a pre-trained road type recognition model to obtain the driving road type to which the kinematic segment belongs.

[0050] In another feasible embodiment, optionally, the process of determining the road type recognition model includes: determining a preset number of vehicles to be trained according to the ranking results of the total mileage traveled within a preset time period; respectively determining the kinematic segments to be trained for each vehicle to be trained within the preset time period; determining at least one motion feature parameter of each kinematic segment to be trained; respectively inputting the motion feature parameters of each kinematic segment to be trained and the road type to which the kinematic segment to be trained belongs into a decision tree algorithm for training to obtain a random forest model; and adjusting the parameters of the random forest model to obtain a trained road type recognition model.

[0051] Among them, the preset time period can be a historical time period, such as in the past year, or in the past month. The preset time period can be set according to actual needs. This solution can select user vehicles with high mileage activity in typical cities, and construct the driving data of these user vehicles into a training set for the recognition of driving segment features of subdivided working conditions. Exemplarily, for a certain vehicle model, this solution can count the mileage data of all vehicles of this vehicle model within a preset time period. For example, assuming that the preset time period is the past year, user vehicles with high mileage activity of this vehicle model in the past year are selected as vehicles to be trained, that is, the driving data of vehicles with a high total mileage value in the past year are used as test set data to form a sample library of target vehicle models to be analyzed. Then the vehicle driving data in the test set data is cleaned and processed to eliminate invalid data, over-limit data, control data and abnormal data. Determine the kinematic segment to be trained for each vehicle to be trained within the preset time period and the type of driving road to which the kinematic segment to be trained belongs. Each kinematic segment is described by using motion characteristic parameters such as vehicle speed, running time, temperature, torque, throttle state, brake state, acceleration ratio, deceleration ratio, uniform acceleration ratio, uniform deceleration ratio, uniform speed ratio, idling ratio, maximum speed, average speed, average acceleration, relative positive acceleration, speed standard deviation, acceleration standard deviation, etc., and each motion characteristic parameter describing the kinematic segment and the type of driving road to which the kinematic segment belongs are respectively input into the decision tree algorithm as training samples for training, and an initial road type recognition model is obtained, that is, a random forest model constructed by many decision trees. Then, the constructed random forest model is parameterized, and the main parameters to be adjusted include the number of sub-models, the maximum tree depth, the maximum number of leaf nodes, the minimum number of leaf node samples, the minimum number of samples required for splitting, the maximum number of features, the splitting condition, etc., and the recognition accuracy of the random forest model is increased to a certain percentage, such as 85%, to obtain a trained road type recognition model.

[0052] Therefore, by using the vehicle's historical driving data to train a road type recognition model based on a decision tree algorithm, it is possible to provide a reliable data source for subsequent steps.

[0053] S240: Determine the proportion of the total mileage of the vehicle on each of the driving road types.

[0054] In another feasible implementation, optionally, determining the proportion of the total mileage of the vehicle in each of the driving road types includes: determining the total mileage of kinematic segments of the vehicle in each of the driving road types; and taking the ratio between the total mileage of each of the kinematic segments as the total mileage proportion.

[0055] Assuming that the driving road type is an urban road, this solution can determine the kinematic segments of each vehicle of the model on the urban road, and then the sum of the mileage in each kinematic segment can be determined as the total mileage of each vehicle on the urban road, thereby determining the total mileage of all vehicles of the model on the urban road. Then, the ratio between the total mileage of the vehicle of the model on urban roads, the total mileage of mountain roads, the total mileage of highways, and the total mileage of suburban roads is determined as the total mileage ratio of the vehicle in each driving road type, for example, 1:2:3:4.

[0056] Therefore, by determining the total mileage of the vehicle's kinematic segments in each driving road type and taking the ratio between the total mileage of each kinematic segment as the total operating mileage ratio, it is possible to determine the weight ratio of each driving road type in the overall driving condition, providing a reliable data source for the subsequent construction of driving conditions for different driving road types.

[0057] S250: Determine the driving condition of the vehicle on each of the driving road types based on the total mileage ratio and the clustering results of the kinematic segments associated with each of the driving road types.

[0058] In this embodiment, optionally, the driving condition of the vehicle on each of the driving road types is determined based on the total mileage ratio and the clustering results of the kinematic segments associated with each of the driving road types, including: determining the time length corresponding to each driving road type according to the total mileage ratio; determining the kinematic segments associated with each driving road type; and obtaining the driving condition of the vehicle on each road type based on the clustering results and the time length of each kinematic segment associated with each driving road type using a K-means clustering algorithm.

[0059] Among them, assuming that the total mileage ratio of a certain model of vehicle in urban roads, mountain roads, highways and suburban roads is 1:2:3:4, then the time length ratio corresponding to the urban road driving condition, mountain road driving condition, highway driving condition and suburban road driving condition is also 1:2:3:4. If the total time length of all conditions is 1000s, the time lengths corresponding to the urban road driving condition, mountain road driving condition, highway driving condition and suburban road driving condition are 100s, 200s, 300s and 400s respectively. In the above steps, the kinematic segments of all vehicles of a certain model on each driving road type have been determined. This scheme can cluster all kinematic segments on the driving road type using the K-means clustering algorithm. The clustering time length is the time length corresponding to the driving condition on the driving road type, and the corresponding relationship between the vehicle driving time as the horizontal axis and the driving speed as the vertical axis within the corresponding time length is obtained. That is, the driving condition on each driving road type.

[0060] Therefore, by determining the time length corresponding to each driving road type according to the total mileage ratio, determining the kinematic segments associated with each driving road type, and clustering the kinematic segments associated with each driving road type based on the K-means clustering algorithm, the driving condition of the vehicle on each road type is obtained. The driving conditions of different driving road types can be scientifically and accurately determined, providing a reliable data source for subsequent bench tests.

[0061] In this embodiment, optionally, after determining the driving condition of the vehicle on each of the driving road types, it also includes: combining the driving conditions on each of the driving road types to obtain the overall driving condition of the vehicle on all driving road types.

[0062] Among them, after determining the driving conditions of a certain model of vehicle on each type of driving road, this solution can also splice the driving conditions on each type of driving road to obtain the driving conditions of a certain model of vehicle on all types of driving roads.

[0063] Therefore, by combining the driving conditions on each type of road, the overall driving conditions of the vehicle on all types of roads can be obtained. This can achieve a scientific and objective characterization of the driving conditions of new energy vehicles on each type of road, providing a reliable data source for subsequent bench tests.

[0064] The technical solution provided by the embodiment of the present invention obtains the kinematic segment of the vehicle; determines at least one motion characteristic parameter based on the kinematic segment; inputs each motion characteristic parameter into the trained road type recognition model to determine the type of driving road; determines the proportion of the total mileage of the vehicle in each type of driving road; and determines the driving condition of the vehicle on each type of driving road based on the total mileage proportion and the clustering results of the kinematic segments associated with each type of driving road. By executing the technical solution provided by the embodiment of the present invention, it is possible to scientifically and objectively characterize the driving conditions of new energy vehicles on different types of roads, providing a reliable data source for subsequent bench tests.

[0065] In order to more clearly describe the technical solution of the present invention, Figure 4 is a flow chart of a method for determining a driving condition of a new energy vehicle provided by an embodiment of the present invention, such as Figure 4 As shown, the technical solution provided by the embodiment of the present invention may also include the following steps:

[0066] Step 1: Determine a preset number of vehicles to be trained according to the ranking results of the total mileage within a preset time period.

[0067] Among them, this solution can identify and filter the selected vehicle model data, mainly identifying and classifying into three types of numbers: pure electric four-wheel drive models, pure electric two-wheel drive models, and hybrid models, with the goal of accurately describing the driving conditions of the models and finely analyzing the data objects. Select users with high mileage activity in the period from January to December, that is, The user data with the highest numerical ranking is used as the test set data, which forms the sample library of the target vehicle models to be analyzed.

[0068] Step 2: Clean the original driving data to remove invalid data, over-limit data, control data and abnormal data.

[0069] Step 3: respectively determine the kinematic segments to be trained for each vehicle to be trained within a preset time period.

[0070] Step 4: Determine at least one motion feature parameter of each kinematic segment to be trained.

[0071] Among them, this scheme can divide road labels into four categories according to driving characteristics: urban roads, mountain roads, expressways and suburban roads. The bypass expressways or ring roads of typical cities are used as the dividing line between urban and suburban areas, and then intersected with the national road database to obtain the urban road and suburban road database. The expressway database is a collection of the expressway parts of roads in provinces and regions, including suburban expressways and bypass expressways. The administrative level of ordinary roads is divided into national highways, provincial highways, county roads, township roads, village roads, and special roads using G, S, X, Y, C, and Z, mainly covering other roads in suburban areas except expressways and mountainous areas. For mountainous roads, DEM data is used to obtain the mountainous area in typical cities in ARCGIS software, thereby obtaining a mountainous road database. The vehicle operation characteristic parameters are selected as follows: vehicle speed, running time, temperature, torque, throttle state, brake state, acceleration ratio, deceleration ratio, uniform acceleration ratio, uniform deceleration ratio, uniform speed ratio, idling ratio, maximum speed, average speed, average acceleration, relative positive acceleration, speed standard deviation, acceleration standard deviation and other 18 motion characteristic parameters for identification.

[0072] Step 5: Input each motion feature parameter of each kinematic segment to be trained and the road type to which the kinematic segment to be trained into the decision tree algorithm for training to obtain a random forest model.

[0073] Among them, this scheme can train the sample set data for the target vehicle model, extract T times with replacement, and extract t short-trip segments each time, eventually forming T samples. It is used to train the segment classification decision tree as the sample at the root node of the decision tree. When each sample has 18 attributes, when each node of the decision tree needs to be split, m attributes are randomly selected from these 18 attributes. Then, one attribute with the maximum Gini coefficient gain is selected from these m attributes as the splitting attribute of the node. Each node must be split in this way until the next time the attribute selected by the node is the attribute used when its parent node just split, then the node has reached the leaf node and does not need to be split further. Note that no pruning is performed during the formation of the entire decision tree. This process is repeated to establish a large number of decision trees, forming a random forest.

[0074] Step 6: Adjust the parameters of the random forest model to obtain a trained road type recognition model.

[0075] Among them, this scheme can adjust parameters according to the constructed random forest model. The main adjusted parameters include the number of sub-models, the maximum tree depth, the maximum number of leaf nodes, the minimum number of leaf node samples, the minimum number of samples required for splitting, the maximum number of features, splitting conditions and other parameters, and improve the accuracy to 85% to obtain a trained road type recognition model.

[0076] Step 7: Get the kinematic fragment of the vehicle.

[0077] Among them, this solution can also clean the vehicle driving data before determining the kinematic segment, and eliminate invalid data, over-limit data, control data and abnormal data.

[0078] Step 8: Determine the driving road type according to the kinematic segment.

[0079] Step 9: Determine the proportion of the total mileage of the vehicle on each type of road.

[0080] Step 10: Determine the driving condition of the vehicle on each driving road type according to the total mileage ratio and the clustering results of the kinematic segments associated with each driving road type.

[0081] Among them, this scheme can cluster the operating conditions of different driving road types through the K-means clustering algorithm, and cluster the full typical spectrum through the total mileage ratio, so as to form the driving conditions of different driving road types and the overall driving conditions.

[0082] The technical solution provided by the embodiment of the present invention can identify the weight ratio of all users under different road section characteristics, and form road spectrum data under different road labels and the overall road condition characteristic spectrum of all users through working condition aggregation. It can comprehensively and accurately characterize the driving conditions of users' vehicles, combine with the whole vehicle economic simulation platform, realize the mileage simulation, obtain the energy consumption prediction model under different regions and different temperatures, and form the user's actual working condition load spectrum according to the user's working condition distribution and proportion as the design input to guide the bench test.

[0083] Figure 5 is a schematic diagram of the structure of a driving condition determination device for a new energy vehicle provided by an embodiment of the present invention. The device can be configured in an electronic device for determining the driving condition of a new energy vehicle, such as Figure 5 As shown, the device comprises:

[0084] A kinematic segment determination module 310 is used to obtain a kinematic segment of a vehicle; the vehicle model is one of a pure electric four-wheel drive model, a pure electric two-wheel drive model, and a hybrid model;

[0085] A driving road type determination module 320, configured to determine a driving road type according to the kinematic segment; the driving road type includes an urban road, a mountain road, a highway, and a suburban road;

[0086] A total mileage ratio determination module 330 is used to determine the total mileage ratio of the vehicle in each of the driving road types;

[0087] The driving condition determination module 340 is used to determine the driving condition of the vehicle on each of the driving road types according to the total mileage ratio and the clustering results of the kinematic segments associated with each of the driving road types.

[0088] Optionally, the driving road type determination module 320 includes a motion feature parameter determination unit, which is used to determine at least one motion feature parameter based on the kinematic segment; and a driving road type determination unit, which is used to input each of the motion feature parameters into a trained road type recognition model to determine the driving road type.

[0089] Optionally, the process of determining the road type recognition model includes: determining a preset number of vehicles to be trained according to the ranking results of the total mileage traveled within a preset time period; respectively determining the kinematic segments to be trained for each vehicle to be trained within the preset time period; determining at least one motion feature parameter of each kinematic segment to be trained; respectively inputting the motion feature parameters of each kinematic segment to be trained and the road type to which the kinematic segment to be trained belongs into a decision tree algorithm for training to obtain a random forest model; and adjusting the parameters of the random forest model to obtain a trained road type recognition model.

[0090] Optionally, the total mileage ratio determination module 330 includes a kinematic segment total mileage determination unit, which is used to determine the total mileage of the kinematic segments of the vehicle in each driving road type; and a total mileage ratio determination unit, which is used to use the ratio between the total mileages of each kinematic segment as the total mileage ratio.

[0091] Optionally, the driving condition determination module 340 includes a time length determination unit, which is used to determine the time length corresponding to each driving road type according to the total mileage ratio; an associated kinematic segment determination unit, which is used to determine the kinematic segments associated with each driving road type; and a driving condition determination unit, which is used to cluster the kinematic segments associated with each driving road type based on a K-means clustering algorithm, and obtain the clustering results and the time length to obtain the driving condition of the vehicle on each road type.

[0092] Optionally, the device also includes an overall driving condition determination module, which is used to combine the driving conditions on each of the driving road types after determining the driving conditions of the vehicle on each of the driving road types, so as to obtain the overall driving condition of the vehicle on all driving road types.

[0093] Optionally, the motion characteristic parameters include at least one of vehicle speed, running time, temperature, torque, throttle state, brake state, acceleration ratio, deceleration ratio, uniform acceleration ratio, uniform deceleration ratio, uniform speed ratio, idle ratio, maximum speed, average speed, average acceleration, relative positive acceleration, speed standard deviation, and acceleration standard deviation.

[0094] The device provided in the above-mentioned embodiments can execute the method for determining the driving condition of a new energy vehicle provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0095] Figure 6 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 6 As shown, the device includes:

[0096] one or more processors 410, Figure 6 A processor 410 is taken as an example;

[0097] Memory 420;

[0098] The device may further include: an input device 430 and an output device 440 .

[0099] The processor 410, memory 420, input device 430 and output device 440 in the device may be connected via a bus or other means. Figure 6 The example of connecting through bus is taken in the following.

[0100] The memory 420, as a non-transitory computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to a method for determining a driving condition of a new energy vehicle in an embodiment of the present invention. The processor 410 executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 420, that is, to implement a method for determining a driving condition of a new energy vehicle in the above method embodiment, namely:

[0101] Obtaining a kinematic segment of a vehicle; the vehicle model is one of a pure electric four-wheel drive model, a pure electric two-wheel drive model, and a hybrid model;

[0102] Determine the type of driving road according to the kinematic segment; the driving road type includes urban roads, mountain roads, expressways and suburban roads;

[0103] Determining the proportion of the total mileage of the vehicle on each of the driving road types;

[0104] The driving condition of the vehicle on each of the driving road types is determined according to the total running mileage ratio and the clustering results of the kinematic segments associated with each of the driving road types.

[0105] The memory 420 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 420 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 420 may optionally include a memory remotely arranged relative to the processor 410, and these remote memories may be connected to the terminal device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0106] The input device 430 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the computer device. The output device 440 may include a display device such as a display screen.

[0107] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, a method for determining a driving condition of a new energy vehicle provided in an embodiment of the present invention is implemented, that is,

[0108] Obtaining a kinematic segment of a vehicle; the vehicle model is one of a pure electric four-wheel drive model, a pure electric two-wheel drive model, and a hybrid model;

[0109] Determine the type of driving road according to the kinematic segment; the driving road type includes urban roads, mountain roads, expressways and suburban roads;

[0110] Determining the proportion of the total mileage of the vehicle on each of the driving road types;

[0111] The driving condition of the vehicle on each of the driving road types is determined according to the total running mileage ratio and the clustering results of the kinematic segments associated with each of the driving road types.

[0112] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.

[0113] Computer-readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0114] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0115] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0116] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for determining a driving condition of a new energy vehicle, characterized in that: include: Obtaining a kinematic segment of a vehicle; the vehicle model is one of a pure electric four-wheel drive model, a pure electric two-wheel drive model, and a hybrid model; Determine the type of driving road according to the kinematic segment; the driving road type includes urban roads, mountain roads, expressways and suburban roads; Determining the proportion of the total mileage of the vehicle on each of the driving road types; Determining the driving condition of the vehicle on each of the driving road types according to the total running mileage ratio and the clustering results of the kinematic segments associated with each of the driving road types; The determining the driving road type according to the kinematic segment comprises: determining at least one motion characteristic parameter based on the kinematic segment; Inputting each of the motion characteristic parameters into a trained road type recognition model to determine the driving road type; The determination process of the road type recognition model includes: Determine a preset number of vehicles to be trained according to the ranking results of the total mileage within a preset time period; Determine the kinematic segments to be trained for each vehicle to be trained within the preset time period respectively; Determining at least one motion feature parameter of each kinematic segment to be trained; Inputting the motion feature parameters of each kinematic segment to be trained and the road type to which the kinematic segment to be trained into a decision tree algorithm for training to obtain a random forest model; The parameters of the random forest model are adjusted to obtain a trained road type recognition model.

2. The method according to claim 1, characterized in that Determining the proportion of the total mileage of the vehicle on each of the driving road types includes: Determine the total kinematic segment mileage of the vehicle in each driving road type; The ratio between the total mileage of each kinematic segment is used as the total running mileage ratio.

3. The method according to claim 1, characterized in that Determining the driving condition of the vehicle on each of the driving road types according to the total mileage ratio and the clustering results of the kinematic segments associated with each of the driving road types includes: Determine the length of time corresponding to each driving road type according to the total running mileage ratio; determining a kinematic segment associated with each travel road type; The kinematic segments associated with each driving road type are clustered based on a K-means clustering algorithm, and the clustering result and the time length are used to obtain the driving condition of the vehicle on each road type.

4. The method according to claim 1, characterized in that: After determining the driving condition of the vehicle on each of the driving road types, the method further includes: The driving conditions on each of the driving road types are combined to obtain the overall driving condition of the vehicle on all driving road types.

5. The method according to claim 1, characterized in that The motion characteristic parameters include at least one of vehicle speed, running time, temperature, torque, throttle status, brake status, acceleration ratio, deceleration ratio, uniform acceleration ratio, uniform deceleration ratio, uniform speed ratio, idle ratio, maximum speed, average speed, average acceleration, relative positive acceleration, speed standard deviation, and acceleration standard deviation.

6. A driving condition determination device for a new energy vehicle, characterized in that: include: A kinematic segment determination module, used for obtaining a kinematic segment of a vehicle; the vehicle model is one of a pure electric four-wheel drive model, a pure electric two-wheel drive model and a hybrid model; A driving road type determination module, used to determine the driving road type according to the kinematic segment; the driving road type includes urban roads, mountain roads, expressways and suburban roads; A total mileage ratio determination module, used to determine the total mileage ratio of the vehicle on each of the driving road types; A driving condition determination module, configured to determine the driving condition of the vehicle on each of the driving road types according to the total mileage ratio and the clustering results of the kinematic segments associated with each of the driving road types; The driving road type determination module includes: a motion characteristic parameter determination unit, configured to determine at least one motion characteristic parameter according to the kinematic segment; A driving road type determination unit, used for inputting each of the motion characteristic parameters into a trained road type recognition model to determine the driving road type; The process of determining the road type recognition model includes: determining a preset number of vehicles to be trained according to the ranking results of the total mileage traveled within a preset time period; respectively determining the kinematic segments to be trained for each vehicle to be trained within the preset time period; determining at least one motion feature parameter for each kinematic segment to be trained; respectively inputting the motion feature parameters of each kinematic segment to be trained and the road type to which the kinematic segment to be trained belongs into a decision tree algorithm for training to obtain a random forest model; and adjusting the parameters of the random forest model to obtain a trained road type recognition model.

7. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining the driving condition of a new energy vehicle as described in any one of claims 1-5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for determining the driving condition of a new energy vehicle as described in any one of claims 1 to 5 is implemented.

Images