Electric vehicle bench test method and system based on actual traffic scenarios

Abstract

The present invention relates to the technical field of vehicle test analysis, and particularly to a method and system for electric vehicle bench test based on actual traffic scenarios. The method includes: obtaining map information and driving scenario data of a target path; constructing a road scenario of the target path according to the map information, constructing a traffic flow scenario of the target path according to the map information and driving scenario data, and generating an actual traffic scenario of the target path based on the road scenario and the traffic flow scenario; building an electric drive system bench of an electric vehicle, controlling the electric drive system bench to perform a simulated driving test on the target path under the actual traffic scenario, collecting data of the simulated driving test, and analyzing the test results of the electric vehicle according to the data of the simulated driving test. Thus, the problems in the related art that using on-road vehicle tests results in unstable test results and potential safety hazards, poor test repeatability, and the difficulty of using standard cycle conditions in bench tests to truly reflect the efficiency of the electric drive system under actual traffic scenarios are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle test analysis, and particularly relates to an electric vehicle bench test method and system based on an actual traffic scenario. Background Art

[0002] In the wave of the new four modernizations of electric vehicles, with the continuous improvement of the refinement degree of vehicle energy management, the efficiency test of the electric drive system has become an important direction of energy management. However, the current electric drive system efficiency test methods mainly rely on standard cycle conditions or custom conditions as the input conditions for electric vehicle tests, such as CLTC-P (China Light Duty Vehicle Test Cycle), WLTC (Worldwide harmonized Light vehicles Test Cycle), etc.

[0003] In related technologies, when using standard cycle conditions for testing, there is an intention for the driver to follow the speed-time curve, which is difficult to truly reflect the efficiency of the electric drive system in an actual traffic scenario; when using the method of on-road vehicle testing, there are problems such as the difficulty in fixing the arrangement of current and voltage sensors and the difficulty in arranging wheel-side speed and torque sensors. In addition, there are safety hazards due to the arrangement of vehicle sensors, and the actual traffic scenario changes instantaneously, resulting in poor test repeatability. Summary of the Invention

[0004] The present invention provides an electric vehicle bench test method and system based on an actual traffic scenario to solve problems such as unstable test results and safety hazards caused by using on-road vehicle testing in related technologies, poor test repeatability, and the difficulty in truly reflecting the efficiency of the electric drive system in an actual traffic scenario using standard cycle conditions in bench testing.

[0005] In a first aspect embodiment of the present invention, an electric vehicle bench test method based on an actual traffic scenario is provided, including the following steps: obtaining map information and driving scenario data of a target path; constructing a road scenario of the target path according to the map information, constructing a traffic flow scenario of the target path according to the map information and the driving scenario data, and generating an actual traffic scenario of the target path according to the road scenario and the traffic flow scenario; building an electric drive system bench of an electric vehicle, controlling the electric drive system bench to perform a simulated driving test on the target path under the actual traffic scenario, collecting data of the simulated driving test, and analyzing the test results of the electric vehicle according to the data of the simulated driving test.

[0006] Optionally, the constructing a road scenario of the target path according to the map information includes: obtaining key road data of the target path in the map information; constructing a road scenario of the target path using the method of gradually increasing by segments according to the key road data.

[0007] Optionally, the construction of the road scenario of the target path using the step-by-step increment method based on the key road data includes: identifying the segment distance, road type, weather condition, angle of entering the road, and traffic light position of each segment road in the key road data; querying a preset table according to the road type to determine the corresponding number of lanes, road width, and speed limit signs; determining the friction coefficient of each segment road according to the road type and weather condition; constructing a road scenario based on the number of lanes, the road width, the speed limit signs, the friction coefficient, the segment distance, the angle of entering the road, and the traffic light position.

[0008] Optionally, the generation of the actual traffic scenario of the target path according to the road scenario and the traffic flow scenario includes: inputting the road scenario and the traffic flow scenario into a target neural network model, and the target neural network model outputs the traffic flow scenario of the target path.

[0009] Optionally, the structure of the target neural network model includes an input layer, an output layer, and a hidden layer. Among them, the number of nodes in the input layer is the number of vehicle parameters, the number of nodes in the output layer is the number of fault indicators, and the number of nodes in the hidden layer is the number of target nodes, where the number of target nodes is obtained by the minimum training times method.

[0010] Optionally, the training method of the target neural network model includes: obtaining key factors of map information and traffic flow scenarios to generate a training data set; using the first activation function as the activation function from the input layer to the hidden layer, and the second activation function as the activation function from the hidden layer to the output layer; training the neural network model using the training data set until the neural network model converges to the training target.

[0011] Optionally, before obtaining the key factors of map information and traffic flow scenarios to generate a training data set, it includes: identifying the historical map information and driving scenario data of the target path; constructing an initial matrix according to the historical map information and driving scenario data, and performing dimensionless processing on the initial matrix to generate a target matrix; calculating the difference between any two elements according to the target matrix to generate a difference matrix, and identifying the maximum value and minimum value of the difference matrix; calculating the correlation coefficient between each factor and traffic volume according to the maximum value and minimum value, and calculating the grey correlation degree between each factor and traffic volume according to the correlation coefficient; selecting factors with grey correlation degrees greater than a preset threshold as the key factors of map information and traffic flow scenarios.

[0012] Optionally, after the target neural network model outputs the traffic flow of the target path, it includes: identifying the traffic volume of adjacent road segments in the target path; if the difference in traffic volume is greater than a preset threshold, then start the cut-in and cut-out mechanism.

[0013] Optionally, building the electric drive system bench of the electric vehicle includes: charging the vehicle to be tested to the target power; removing the tires of the vehicle to be tested; installing the vehicle to be tested on the shaft coupling dynamometer through a flange, and at the same time installing the steering tie rod of the vehicle to the vehicle to be tested, and initializing the shaft coupling dynamometer; arranging sensors and data acquisition devices to synchronously collect vehicle and dynamometer data.

[0014] In a second aspect embodiment of the present invention, a bench test system for an electric vehicle based on an actual traffic scenario is provided. The system is implemented by applying the bench test method for an electric vehicle based on an actual traffic scenario described in the above embodiment. The system includes: a data acquisition module for synchronously collecting the current and voltage signals, vehicle CAN signals, and shaft coupling dynamometer signals of the vehicle to be tested; a networking module for obtaining the map information and driving scenario data of the target path; an actual traffic scenario construction module communicatively connected to the networking module for constructing an actual traffic scenario according to the map information and driving scenario data of the target path; a vehicle simulation model communicatively connected to the vehicle to be tested; a shaft coupling dynamometer for vehicle efficiency testing, simulating the target data of the vehicle to be tested, and feeding the target data back to the shaft coupling dynamometer control module; a shaft coupling dynamometer control module for controlling the shaft coupling dynamometer; a ring screen for displaying the actual traffic scenario to the vehicle to be tested; an environmental chamber for simulating the actual environmental temperature to build the test conditions; a host computer for running the networking module to obtain the map information and driving scenario data of the target path, inputting the map information and driving scenario data of the target path into the actual traffic scenario construction module to construct an actual traffic scenario, and displaying the actual traffic scenario to the vehicle to be tested; running the shaft coupling dynamometer control module to control the operation of the shaft coupling dynamometer, inputting the data collected by the shaft coupling dynamometer into the simulation model, and running the simulation model to perform simulation to obtain the test results.

[0015] Therefore, the present invention has at least the following beneficial effects:

[0016] The embodiment of the present invention can construct the road scenario of the target path according to the map information, construct the traffic flow scenario of the target path according to the map information and driving scenario data, generate the actual traffic scenario of the target path according to the road scenario and traffic flow scenario, build the electric drive system bench of the electric vehicle, control the electric drive system bench to perform a simulated driving test on the target path in the actual traffic scenario, collect the data of the simulated driving test, analyze the test results of the electric vehicle according to the data of the simulated driving test, construct the actual traffic scenario by fusing the online map information, and realize the test of the vehicle electric drive efficiency on the shaft coupling dynamometer. It can not only improve the accuracy of the test, but also ensure the safety, stability, consistency, and repeatability of the test process, and reduce the overall cost.

[0017] Additional aspects and advantages of the present invention will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present invention. Description of the Drawings

[0018] The above-mentioned and / or additional aspects and advantages of the present invention will become apparent and be readily understood from the following description of embodiments in conjunction with the drawings, wherein:

[0019] Figure 1 It is a flowchart of a bench test method for an electric vehicle based on an actual traffic scenario provided according to an embodiment of the present invention;

[0020] Figure 2 It is a schematic diagram of a road scene construction provided according to an embodiment of the present invention;

[0021] Figure 3 It is a schematic diagram of a method for automatically constructing an actual traffic scenario provided according to an embodiment of the present invention;

[0022] Figure 4 It is a schematic diagram of a bench test method for the efficiency of an electric drive system of an electric vehicle based on an actual traffic scenario provided according to an embodiment of the present invention;

[0023] Figure 5 It is an example diagram of a bench test system for an electric vehicle based on an actual traffic scenario provided according to an embodiment of the present invention.

[0024] Description of the reference numerals: The bench test system 10 for an electric vehicle based on an actual traffic scenario, the data acquisition module 100, the networking module 200, the actual traffic scenario construction module 300, the vehicle simulation model 400, the shaft coupling dynamometer 500, the shaft coupling dynamometer control module 600, the ring screen 700, the environmental chamber 800, and the upper computer 900. Detailed Embodiments

[0025] The embodiments of the present invention will be described in detail below. The examples of the embodiments are shown in the drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and are intended to explain the present invention, but should not be construed as limiting the present invention.

[0026] The bench test method and system for an electric vehicle based on an actual traffic scenario according to an embodiment of the present invention will be described below with reference to the drawings.

[0027] Specifically, Figure 1 It is a schematic flowchart of a bench test method for an electric vehicle based on an actual traffic scenario provided by an embodiment of the present invention.

[0028] As Figure 1As shown in the figure, the electric vehicle bench test method based on the actual traffic scenario includes the following steps:

[0029] In step S101, obtain the map information and driving scenario data of the target path.

[0030] Among them, the target path can be selected according to requirements without specific limitation.

[0031] It can be understood that in the embodiments of the present invention, by obtaining the map information and driving scenario data of the target path, it is convenient to subsequently construct the actual traffic scenario of the target path.

[0032] Specifically, the network connection module is used to obtain online map information. Through the online map API interface, key information of the test path is obtained, including motorized turning points, section distances, section travel times, segmented distances, angles of each segmented entry road, segmented travel times, segmented road types, segmented congestion levels, number of traffic lights, traffic light positions, weather, temperature, etc.; among them, the angles of the entry roads are divided into 12 levels, including 0-11, "0" represents 345 degrees to 15 degrees, and so on, 11" represents 315 degrees to 345 degrees", where the angle is the clockwise angle between the entry road angle and the due north direction; specifically, the meanings represented by 0-11 are: 0 - [345° - 15°]; 1 - [15° - 45°]; 2 - [45° - 75°]; 3 - [75° - 105°]; 4 - [105° - 135°]; 5 - [135° - 165°]; 6 - [165° - 195°]; 7 - [195° - 225°]; 8 - [225° - 255°]; 9 - [255° - 285°]; 10 - [285° - 315°]; 11 - [315° - 345°]. The motorized turning points include eight reference directions, namely 1-8, where 1 - straight ahead, 2 - right front turn, 3 - right turn, 4 - right rear turn, 5 - U-turn, 6 - left rear turn, 7 - left turn, 8 - left front turn; the road types of the segments include 10 types, 0 - highway, 1 - urban highway, 2 - national highway, 3 - provincial highway, 4 - county road, 5 - rural road in townships and villages, 6 - other roads, 7 - ninth-class road, 8 - shipping route (ferry), 9 - pedestrian road. The segmented congestion levels include four types, namely 1 - unobstructed, 2 - slow moving, 3 - congested, 4 - severely congested.

[0033] In step S102, construct the road scenario of the target path according to the map information, construct the traffic flow scenario of the target path according to the map information and driving scenario data, and generate the actual traffic scenario of the target path according to the road scenario and traffic flow scenario.

[0034] It can be understood that, in the embodiments of the present invention, the road scene of the target path can be constructed according to map information, the traffic flow scene of the target path can be constructed according to map information and driving scene data, and the actual traffic scene of the target path can be generated according to the road scene and the traffic flow scene, so as to simulate as realistically as possible the situation of a vehicle driving on an actual road during subsequent testing, and improve the accuracy and reliability of the efficiency test of the electric drive system of an electric vehicle.

[0035] Specifically, the actual traffic scene construction module is used to construct the actual traffic scene, including road scene construction and traffic flow construction. Based on the section distance, the angle of entering the road for each section, the motorized turning point, the section distance, the section road type, and the traffic light position in the online map working condition information, the road scene is automatically constructed, and the rolling resistance coefficient of the road is corrected in real time according to information such as road type, weather, and temperature, making the constructed road scene more real-time; it is constructed according to historical traffic information and information such as motorized turning points, section congestion levels, traffic light positions, and weather provided by the online map.

[0036] In the embodiments of the present invention, constructing the road scene of the target path according to map information includes: obtaining the key road data of the target path in the map information; constructing the road scene of the target path using the method of incrementing section by section according to the key road data.

[0037] It can be understood that, in the embodiments of the present invention, the road scene of the target path can be constructed using the method of incrementing section by section according to the key road data of the target path in the map information. The method of incrementing section by section can accurately simulate the specific characteristics of each section of the road, such as road type, number of lanes, width, speed limit sign, friction coefficient, etc., ensuring that the physical properties of each section of the road can be accurately reflected; based on the real-time information provided by the online map (such as weather, temperature, traffic light position, etc.), each section of the road can be dynamically corrected, making the constructed road scene closer to the actual situation and improving the accuracy of subsequent testing.

[0038] In the embodiments of the present invention, constructing the road scene of the target path using the method of incrementing section by section according to the key road data includes: identifying the section distance, road type, weather conditions, angle of entering the road, and traffic light position of each section of the road in the key road data; querying a preset table according to the road type to determine the corresponding number of lanes, road width, and speed limit sign; determining the friction coefficient of each section of the road according to the road type and weather conditions; constructing the road scene according to the number of lanes, road width, speed limit sign, friction coefficient, section distance, angle of entering the road, and traffic light position.

[0039] Among them, the preset table can be set according to the actual situation, as shown in Table 1 below, without specific limitation.

[0040] It can be understood that the embodiments of the present invention can identify the segment distance, road type, weather condition, angle of entering the road, and traffic light position of each segment of the road in the key road data; query the preset table according to the road type to determine the corresponding number of lanes, road width, and speed limit sign; determine the friction coefficient of each segment of the road according to the road type and weather condition; construct a road scene based on the number of lanes, road width, speed limit sign, friction coefficient, segment distance, angle of entering the road, and traffic light position, so as to accurately simulate the specific characteristics of each segment of the road, make the constructed road scene closer to the actual situation, and improve the accuracy of subsequent tests.

[0041] Specifically, as Figure 2 shown, the road scene construction is carried out by an increment-by-segment method. The segment distance, segment road type, angle of each segment entering the road, and traffic light position are fed back by using an online map. For each segment of the road in the scene construction module, the road type is defined, and the number of lanes, road width, speed limit sign, and friction coefficient are set. Among them, the settings of the number of lanes, road width, and speed limit sign are obtained by statistically analyzing the actually collected driving scene database. For different types of road types, the construction lookup table index is extracted as shown in Table 1 below. By inputting the road type, the number of lanes, road width, and speed limit sign can be obtained.

[0042] Table 1 Road type correspondence table

[0043]

[0044] For example, if the road type corresponding to the target path of the present invention is a highway, the corresponding number of lanes is LN1, the road width is LW1, and the speed limit sign is Vlimt1. The final result can be obtained by querying Table 1 according to specific requirements.

[0045] In addition, the friction coefficients of different roads of the present invention are obtained through Table 2 below. By inputting the road type and weather, the friction coefficients of each segment of the road can be obtained.

[0046] Table 2 Friction coefficient correspondence table

[0047]

[0048] For example, if the road type corresponding to the target path of the present invention is a highway and the weather condition today is sunny, the friction coefficient of the corresponding road is Lf11.

[0049] Then, it increases segment by segment according to the angle of each segment entering the road and the segment length, and finally arranges the position of the traffic lights to finally form the planned road scene.

[0050] In the embodiment of the present invention, the actual traffic scenario for generating the target path according to the road scenario and the traffic flow scenario includes: inputting the road scenario and the traffic flow scenario into the target neural network model, and the target neural network model outputs the traffic flow scenario of the target path.

[0051] It can be understood that in the embodiment of the present invention, the road scenario and the traffic flow scenario can be input into the target neural network model, and the target neural network model outputs the traffic flow scenario of the target path. The target neural network can quickly adapt to changes in road conditions and traffic conditions, thereby timely adjusting the traffic flow prediction results to ensure that the test scenario is always close to reality, so as to facilitate the subsequent efficiency test of the electric vehicle drive system to be carried out under conditions close to the real situation, and at the same time ensure that the test results have high representativeness and repeatability.

[0052] Specifically, as Figure 3 shown, the present invention can use historical data such as road type, segment distance, segment congestion, segment travel time, weather, etc., motor vehicle traffic volume, non-motor vehicle traffic volume, pedestrian traffic volume, motor vehicle speed, etc. to train the neural network model.

[0053] The model input data can include motor vehicle turning points, segment distances, segment travel times, sectional distances, angles of entering the road for each section, sectional travel times, sectional road types, sectional traffic congestion levels, traffic light numbers, traffic light positions, weather and temperature, etc.; the model outputs traffic flow scenarios such as motor vehicle traffic volume, non-motor vehicle traffic volume, pedestrian traffic volume, and motor vehicle speed.

[0054] In the embodiment of the present invention, the structure of the target neural network model includes an input layer, an output layer, and a hidden layer. Among them, the number of nodes in the input layer is the number of vehicle parameters, the number of nodes in the output layer is the number of fault indicators, and the number of nodes in the hidden layer is the number of target nodes, where the number of target nodes is obtained by the minimum training times method.

[0055] Specifically, set the number of nodes in the input layer of the neural network model to N, where N is the number of vehicle parameters, and set the number of output nodes to P, where P is the number of fault indicators; set the number of hidden layers to N1, where N1 is 1 or 2. If the number of layers is too many, overfitting will occur, affecting the model operation speed and accuracy. The number of nodes N2 in each layer is obtained by the minimum training times method:

[0056] Specifically, first determine a basic range through the empirical formula, using the first empirical formula: N2 = (N + P) 1 / 2 + b; where b is a natural number between [1, 10], and an empirical value n21 of the number of nodes is obtained; then according to the second empirical formula: N2 = 2N + 1; an empirical value n22 of the number of nodes is obtained, and thus N2 takes a natural number between [n21, n22].

[0057] Then, the golden section method is used to select the value n23 of the number of nodes, and the number of training times when the neural network models with the number of nodes n21, n22, and n23 are stable is calculated. The two settlement quantities corresponding to the smallest two times are selected, and then the golden section method is used to continue taking values between the corresponding nodes. This is repeated until a unique value is selected, which is the number of hidden layer nodes. Selecting the appropriate number of nodes in this way can quickly achieve result prediction and improve efficiency.

[0058] In the embodiment of the present invention, the training method of the target neural network model includes: obtaining key factors of map information and traffic flow scenarios to generate a training data set; among them, using the first activation function as the activation function from the input layer to the hidden layer, and the second activation function as the activation function from the hidden layer to the output layer; using the training data set to train the neural network model until the neural network model converges to the training target.

[0059] Among them, the first activation function is the tangent sigmoid TansIg function, and the second activation function is the Purelin function, which can be selected according to actual needs and is not specifically limited.

[0060] It can be understood that the embodiment of the present invention can obtain key factors of map information and traffic flow scenarios to generate a training data set; among them, using the first activation function as the activation function from the input layer to the hidden layer, and the second activation function as the activation function from the hidden layer to the output layer; using the training data set to train the neural network model until the neural network model converges to the training target to improve the accuracy of model prediction.

[0061] Specifically, the configuration of the calculation numbers of the neural network model is as follows: Use MATLAB to establish a three-layer or four-layer BP neural network model and train it, set the training target to 0.01 (i.e., the error between the predicted value and the actual value); select the tangent sigmoid TansIg function as the activation function from the input layer to the hidden layer, select the Purelin function as the activation function from the hidden layer to the output layer, set the number of training times to a large value (usually set to 10,000 times, and generally the model can converge without reaching the target training times), and the learning rate is 0.01. A smaller learning rate can ensure the stability of the system; after training, the network model successfully converges to the training target. At this time, the training of the backpropagation neural network model is completed, and the number of training times is recorded.

[0062] Based on the above neural network model, by inputting real-time online map information, the key quantities of traffic flow information can be obtained, including the traffic volume of motor vehicles, the traffic volume of non-motor vehicles, the traffic volume of pedestrians, and the driving speed of motor vehicles. Thus, a traffic flow scenario can be constructed on the road scenario.

[0063] The traffic flow scenario obtains online map information from the map every certain period, such as 5 minutes, and then uses the above-trained neural network model to reconstruct the traffic flow to ensure accurate reproduction during the test.

[0064] In the embodiment of the present invention, before obtaining the training data set from the key factors of the map information and the traffic flow scenario, it includes: identifying the historical map information and driving scenario data of the target path; constructing an initial matrix according to the historical map information and driving scenario data, and performing dimensionless processing on the initial matrix to generate a target matrix; calculating the difference between any two elements according to the target matrix to generate a difference matrix, and identifying the maximum value and minimum value of the difference matrix; calculating the correlation coefficient between each factor and the traffic volume according to the maximum value and minimum value, and calculating the grey correlation degree between each factor and the traffic volume according to the correlation coefficient; selecting the factors with the grey correlation degree greater than the preset threshold as the key factors of the map information and the traffic flow scenario.

[0065] It can be understood that the embodiment of the present invention can identify the historical map information and driving scenario data of the target path; construct an initial matrix according to the historical map information and driving scenario data, and perform dimensionless processing on the initial matrix to generate a target matrix; calculate the difference between any two elements according to the target matrix to generate a difference matrix, and identify the maximum value and minimum value of the difference matrix; calculate the correlation coefficient between each factor and the traffic volume according to the maximum value and minimum value, and calculate the grey correlation degree between each factor and the traffic volume according to the correlation coefficient; select the factors with the grey correlation degree greater than the preset threshold as the key factors of the map information and the traffic flow scenario, so as to use the factors with higher traffic flow correlation degree to form training samples to train the neural network model. Compared with the conventional training method, it can greatly improve the accuracy of model prediction and improve the calculation efficiency and accuracy.

[0066] Specifically, using the grey correlation algorithm, calculate the correlation between each online map information and the traffic volume, as well as the driving speed respectively, and construct an initial matrix according to the historical online map information and the collected driving scenario database; perform dimensionless processing on the initial matrix to obtain the first matrix; calculate the difference matrix based on the first matrix; determine the maximum value and minimum value of the difference matrix; determine the correlation coefficient according to the maximum value and minimum value; determine the grey correlation degree according to the correlation coefficient; select the factors with the grey correlation degree greater than the set threshold as the first characteristic factors.

[0067] Specifically, first construct the initial matrix X:

[0068] (1)

[0069] In the formula, the 1st to Nth columns respectively represent the numerical values of the characteristic parameters of each road section, such as the segmented distance, segmented time consumption, segmented congestion degree, weather, temperature, segmented road type, etc. The kth to k+3rd columns represent the numerical values of the traffic flow scenario indicators (i.e., the kth column is the N+1th column, the k+1th column is the N+2th column, the k+2th column is the N+3th column, and the k+3th column is the N+4th column), which are respectively the traffic volume of motor vehicles, the traffic volume of non-motor vehicles, the traffic volume of pedestrians, and the driving speed of motor vehicles. m represents the number of data rows, that is, the total number of segmented data collected;

[0070] Then, the initial matrix is dimensionless processed to obtain the first matrix Y. For different weather conditions, different numerical representations are used. For example, 1 represents sunny and 2 represents rainy. To avoid negative values for temperature, the temperature unit is in Kelvin (K).

[0071] (2)

[0072] In the formula, is the data in the standardized matrix Y, is the data in the initialized matrix X, is the data in the jth column of the initialized matrix X; i = 1, 2, 3...m, j = 1, 2, 3...N+4.

[0073] Then, calculate the difference matrix δY:

[0074] (3)

[0075] In the formula, is any element of the difference matrix δY, i = 1, 2, 3...m, j = 1, 2, 3...N+4.

[0076] Calculate the maximum value Max and minimum value Min of the difference matrix:

[0077]

[0078] (4)

[0079] Calculate the correlation coefficient matrix:

[0080] (5)

[0081] In the formula, represents the correlation coefficient between the jth map factor in the data of the ith segment and the (N+1)th factor (in this calculation, the (N+1)th factor represents the traffic volume of motor vehicles). ρ is the resolution coefficient, ρ ∈ (0, 1), and generally takes a value of 0.5. i = 1, 2, 3...m, j = 1, 2, 3...N.

[0082] Calculate the grey correlation degree:

[0083] (6)

[0084] In the formula, represents the j-th map factor and the (N + 1)-th factor, where i = 1, 2, 3... m, and j = 1, 2, 3... N. Thus, the correlation degree between each factor and the (N + 1)-th factor (in this calculation, the (N + 1)-th factor represents the traffic volume of motor vehicles) can be obtained. represents the correlation coefficient between the j-th map factor and the (N + 1)-th factor (in this calculation, the (N + 1)-th factor represents the traffic volume of motor vehicles) in the i-th segment data.

[0085] Similarly, the grey correlation degree between the j-th map factor and the (N + 2)-th, (N + 3)-th, and (N + 4)-th traffic flow factors can be calculated; the factors with a grey correlation degree greater than V are selected as the first characteristic factors, and V generally takes a value of 0.8.

[0086] If there are N1 factors greater than V, the dimension of the training matrix composed of the first characteristic factors is N1. Thus, the factors with a lower correlation degree with the traffic flow can be removed, improving the calculation efficiency and accuracy.

[0087] In the embodiment of the present invention, after the target neural network model outputs the traffic flow of the target path, it includes: identifying the traffic volume of adjacent road segments in the target path; if the traffic volume difference is greater than a preset threshold, the cut-in and cut-out mechanism is activated.

[0088] Among them, the preset threshold can be set according to the actual situation and is not specifically limited.

[0089] It can be understood that the embodiment of the present invention identifies the traffic volume of adjacent road segments in the target path; if the traffic volume difference is greater than a preset threshold, the cut-in and cut-out mechanism is activated, thereby ensuring the smoothness of the entire traffic flow and improving the accuracy of the actual traffic scenario construction.

[0090] Specifically, the cut-in and cut-out mechanism is to circularly calculate the differences in the traffic volume of motor vehicles, non-motor vehicles, and pedestrians in adjacent segments. If the previous segment has more traffic volume than the next segment, the intersection is designed to cut out the excess traffic volume. If the previous segment has less traffic volume than the next segment, the intersection is designed to cut in the excess traffic volume, thereby ensuring the smoothness of the entire traffic flow.

[0091] In step S103, a bench of the electric drive system of the electric vehicle is built, and the bench of the electric drive system is controlled to perform a simulated driving test on the target path in the actual traffic scenario, the data of the simulated driving test is collected, and the test results of the electric vehicle are analyzed according to the data of the simulated driving test.

[0092] It can be understood that the embodiments of the present invention can build a bench test rig for the electric drive system of an electric vehicle, control the bench test rig of the electric drive system to conduct a simulated driving test on a target path in an actual traffic scenario, collect the data of the simulated driving test, analyze the test results of the electric vehicle according to the data of the simulated driving test, construct an actual traffic scenario by fusing online map information, and realize the test of the electric drive efficiency of the vehicle on an axle-coupled dynamometer. This can not only improve the accuracy of the test, but also ensure the safety, stability, consistency and repeatability of the test process, and reduce the overall cost.

[0093] It should be noted that the test results of the present invention may include the driving efficiency and feedback efficiency during the actual driving process, without specific limitations.

[0094] In the embodiments of the present invention, building a bench test rig for the electric drive system of an electric vehicle includes: charging the vehicle to be tested to a target power; removing the tires of the vehicle to be tested; installing the vehicle to be tested on an axle-coupled dynamometer through a flange, and at the same time installing the steering tie rod of the vehicle to the vehicle to be tested, and initializing the settings of the axle-coupled dynamometer; arranging sensors and data acquisition devices to synchronously collect the data of the vehicle and the dynamometer.

[0095] It can be understood that the embodiments of the present invention can charge the vehicle to be tested to a target power; remove the tires of the vehicle to be tested; install the vehicle to be tested on an axle-coupled dynamometer through a flange, and at the same time install the steering tie rod of the vehicle to the vehicle to be tested, initialize the settings of the axle-coupled dynamometer, and arrange sensors and data acquisition devices to synchronously collect the data of the vehicle and the dynamometer, so as to do the preparatory work for the preliminary test, reduce various potential safety hazards that may be encountered in the on-road test of the actual vehicle, and ensure the safety, stability, consistency and repeatability of the test process.

[0096] According to the bench test method for an electric vehicle based on an actual traffic scenario proposed by the embodiments of the present invention, construct a road scenario of a target path according to map information, construct a traffic flow scenario of a target path according to map information and driving scenario data, generate an actual traffic scenario of a target path according to the road scenario and the traffic flow scenario, build a bench test rig for the electric drive system of an electric vehicle, control the bench test rig of the electric drive system to conduct a simulated driving test on a target path in an actual traffic scenario, collect the data of the simulated driving test, analyze the test results of the electric vehicle according to the data of the simulated driving test, construct an actual traffic scenario by fusing online map information, and realize the test of the electric drive efficiency of the vehicle on an axle-coupled dynamometer. This can not only improve the accuracy of the test, but also ensure the safety, stability, consistency and repeatability of the test process, and reduce the overall cost.

[0097] The following will be combined with Figure 4 Elaborate in detail on the bench test method for an electric vehicle based on an actual traffic scenario of the present invention, specifically as follows:

[0098] Step 1: Scenario construction.

[0099] Input the starting point, ending point, and waypoints in the online map in the connected module to obtain the driving information of the planned route, and then input the information in the online map into the actual scenario construction module to automatically construct the actual traffic scenario. Automatically obtain the online map information at regular intervals during driving to update the traffic flow scenario, making the constructed scenario highly real-time. The constructed scenario can be stored in the scenario library. Build a simulation model and input the vehicle parameters to make the parameters of the simulation model consistent with those of the test vehicle.

[0100] Step 2: Vehicle preparation.

[0101] Charge the vehicle to an appropriate power level, then remove the tires and install the vehicle on the shaft coupling dynamometer through a flange. At the same time, install the vehicle's steering tie rod to the vehicle. Then input the wheel diameter, rolling resistance coefficient, and test mass on the control interface of the shaft coupling dynamometer. Then perform rolling resistance matching so that the dynamometer can simulate the vehicle driving resistance at any vehicle speed. Arrange sensors such as current and voltage, and data acquisition equipment to synchronously collect vehicle quantity and dynamometer data.

[0102] Step 3: Scenario joint debugging.

[0103] Start the host computer, run the simulation model and the traffic scenario, and at the same time start the dome screen, environmental chamber, shaft coupling dynamometer, and data acquisition system, so that the driver can see the actual traffic scenario on the dome screen and drive normally on the route according to the scenario, and the vehicle driving is coordinated with the scenario.

[0104] Step 4: Test and analysis.

[0105] Conduct the efficiency test of the actual traffic scenario, record the vehicle information and shaft coupling dynamometer information during the test process, and calculate the drive efficiency and feedback efficiency during the actual driving process.

[0106] In summary, the present invention integrates online map information to construct an actual traffic scenario, develops a test device, and realizes the test of the vehicle's electric drive efficiency on the shaft coupling dynamometer, solving the problem of difficult energy flow test in the actual traffic scenario.

[0107] Secondly, a bench test system for an electric vehicle based on an actual traffic scenario according to an embodiment of the present invention is described with reference to the accompanying drawings.

[0108] Figure 5 It is a block diagram of a bench test system for an electric vehicle based on an actual traffic scenario according to an embodiment of the present invention.

[0109] As Figure 5As shown in the figure, the bench test system 10 for electric vehicles based on the actual traffic scenario includes: a data acquisition module 100, a networking module 200, an actual traffic scenario construction module 300, a vehicle simulation model 400, a shaft coupling dynamometer 500, a shaft coupling dynamometer control module 600, a ring screen 700, an environmental chamber 800, and a host computer 900.

[0110] Among them, the data acquisition module 100 is used to synchronously collect the current and voltage signals of the vehicle under test, the vehicle CAN signal, and the shaft coupling dynamometer signal; the networking module 200 is used to obtain the map information and driving scenario data of the target path; the actual traffic scenario construction module 300 communicatively connected to the networking module 200 is used to construct the actual traffic scenario according to the map information and driving scenario data of the target path; the vehicle simulation model 400 communicatively connected to the vehicle under test; the shaft coupling dynamometer 500 is used for vehicle efficiency testing, simulating the target data of the vehicle under test, and feeding the target data back to the shaft coupling dynamometer control module; the shaft coupling dynamometer control module 600 is used to control the shaft coupling dynamometer; the ring screen 700 is used to display the actual traffic scenario to the vehicle under test; the environmental chamber 800 is used to simulate the actual environmental temperature to build the test conditions; the host computer 900 is used to run the networking module to obtain the map information and driving scenario data of the target path, input the map information and driving scenario data of the target path into the actual traffic scenario construction module to construct the actual traffic scenario, and display the actual traffic scenario to the vehicle under test; run the shaft coupling dynamometer control module to control the operation of the shaft coupling dynamometer, input the data collected by the shaft coupling dynamometer into the simulation model, and run the simulation model to obtain the test results.

[0111] Specifically, this system includes a host computer system, which covers a networking module, an actual traffic scenario construction module, a vehicle simulation model, a shaft coupling dynamometer control module, a shaft coupling dynamometer, a ring screen, an environmental chamber, a current sensor, a voltage sensor, and a data acquisition module.

[0112] The host computer system is used to collect and record the data of the data acquisition module, run the shaft coupling dynamometer control module to control the operation of the shaft coupling dynamometer, input the information recorded by the shaft coupling dynamometer into the simulation model, run the simulation model and the actual traffic scenario, run the networking module, and obtain the online map information.

[0113] The networking module is used to obtain the online map information, and through the online map API (Application Programming Interface) interface, obtain the key information of the test path.

[0114] The vehicle simulation model is used to operate in an actual traffic scenario by integrating actual vehicle information. The vehicle model includes a chassis, an electric drive system, a steering system, a tire system, a suspension system, a braking system, a driver model, a thermal management system, an aerodynamic model, etc. Among them, the electric drive system, the steering system, the braking system, and the driver model are added with interfaces for introducing external information, and information such as wheel speed at the wheel ends, steering angle, accelerator pedal, and brake pedal feedback from the whole vehicle is introduced. For other parts, existing base models are used without additional construction.

[0115] The shaft coupling dynamometer control module is used to control the shaft coupling dynamometer, input vehicle parameters and bench parameters, and can collect, record, and forward shaft coupling dynamometer data.

[0116] The shaft coupling dynamometer is used for vehicle efficiency testing, simulating the driving resistance of the whole vehicle, testing vehicle information such as wheel speed and torque at the wheel ends and steering angle, and feeding back the above vehicle information to the shaft coupling dynamometer control module, and then feeding back from the control module to the vehicle simulation model, so that the longitudinal and lateral movements of the vehicle are reflected in the actual traffic scenario.

[0117] The panoramic screen is used to display the actual traffic scenario, and the driver actually operates the longitudinal and lateral movements of the vehicle according to the information in the scenario.

[0118] The environmental chamber is used to simulate the actual environmental temperature.

[0119] Current sensors and voltage sensors are used to test the current and voltage of components such as the electric drive system, power battery, compressor, PTC (Positive Temperature Coefficient) heater, and DCDC of the vehicle's high-voltage components. The data acquisition module is used to synchronously collect current and voltage signals, vehicle CAN signals, and shaft coupling dynamometer signals, and the collected data is used to analyze the energy efficiency of the vehicle in the actual traffic scenario.

[0120] According to the bench test system for electric vehicles based on the actual traffic scenario proposed by the embodiment of the present invention, a road scenario of the target path is constructed according to map information, a traffic flow scenario of the target path is constructed according to map information and driving scenario data, an actual traffic scenario of the target path is generated according to the road scenario and the traffic flow scenario, the electric drive system bench of the electric vehicle is built, the electric drive system bench is controlled to perform simulated driving tests on the target path in the actual traffic scenario, the data of the simulated driving tests is collected, the test results of the electric vehicle are analyzed according to the data of the simulated driving tests, the actual traffic scenario is constructed by integrating online map information, and the vehicle electric drive efficiency test is realized on the shaft coupling dynamometer, which can not only improve the accuracy of the test, but also ensure the safety, stability, consistency, and repeatability of the test process, and reduce the overall cost.

[0121] In the description of this specification, the descriptions with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0122] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "N" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0123] Any process or method description in a flowchart or described in other ways herein can be understood to represent a module, segment, or portion of code including one or N executable instructions for implementing a customized logical function or process, and the scope of the preferred embodiments of the present invention includes additional implementations, where the functions can be executed in a substantially simultaneous manner or in a reverse order according to the involved functions, rather than in the order shown or discussed, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0124] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by a combination of any one or more of the following technologies well known in the art: discrete logic circuits with logic gate circuits for implementing logical functions on data signals, application specific integrated circuits with appropriate combinational logic gate circuits, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

[0125] Those of ordinary skill in the technical field can understand that all or part of the steps carried by the method for implementing the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

Claims

1. An electric vehicle bench test method based on the actual traffic scenario, characterized in that, Including the following steps: Obtain the map information and driving scenario data of the target path; Construct the road scenario of the target path according to the map information, construct the traffic flow scenario of the target path according to the map information and the driving scenario data, and input the road scenario and the traffic flow scenario into the target neural network model. The target neural network model outputs the traffic flow scenario of the target path, where the target neural network model is trained based on a training data set generated from the key factors of the map information and the traffic flow scenario; Build a dynamometer bench for the electric drive system of the electric vehicle, control the dynamometer bench of the electric drive system to perform a simulated driving test on the target path in the actual traffic scenario, collect the data of the simulated driving test, and analyze the test results of the electric vehicle according to the data of the simulated driving test; Before generating the training data set based on the key factors of the map information and the traffic flow scenario, it includes: identifying the historical map information and driving scenario data of the target path; constructing an initial matrix according to the historical map information and driving scenario data, and performing a dimensionless processing on the initial matrix to generate a target matrix; calculating the difference between any two elements according to the target matrix to generate a difference matrix, and identifying the maximum value and the minimum value of the difference matrix; calculating the correlation coefficient between each factor and the traffic volume according to the maximum value and the minimum value, and calculating the grey correlation degree between each factor and the traffic volume according to the correlation coefficient; selecting the factors with a grey correlation degree greater than a preset threshold as the key factors of the map information and the traffic flow scenario.

2. The electric vehicle bench test method based on the actual traffic scenario according to claim 1, wherein The constructing the road scenario of the target path according to the map information includes: Obtain the key road data of the target path in the map information; Construct the road scenario of the target path by using the method of increasing section by section according to the key road data.

3. The electric vehicle bench test method based on the actual traffic scenario according to claim 2, characterized in that, The constructing the road scenario of the target path by using the method of increasing section by section according to the key road data includes: Identify the section distance, road type, weather condition, angle of entering the road, and traffic light position of each section road in the key road data; Query a preset table according to the road type to determine the corresponding number of lanes, road width, and speed limit signs; Determine the friction coefficient of each section road according to the road type and weather condition; Construct a road scenario according to the number of lanes, the road width, the speed limit signs, the friction coefficient, the section distance, the angle of entering the road, and the traffic light position.

4. The electric vehicle bench test method based on the actual traffic scenario according to claim 1, wherein The structure of the target neural network model includes an input layer, an output layer, and a hidden layer. Among them, the number of nodes in the input layer is the number of vehicle parameters, the number of nodes in the output layer is the number of fault indicators, and the number of nodes in the hidden layer is the number of target nodes, where the number of target nodes is obtained by the minimum training times method.

5. The electric vehicle bench test method based on the actual traffic scenario according to claim 1, characterized in that, The training method of the target neural network model includes: Obtain the key factors of the map information and the traffic flow scenario to generate a training data set; among them, use the first activation function as the activation function from the input layer to the hidden layer, and the second activation function as the activation function from the hidden layer to the output layer; Use the training data set to train the neural network model until the neural network model converges to the training target.

6. The electric vehicle bench test method based on the actual traffic scenario according to claim 1, wherein After the target neural network model outputs the traffic flow of the target path, it includes: Identify the traffic volumes of adjacent road sections in the target path; If the difference in the traffic volumes is greater than a preset threshold, start the cut-in and cut-out mechanism.

7. The electric vehicle bench test method based on the actual traffic scenario according to claim 1, characterized in that, The building of the electric drive system bench of the electric vehicle includes: Charge the vehicle under test to the target power; Remove the tires of the vehicle under test; Install the vehicle under test on the shaft coupling dynamometer through a flange, and at the same time install the vehicle's steering tie rod on the vehicle under test; Perform initialization settings on the shaft coupling dynamometer; Arrange sensors and data acquisition devices to synchronously collect vehicle and dynamometer data.

8. An electric vehicle bench test system based on an actual traffic scenario, characterized in that, The system is implemented by applying the electric vehicle bench test method based on the actual traffic scenario described in any one of claims 1-7, wherein the system includes: A data acquisition module for synchronously collecting the current and voltage signals of the vehicle under test, the vehicle CAN signal, and the shaft coupling dynamometer signal; A networking module for obtaining the map information and driving scenario data of the target path; An actual traffic scenario construction module communicatively connected to the networking module for constructing an actual traffic scenario according to the map information and driving scenario data of the target path; A vehicle simulation model communicatively connected to the vehicle under test; A shaft coupling dynamometer for vehicle efficiency testing, simulating the target data of the vehicle under test, and feeding the target data back to the shaft coupling dynamometer control module; A shaft coupling dynamometer control module for controlling the shaft coupling dynamometer; A surround screen for displaying the actual traffic scenario to the vehicle under test; An environmental chamber for simulating the actual environmental temperature to set up the test conditions; A host computer for running the networking module to obtain the map information and driving scenario data of the target path, inputting the map information and the driving scenario data of the target path into the actual traffic scenario construction module to construct an actual traffic scenario, and displaying the actual traffic scenario to the vehicle under test; running the shaft coupling dynamometer control module to control the operation of the shaft coupling dynamometer, inputting the data collected by the shaft coupling dynamometer into the simulation model, and running the simulation model to obtain the test results.

Images