Vehicle sliding resistance determination method and device, and training method of resistance parameter prediction model

Abstract

The present disclosure provides a vehicle sliding resistance determination method, device and training method of resistance parameter prediction model, which can be applied to the technical field of automobile detection. The method comprises: in response to a detection request for detecting sliding resistance of a target vehicle, determining attribute information of the target vehicle, vehicle driving information and current mass of the vehicle; in the case that the target vehicle meets a preset condition based on the attribute information and the current mass of the vehicle, inputting the attribute information into a trained resistance parameter prediction model to obtain a resistance parameter; based on the resistance parameter, obtaining a correlation between the sliding resistance and the driving speed, wherein the correlation corresponds to a target vehicle with a target mass value; based on the correlation and the attribute information, determining a target resistance determination function corresponding to the target vehicle; inputting the vehicle driving information and the current mass of the vehicle into the target resistance determination function to obtain a sliding resistance value of the target vehicle.

Description

Technical Field

[0001] This disclosure relates to the field of automotive testing technology, and in particular to a method, device, and training method for a resistance parameter prediction model for determining vehicle sliding resistance. Background Technology

[0002] Currently, the primary method for determining a vehicle's actual road resistance is the coasting test method. This involves conducting a coasting test on the vehicle under conditions specified in national standards to obtain the resistance value during coasting. While the coasting test method can obtain the resistance value of a target vehicle relatively accurately, it is subject to stringent environmental conditions and only provides the coasting resistance value under the specific test mass conditions. When the vehicle's mass changes, the resistance also changes accordingly, requiring a re-test to determine the coasting resistance value under that mass.

[0003] In realizing the concept disclosed herein, the inventors discovered at least the following problems in the related technologies: obtaining the gliding resistance value of a vehicle using the related technologies is inefficient and costly. Summary of the Invention

[0004] In view of the above problems, this disclosure provides a method, apparatus, device, medium and procedure for determining vehicle gliding resistance.

[0005] According to one aspect of this disclosure, a method for determining vehicle coasting resistance is provided, comprising: responding to a detection request for detecting the coasting resistance of a target vehicle, determining attribute information, vehicle driving information, and the current mass of the target vehicle; if, based on the attribute information and the current mass of the vehicle, it is determined that the target vehicle meets preset conditions, inputting the attribute information into a trained resistance parameter prediction model to obtain resistance parameters, wherein the resistance parameter prediction model is used to predict resistance parameters corresponding to a target vehicle with a target mass of a target value; based on the resistance parameters, obtaining a correlation between coasting resistance and driving speed, wherein the correlation corresponds to a target vehicle with a target mass of a target value; based on the correlation and attribute information, determining a target resistance determination function corresponding to the target vehicle; and inputting the vehicle driving information and the current mass of the vehicle into the target resistance determination function to obtain the coasting resistance value of the target vehicle.

[0006] According to another aspect of this disclosure, a training method for a drag parameter prediction model is provided, comprising: inputting sample data into the drag parameter prediction model to obtain test drag parameters, wherein the sample data is obtained with the vehicle mass as the target value; obtaining a loss value based on the test drag parameters and the real drag parameters corresponding to the sample data; and adjusting the hyperparameters in the drag parameter prediction model based on the loss value to obtain a trained drag parameter prediction model, wherein the trained drag parameter prediction model is used in the above method.

[0007] Another aspect of this disclosure provides a device for determining vehicle gliding resistance, comprising: an acquisition module, configured to determine attribute information, vehicle driving information, and current vehicle mass of the target vehicle in response to a detection request for detecting the gliding resistance of a target vehicle; a parameter determination module, configured to input the attribute information into a trained resistance parameter prediction model to obtain resistance parameters when the target vehicle meets preset conditions, wherein the resistance parameter prediction model is used to predict the resistance parameters corresponding to the target vehicle with a target vehicle mass of a target value; a relationship determination module, configured to obtain the correlation between gliding resistance and driving speed based on the resistance parameters, wherein the correlation corresponds to the target vehicle with a target vehicle mass of a target value; a function determination module, configured to determine a target resistance determination function corresponding to the target vehicle based on the correlation and attribute information; and a resistance determination module, configured to input the vehicle driving information and current vehicle mass into the target resistance determination function to obtain the gliding resistance value of the target vehicle.

[0008] According to another aspect of this disclosure, a training apparatus for a drag parameter prediction model is provided, comprising: an input module for inputting sample data into the drag parameter prediction model to obtain test drag parameters, wherein the sample data is obtained with the vehicle mass as a target value; a loss value determination module for obtaining a loss value based on the test drag parameters and the actual drag parameters corresponding to the sample data; and an adjustment module for adjusting the hyperparameters in the drag parameter prediction model based on the loss value to obtain a trained drag parameter prediction model, wherein the trained drag parameter prediction model is used in the above method.

[0009] Another aspect of this disclosure provides an electronic device, including: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to perform the above-described method for determining vehicle gliding resistance and the method for training a resistance parameter prediction model.

[0010] Another aspect of this disclosure provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the aforementioned method for determining vehicle gliding resistance and the method for training a resistance parameter prediction model.

[0011] Another aspect of this disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method for determining vehicle gliding resistance and the method for training a resistance parameter prediction model.

[0012] According to the method for determining vehicle coasting resistance provided in this disclosure, by acquiring the attribute information and current mass of the target vehicle, it can be determined whether the target vehicle meets preset conditions. If the target vehicle meets the preset conditions, the attribute information is input into a trained resistance parameter prediction model to obtain resistance parameters. Based on these resistance parameters, a correlation between the coasting resistance and speed of the target vehicle at a target mass is obtained. Based on this correlation and the attribute information, a target resistance determination function corresponding to the target vehicle can be determined. By inputting the vehicle's driving information and current mass into this target resistance determination function, the coasting resistance value of the target vehicle at its current mass can be obtained. Since the resistance parameters at a target mass are obtained through the resistance parameter prediction model, a correlation between the coasting resistance and speed at a target mass is obtained. Based on this correlation and attribute information, a target resistance determination function applicable to any mass is determined, thereby obtaining the coasting resistance value of the target vehicle at its current mass. Therefore, this method at least partially solves the problems of low efficiency and high cost in related technologies, achieving the technical effect of reducing experimental costs and time, and improving the efficiency of coasting resistance calculation. Attached Figure Description

[0013] The foregoing contents, as well as other objects, features, and advantages of this disclosure, will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0014] Figure 1 The illustration schematically shows an application scenario of the method for determining vehicle skidding resistance and the training method for a resistance parameter prediction model according to embodiments of the present disclosure.

[0015] Figure 2 A flowchart illustrating a method for determining vehicle coasting resistance according to an embodiment of the present disclosure is shown schematically.

[0016] Figure 3 A flowchart illustrating a method for training a drag parameter prediction model according to an embodiment of the present disclosure is shown schematically.

[0017] Figure 4 This diagram illustrates a training set fitting error of a drag parameter prediction model according to an embodiment of the present disclosure.

[0018] Figure 5This diagram illustrates a test set fitting error of a drag parameter prediction model according to an embodiment of the present disclosure.

[0019] Figure 6(a) schematically illustrates a method for determining vehicle coasting resistance when the vehicle is fully loaded according to an embodiment of the present disclosure and a comparison of the results of coasting tests;

[0020] Figure 6(b) schematically illustrates a method for determining vehicle coasting resistance under 80% load according to an embodiment of the present disclosure and a comparison of the results of coasting tests;

[0021] Figure 6(c) schematically illustrates a method for determining vehicle coasting resistance under 60% load according to an embodiment of the present disclosure and a comparison of the results of coasting tests;

[0022] Figure 6(d) schematically illustrates a method for determining vehicle skidding resistance under 40% load according to an embodiment of the present disclosure and a comparison of the results of skidding tests;

[0023] Figure 6(e) schematically illustrates a method for determining vehicle coasting resistance under 20% load according to an embodiment of the present disclosure and a comparison of the results of coasting tests;

[0024] Figure 6(f) schematically illustrates a method for determining vehicle coasting resistance at 0% load according to an embodiment of the present disclosure and a comparison of the results of coasting tests;

[0025] Figure 7 The diagram illustrates a data flow graph of a method for determining vehicle coasting resistance according to an embodiment of the present disclosure.

[0026] Figure 8 The diagram schematically illustrates a data flow diagram of another method for determining vehicle coasting resistance according to an embodiment of the present disclosure.

[0027] Figure 9 A schematic block diagram of a device for determining vehicle slip resistance according to an embodiment of the present disclosure is shown.

[0028] Figure 10 A schematic diagram illustrating the structure of a training apparatus for a drag parameter prediction model according to an embodiment of the present disclosure; and

[0029] Figure 11 A block diagram of an electronic device suitable for implementing a method for determining vehicle coasting resistance and a method for training a resistance parameter prediction model, according to an embodiment of the present disclosure, is shown schematically. Detailed Implementation

[0030] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0031] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0032] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0033] When using expressions such as "at least one of A, B, and C", they should generally be interpreted in accordance with the meaning that is commonly understood by a person skilled in the art (e.g., "a system having at least one of A, B, and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B, and C, etc.).

[0034] During the research process, the inventors discovered that there are currently two methods for determining the actual road driving resistance of vehicles in my country's national standards. One method is the coasting test method, which involves conducting a coasting test on the target vehicle under conditions specified in the national standards, measuring the time Δt taken for the vehicle to gradually coast from high speed to low speed in each speed range ΔV, and then applying the formula F... 阻力 The resistance value of the vehicle during coasting can be calculated by using m·ΔV / Δt.

[0035] The second method is the national standard recommended value method. Recommended values ​​are derived from experimental experience. After determining the vehicle type and the test quality, the resistance parameters of the target vehicle's coasting resistance curve are obtained by consulting a recommended value table, and the coasting resistance value is calculated based on these parameters. However, national standard recommended values ​​generally differ significantly from actual values; therefore, the coasting test method is often used to obtain the vehicle's coasting resistance value.

[0036] The coasting test method can obtain the coasting resistance value of a target vehicle relatively accurately, but it has significant limitations. The coasting test has stringent environmental requirements, is time-consuming and labor-intensive, and can only obtain the coasting resistance value under the test mass conditions at that time. When the vehicle mass changes, the vehicle resistance also changes accordingly, so it is necessary to repeat the coasting test to determine the coasting resistance value under that mass. This method is inefficient and costly.

[0037] With the development of artificial intelligence and machine learning, various algorithms have emerged. Now, machines can learn and train on a large amount of coasting test data to grasp its internal rules. Algorithms can then be used to predict vehicle resistance, thus obtaining the vehicle's coasting resistance relatively accurately without having to conduct coasting tests on the target vehicle.

[0038] However, machine learning also has limitations. It requires high-quality datasets. When conducting coasting tests, most companies test vehicles under full load, rarely testing them under other loads such as no load or half load. In such cases, machine learning can only predict the coasting resistance of heavy vehicles under full load by learning from the dataset. If we want to obtain the resistance under other loads, such as no load, half load, or resistance beyond the range of test quality in the dataset, machine learning predictions will be very inaccurate.

[0039] Figure 1 The illustration schematically depicts an application scenario of the method for determining vehicle gliding resistance and the training method for a resistance parameter prediction model according to embodiments of the present disclosure.

[0040] like Figure 1 As shown, application scenario 100 according to this embodiment may include terminal devices 101, 102, and 103, network 104, and server 105. Network 104 is used as a medium to provide a communication link between terminal devices 101, 102, and 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables, etc.

[0041] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0042] Terminal devices 101, 102, and 103 can be various electronic devices with displays and web browsing capabilities, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0043] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using terminal devices 101, 102, and 103 (for example only). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0044] It should be noted that the method for determining vehicle coasting resistance and the training method for the resistance parameter prediction model provided in this embodiment can generally be executed by server 105. Correspondingly, the device for determining vehicle coasting resistance and the device for training the resistance parameter prediction model provided in this embodiment can generally be located in server 105. The method for determining vehicle coasting resistance and the training method for the resistance parameter prediction model provided in this embodiment can also be executed by a server or server cluster that is different from server 105 and can communicate with terminal devices 101, 102, 103 and / or server 105. Correspondingly, the device for determining vehicle coasting resistance and the device for training the resistance parameter prediction model provided in this embodiment can also be located in a server or server cluster that is different from server 105 and can communicate with terminal devices 101, 102, 103 and / or server 105.

[0045] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0046] The following will be based on Figure 1 The described scene, through Figures 2-8 The method for determining vehicle gliding resistance according to the disclosed embodiments is described in detail.

[0047] Figure 2 A flowchart illustrating a method for determining vehicle gliding resistance according to an embodiment of the present disclosure is shown schematically.

[0048] like Figure 2 As shown, the method includes operations S210 to S250.

[0049] In operation S210, in response to a detection request for detecting the sliding resistance of the target vehicle, the target vehicle's attribute information, vehicle driving information, and current vehicle mass are determined.

[0050] In operation S220, based on attribute information and the current mass of the vehicle, if the target vehicle meets the preset conditions, the attribute information is input into the trained drag parameter prediction model to obtain the drag parameters. The drag parameter prediction model is used to predict the drag parameters corresponding to the target vehicle with the target mass.

[0051] In operation S230, based on the resistance parameters, the correlation between gliding resistance and driving speed is obtained, where the correlation corresponds to the target vehicle with the vehicle mass as the target value.

[0052] In operation S240, based on the correlation and attribute information, the target resistance determination function corresponding to the target vehicle is determined.

[0053] In operation S250, the vehicle driving information and the current mass of the vehicle are input into the target resistance determination function to obtain the sliding resistance value of the target vehicle.

[0054] According to embodiments of this disclosure, a detection request for detecting the gliding resistance of a target vehicle can be sent by any server to a server or client capable of executing a method for determining the gliding resistance of a vehicle.

[0055] According to embodiments of this disclosure, the attribute information may include vehicle attributes or environmental attributes. Vehicle attributes may include: vehicle test mass, frontal area value, number of tires, tire pressure value, etc. Environmental attributes may include temperature value, pressure value, humidity value, etc. The vehicle test mass may be the mass of the vehicle when the target value is achieved.

[0056] According to embodiments of this disclosure, the mass of a vehicle is the sum of the vehicle's own mass and the load mass, where the load mass is the mass of the vehicle's load, and the vehicle mass can be characterized as a percentage of the vehicle's load.

[0057] According to embodiments of this disclosure, the target value is not limited and can be the mass of the vehicle when fully loaded or the mass of the vehicle with any load.

[0058] According to embodiments of this disclosure, the current mass of the vehicle can be the sum of the vehicle's own mass and the vehicle's current load mass. The current mass of the vehicle can be any value, and it can be equal to or not equal to the target value.

[0059] According to embodiments of this disclosure, vehicle attributes can be determined from a detection request or from a database based on the vehicle's identifier.

[0060] According to embodiments of this disclosure, vehicle driving information may include the vehicle's current speed and air density.

[0061] According to embodiments of this disclosure, vehicle driving information and the current vehicle mass can be determined from a detection request.

[0062] According to embodiments of this disclosure, the drag parameters of a target vehicle with a target mass can also be obtained by conducting a coasting test on the target vehicle with a target mass.

[0063] According to the embodiments of this disclosure, the implementation method of the resistance parameter prediction model is not limited. It can be a generalized regression neural network (GRNN) or other neural networks, such as recurrent neural networks (RNN), convolutional neural networks (CNN), etc.

[0064] According to embodiments of this disclosure, when using GRNN, a Genetic Algorithms-Generalized Regression Neural Network (GA-GRNN) optimized based on genetic algorithms can be employed.

[0065] According to embodiments of this disclosure, the GRNN neural network can achieve good prediction accuracy even with a small number of samples; and the GRNN neural network is suitable for nonlinear fitting, which is the fitting of the gliding drag curve; moreover, the smoothing factor is a hyperparameter of the GRNN neural network model, and the value of the smoothing factor has a significant impact on the prediction accuracy. By using a genetic algorithm (GA) to optimize the smoothing factor, the prediction accuracy can be optimized, thereby obtaining more accurate drag parameters.

[0066] According to embodiments of this disclosure, the resistance parameters are those required to calculate the vehicle's coasting resistance.

[0067] According to embodiments of this disclosure, by performing target calculations on the correlation between gliding resistance and driving speed and the frontal area, temperature, and pressure values ​​in the attribute information, a target resistance determination function can be obtained to determine the current gliding resistance of the target vehicle.

[0068] According to embodiments of this disclosure, the sliding resistance value corresponding to the vehicle's current mass can be determined by inputting vehicle driving information and the vehicle's current mass into a target resistance determination function.

[0069] According to embodiments of this disclosure, by keeping the vehicle's current mass and air density constant while continuously changing the vehicle's speed, the correlation between the sliding resistance corresponding to the vehicle's current mass and the driving speed can be obtained.

[0070] According to embodiments of this disclosure, similarly, the sliding resistance value of a target vehicle under any conditions can be determined by inputting arbitrary vehicle mass and arbitrary vehicle driving information into the target resistance determination function.

[0071] According to embodiments of this disclosure, obtaining the correlation between gliding resistance and driving speed based on resistance parameters may include the following operations.

[0072] Based on the resistance parameters and multiple preset driving speeds, the gliding resistance corresponding to the multiple preset driving speeds is obtained; based on the gliding resistance corresponding to the multiple preset driving speeds and the multiple preset driving speeds, the correlation between gliding resistance and driving speed is obtained.

[0073] According to embodiments of this disclosure, the preset driving speed is not limited; it can be data pre-stored in the database or data randomly generated based on a random function.

[0074] According to the embodiments of this disclosure, the sliding resistance corresponding to the multiple preset driving speeds can be obtained by performing calculations based on the resistance parameters and multiple preset driving speeds as shown in the following formula (2). By establishing a correlation between the multiple sliding resistances and the multiple preset driving speeds, the correlation between the sliding resistance and the driving speed can be obtained.

[0075] F = A·V 2 +B·V+C;(2)

[0076] Where F is the vehicle's sliding resistance, V is the vehicle's speed, and A, B, and C are resistance parameters.

[0077] According to embodiments of this disclosure, the relationship between gliding resistance and driving speed can be represented by tables, graphs, or other means.

[0078] According to embodiments of this disclosure, since the drag parameter prediction model is used to predict the drag parameters corresponding to a target vehicle with a target vehicle mass, the obtained correlation between gliding resistance and driving speed is also for the case where the vehicle mass is the target value.

[0079] According to embodiments of this disclosure, the preset conditions include: a first sub-preset condition and a second sub-preset condition, wherein the first sub-preset condition includes: there is no target resistance determination function corresponding to the target vehicle in the database; the second sub-preset condition includes: the current mass of the vehicle is not equal to the target value.

[0080] According to embodiments of this disclosure, the following operations may be included.

[0081] Based on attribute information, determine whether the target vehicle meets the first sub-preset condition; if the target vehicle does not meet the first sub-preset condition, compare the current mass of the vehicle with the target value to determine whether the target vehicle meets the second sub-preset condition; if the target vehicle meets both the first and second sub-preset conditions, determine that the target vehicle meets the preset conditions.

[0082] According to embodiments of this disclosure, vehicle data such as the frontal area and number of tires of a target vehicle can be determined from attribute information, thereby determining the type of the target vehicle, and then determining whether a target resistance determination function corresponding to the target vehicle exists in the database based on the type of the target vehicle.

[0083] According to embodiments of this disclosure, the type of the target vehicle can also be determined directly from the detection request.

[0084] According to embodiments of this disclosure, when it is determined that the target vehicle meets the first sub-preset condition, a target resistance determination function corresponding to the target vehicle can be determined from the database based on the type of the target vehicle, and the vehicle driving information can be input into the target resistance determination function to obtain the sliding resistance value of the target vehicle.

[0085] According to embodiments of this disclosure, the current mass of the vehicle is compared with a target value to determine whether the target vehicle meets a second sub-preset condition. If the current mass of the vehicle is equal to the target value, it is determined that the target vehicle does not meet the second sub-preset condition.

[0086] According to an embodiment of this disclosure, if the target vehicle does not meet the second sub-preset condition, the vehicle attribute information is input into the resistance parameter prediction model to obtain the resistance parameter, and based on the resistance parameter, the sliding resistance value for the target vehicle is obtained.

[0087] According to embodiments of this disclosure, determining whether the target vehicle meets preset conditions first can improve the efficiency of calculating the sliding resistance for target vehicles that have a target resistance determination function or can directly calculate the resistance value using a resistance parameter prediction model.

[0088] According to embodiments of this disclosure, determining the target resistance determination function corresponding to the target vehicle based on association and attribute information may include the following operations.

[0089] Based on the correlation and multiple preset speed ranges, the driving time for each preset speed range is obtained; based on the driving time, attribute information, and preset road resistance coefficient for each preset speed range, the initial resistance determination function corresponding to each preset speed range is obtained; based on the initial resistance determination function corresponding to each preset speed range and the target kinetic energy value corresponding to each preset speed range, the coefficient value of the road resistance coefficient for the target vehicle is determined; based on the coefficient value, the target resistance determination function corresponding to the target vehicle is determined.

[0090] According to the embodiments of this disclosure, the driving time of each of the multiple preset speed ranges can be obtained through the correlation relationship and multiple preset speed ranges, as shown in the following formula (3).

[0091] F = m·a = m·ΔV / Δt; (3)

[0092] Where m is the vehicle mass, which is the target value here, a is the acceleration corresponding to the preset speed range, ΔV is the difference between the boundary values ​​of the preset speed range, Δt is the travel time, and F is the vehicle mass and the vehicle's sliding resistance.

[0093] According to the embodiments of this disclosure, by processing the driving time of each of the multiple preset speed ranges, the windward area value, temperature value, pressure value, preset road resistance coefficient, preset speed range, target value, and other parameters in the attribute information, a target resistance determination function corresponding to each of the multiple preset speed ranges can be obtained.

[0094] According to embodiments of this disclosure, target kinetic energy values ​​corresponding to multiple preset speed ranges can be obtained based on the boundary values ​​of the target value and the preset speed range.

[0095] According to the embodiments of this disclosure, the coefficient value of the road resistance coefficient for the target vehicle is determined based on the initial resistance determination function corresponding to each of the multiple preset speed ranges and the target kinetic energy value corresponding to each of the multiple preset speed ranges, as shown in the following formula (4).

[0096]

[0097] According to embodiments of this disclosure, The formula is used to determine the target kinetic energy value corresponding to a preset speed range; Formula for determining the function of initial resistance.

[0098] Where m represents the vehicle mass, which is the target value here; V1 and V2 represent the maximum and minimum boundary speed values ​​in the speed range; S≈V3·t1, where S is the distance traveled by the vehicle as it coasts from speed V1 to speed V2; and V3=(V1+V2) / 2.

[0099] According to embodiments of this disclosure, since in addition to the preset road resistance coefficient, i.e., C′ d f′ co1 f co2 Any coefficient other than e can be obtained by acquisition or calculation. Therefore, by determining the initial resistance determination function and the target kinetic energy value for each of the multiple preset speed ranges, a set of equations with multiple equations is obtained. Solving the set of equations yields the coefficient value of the road resistance coefficient for the target vehicle.

[0100] According to embodiments of this disclosure, since the target kinetic energy value is used in determining the target resistance determination function, the process of determining the target resistance determination function corresponding to the target vehicle based on the correlation and attribute information, and inputting the vehicle driving information and the current mass of the vehicle into the target resistance determination function to obtain the sliding resistance value of the target vehicle can also be referred to as employing the sliding kinetic energy method.

[0101] According to the embodiments of this disclosure, since the target kinetic energy value corresponding to the preset speed range is equivalent to the vehicle's sliding resistance and the distance traveled in the preset speed range, the following formula (5) can be determined.

[0102]

[0103] Where F represents the vehicle's sliding resistance.

[0104] According to an embodiment of this disclosure, when the coefficient value of the road resistance coefficient for the target vehicle is obtained, a function of F can be obtained, namely the target resistance determination function, specifically, the target resistance determination function is shown in the following formula (1).

[0105]

[0106] Where F is the gliding resistance, A is the frontal area, ρ is the air density, V is the vehicle speed, and C' is the gliding resistance. d C d +d, C d Where is the air drag coefficient, d is a constant, and f′ is the air drag coefficient. co1 f co1 +b, f co1 Here, b is the first rolling resistance coefficient, and f is a constant. co2 is the second rolling resistance coefficient, m is the vehicle mass (target value), g is the gravitational acceleration, and e is a constant.

[0107] According to embodiments of this disclosure, the gliding resistance value of a vehicle can be determined based on the following resistances: since the main forces a vehicle experiences during gliding include air resistance, rolling resistance, and other resistances, the gliding resistance of the vehicle during gliding can be determined based on air resistance, rolling resistance, and other resistances.

[0108] According to embodiments of this disclosure, the formulas for air resistance, rolling resistance, and other resistances are as shown in the following formulas (6) to (9).

[0109]

[0110] F 滚动 =(f co1 +f co2 ·V)·mg; (7)

[0111] Among them, F 空气 For air resistance, F 滚动 This represents rolling resistance.

[0112] According to embodiments of this disclosure, since the gliding resistance changes when the vehicle's mass changes, other resistances also change. Therefore, the change in other resistances is linked to the change in mass. The greater the mass during gliding, the greater the other resistances will be, as shown in formula (8).

[0113] F 其他1 = a + b·mg; (8)

[0114] According to the embodiments of this disclosure, since the gliding resistance of the vehicle also changes when the speed changes, the change of other resistances is linked to the speed. The greater the speed when the vehicle is gliding, the greater the other resistances are. Assuming that the other resistances are in a quadratic function relationship with the speed, the other resistances are obtained as shown in formula (9).

[0115] F 其他2 = b·mg + d·V 2 +e;(9)

[0116] According to an embodiment of this disclosure, based on formula (10), a target resistance determination function with unknown road resistance coefficient values ​​can be obtained.

[0117] F = F 空气 +F 滚动 +F 其他1 +F 其他2 (10)

[0118] According to embodiments of this disclosure, the sliding resistance value under the current vehicle mass can be obtained by inputting the air density, the current vehicle speed, and the current vehicle mass into the target resistance determination function.

[0119] According to embodiments of this disclosure, by employing a drag parameter prediction model to obtain drag parameters and determining a target drag determination function based on the drag parameters and attribute information, the vehicle's coasting resistance under arbitrary mass can be obtained. This allows the vehicle to obtain its coasting resistance value under arbitrary load without conducting coasting tests, saving test costs and time and improving work efficiency. At the same time, it solves the shortcomings of drag parameter prediction models, which can only predict the resistance within the test mass range of the dataset, and also overcomes the dependence of the coasting kinetic energy method on coasting test data.

[0120] According to embodiments of this disclosure, the preset speed range includes boundary speed values; the coefficient value of the road resistance coefficient for the target vehicle is determined based on the initial resistance determination function corresponding to each of the multiple preset speed ranges and the target kinetic energy value corresponding to each of the multiple preset speed ranges, which may include the following operations.

[0121] Based on the boundary speed values ​​and target values ​​of multiple preset speed ranges, the target kinetic energy values ​​corresponding to each preset speed range are determined; based on the target kinetic energy values ​​corresponding to each preset speed range and the initial resistance determination function corresponding to each preset speed range, a set of coefficient solving equations is obtained; the set of coefficient solving equations is solved to obtain the coefficient values ​​of the road resistance coefficient.

[0122] According to embodiments of this disclosure, the boundary speed values ​​of the preset speed range include a minimum boundary speed value and a maximum boundary speed value, and the preset speed range represents the vehicle gradually gliding from the maximum boundary speed value to the minimum boundary speed value.

[0123] According to the embodiments of this disclosure, the number of preset speed intervals is the same as the number of equations in the system of equations. Each preset speed interval corresponds to one equation. Based on formula (4), it can be known that there are 4 preset road resistance coefficients. Under normal circumstances, only 4 equations are needed to obtain the coefficient value. However, in order to improve the accuracy of the coefficient value, n preset speed intervals can be used to obtain n road resistance coefficients. By using the system of equations including n equations to approximate the coefficient value, the optimization processing of the solution value can be realized, thereby obtaining the coefficient value with the smallest error.

[0124] According to the embodiments of this disclosure, the target kinetic energy value corresponding to multiple preset speed ranges and the initial resistance determination function corresponding to each of the multiple preset speed ranges can be calculated by using the calculation formula as shown in formula (4), thereby accurately and quickly obtaining the coefficient value of the road resistance coefficient for the target vehicle.

[0125] According to embodiments of this disclosure, the attribute information includes windward area value, temperature value, and pressure value; based on the driving time, attribute information, and preset road resistance coefficient of each of the multiple preset speed ranges, an initial resistance determination function corresponding to each of the multiple preset speed ranges is obtained, which may include the following operations.

[0126] Based on the boundary speed values ​​and travel time of each of the multiple preset speed ranges, the travel distance of each of the multiple preset speed ranges is determined; the air density is determined based on the temperature and pressure values; and the initial resistance determination function corresponding to each of the multiple preset speed ranges is obtained based on the air density, the frontal area, the travel distance of each of the multiple preset speed ranges, and the preset road resistance coefficient.

[0127] According to embodiments of this disclosure, the intermediate speed value in a preset speed range can be determined by dividing the sum of the minimum and maximum boundary speed values ​​by 2, and then the travel distance value corresponding to the preset speed range can be obtained by multiplying the intermediate speed value by the travel time.

[0128] According to the embodiments of this disclosure, the initial resistance determination function is obtained by calculating the air density, windward area value, travel distance value of each of the multiple preset speed ranges, preset road resistance coefficient, target value, and multiple intermediate speed values ​​as shown in formula (4).

[0129] According to embodiments of this disclosure, the error value of the target resistance determination function can be determined by the following formula (11), thereby determining whether the coefficient value of the road resistance coefficient for the target vehicle is accurate and whether the resistance parameter prediction model is accurate based on the error value.

[0130]

[0131] Among them, A, B, and C are resistance parameters obtained through gliding tests or determined by resistance parameter prediction models.

[0132] According to an embodiment of this disclosure, specifically, the sliding resistance value corresponding to vehicle speeds of 10, 20, 30, 40, 50, 60, 70, 80 km / h can be obtained by inputting the coefficient value into formula (11). Then, the sliding resistance value is subtracted from the sliding resistance value calculated by the corresponding resistance parameter obtained through sliding experiment or resistance parameter prediction model to obtain the error value.

[0133] According to embodiments of this disclosure, when the error value is less than a preset error value, an alarm message can be sent to provide an early warning of the accuracy of the coefficient value and resistance parameter prediction model, so as to carry out subsequent inspection work.

[0134] Figure 3A flowchart illustrating a training method for a drag parameter prediction model according to an embodiment of the present disclosure is shown.

[0135] like Figure 3 As shown, the method includes operations S310 to S330.

[0136] In operation S310, the sample data is input into the resistance parameter prediction model to obtain the test resistance parameters. The sample data is obtained with the vehicle mass as the target value.

[0137] When operating the S320, the loss value is obtained based on the test resistance parameters and the actual resistance parameters corresponding to the sample data.

[0138] In operation S330, based on the loss value, the hyperparameters in the resistance parameter prediction model are adjusted to obtain a trained resistance parameter prediction model, which is used in the above method.

[0139] According to embodiments of this disclosure, the sample data can be obtained by conducting a sufficient number of coasting tests on a vehicle, such as a heavy vehicle, under the condition of meeting the national standard coasting test requirements, to obtain historical coasting test data, and then filtering and classifying the data obtained from the historical coasting test data.

[0140] According to embodiments of this disclosure, training a drag parameter prediction model using only sample data with vehicle mass as the target value can reduce the difficulty and cost of obtaining sample data.

[0141] According to embodiments of this disclosure, a drag parameter prediction model is trained using sample data of different types of vehicles. Different drag parameter prediction models are also trained for different types of vehicles. For example, heavy vehicles such as vans, stake vans, dump trucks, buses, and semi-trailer tractors use separate drag parameter prediction models for training and prediction.

[0142] According to embodiments of this disclosure, for vehicles belonging to the same major category but different subcategories, such as types N1, N2, and N3, the drag parameter prediction model is also used separately for learning, training, and prediction.

[0143] According to the embodiments of this disclosure, the selection of input parameters in the sample data of the drag parameter prediction model is crucial. The selection of input parameters directly affects the prediction effect of the drag parameter prediction model. As many major influencing factors affecting drag as possible should be taken into account as input parameters of the drag parameter prediction model, such as: vehicle test mass, frontal area value, number of tires, tire pressure value, temperature value, pressure value, and humidity value.

[0144] According to embodiments of this disclosure, vehicle test mass, number of tires, tire pressure, and temperature primarily affect the vehicle's rolling resistance, while frontal area, pressure, and humidity primarily affect its air resistance. Other factors, such as wind speed, can significantly impact air resistance; however, in coasting tests, the wind speed requirement is an average wind speed <3 m / s and gusts <5 m / s measured at a height of 1.6 m above the road surface. Both forward and reverse coasting are performed on a single road, thus eliminating the influence of wind speed and minor road gradients. Air density also affects air resistance, but by using temperature and pressure as input parameters, air density is indirectly determined. Since the vehicle is in neutral during coasting and the engine is not engaged, engine-related resistance can be ignored.

[0145] According to the embodiments of this disclosure, the output parameters of the resistance parameter prediction model are selected as the resistance quadratic term coefficient A, resistance linear term coefficient B, and resistance constant term coefficient C in formula (2), which are obtained by calculation and fitting through gliding tests.

[0146] According to embodiments of this disclosure, a large amount of sample data can be used as the model's dataset. Then, the dataset is divided into a training set and a test set. 80% of the dataset can be used as the model's training set, and 20% of the dataset can be used as the model's test set. Then, data normalization is performed, a resistance parameter prediction model is constructed, and then data inverse normalization is performed. Finally, the fitting error of the training set and the prediction error of the test set are output.

[0147] According to embodiments of this disclosure, the smaller the fitting error value of the training set, the better the learning effect of the neural network model on the dataset, and consequently, the smaller the prediction error value of the test set. Therefore, in one implementation, the fitting error value of the training set and the prediction error value of the test set can both be defined as: the difference between the resistance values ​​corresponding to the quadratic function formed by the coefficients A, B, and C of the quadratic term of resistance in historical coasting test data and the quadratic function formed by the resistance parameters obtained from the resistance parameter prediction model at multiple vehicle speeds such as 10, 20, 30, 40, 50, 60, 70, and 80 km / h, respectively, after taking the absolute values ​​of the obtained values, and averaging them. Specifically, the formula for calculating the error value E can be as follows.

[0148]

[0149] Where A1, B1, and C1 represent the quadratic coefficient, linear coefficient, and constant coefficient of the quadratic function value of the gliding test, respectively; and A2, B2, and C2 represent the quadratic coefficient, linear coefficient, and constant coefficient of the quadratic function value of the resistance parameter predicted by the resistance parameter prediction model, respectively.

[0150] According to embodiments of this disclosure, the error value E can be used as the loss value of the resistance parameter prediction model to adjust the parameters of the resistance parameter prediction model.

[0151] According to embodiments of this disclosure, the error threshold is not limited, and different error thresholds can be set according to actual conditions. For example, the error threshold is defined as 0.16.

[0152] According to embodiments of this disclosure, the percentage of errors E calculated from all sample data in the training set and test set that are less than 0.16 can be statistically determined. If the percentage is greater than 85%, then the training set data is considered to have good training effect, and the test set prediction effect is also good. The model can be used to predict the resistance parameters of a vehicle.

[0153] According to an embodiment of this disclosure, in one implementation, an N3 type semi-trailer tractor was selected as the object of the resistance parameter prediction model. A dataset was constructed based on historical skidding test data of the N3 semi-trailer tractor, and a total of 685 data points were collected. 660 data points were selected as training set samples for the resistance parameter prediction model, and the remaining 25 data points were selected as test set samples for the resistance parameter prediction model.

[0154] Figure 4 The diagram illustrates a training set fitting error of a drag parameter prediction model according to an embodiment of the present disclosure.

[0155] like Figure 4 As shown, if the fitting error of the training set is defined as 0.16, after the resistance parameter prediction model learns, the proportion of training set fitting errors below 0.16 is 86.2%. If the fitting error of the training set is defined as 0.2, then the proportion can reach 93%. Figure 4 As shown.

[0156] Figure 5 The diagram illustrates a test set fitting error of a drag parameter prediction model according to an embodiment of the present disclosure.

[0157] like Figure 5 As shown, the prediction error of the 25 test set samples is relatively small, which indicates that the prediction effect of the resistance parameter prediction model is quite good.

[0158] According to embodiments of this disclosure, for a heavy-duty N3 semi-trailer tractor with a target mass, such as a fully loaded vehicle, its test mass, frontal area, number of tires, tire pressure, temperature, pressure, and humidity can be input. Through a trained resistance parameter prediction model, the resistance parameters of the vehicle can be predicted, and the correlation between the sliding resistance and the driving speed can be obtained based on the resistance parameters. Then, based on the correlation, the driving time required for the vehicle in each speed range can be calculated, resulting in a speed-time graph or table (VT), as shown in Table 1.

[0159] Table 1

[0160]

[0161]

[0162] According to embodiments of this disclosure, based on Table 1, the time taken is 21.605625s in the speed range from 75km / h to 65km / h; 24.8425s in the speed range from 65km / h to 55km / h; 29.111875s in the speed range from 55km / h to 45km / h; 32.885s in the speed range from 45km / h to 35km / h; 37.26625s in the speed range from 35km / h to 25km / h; and 29.111875s in the speed range from 55km / h to 45km / h; 32.885s in the speed range from 35km / h to 25km / h; and 37.26625s in the speed range from 25km / h to 65km / h. The time taken was 41.283125s for the speed range up to 15km / h; 22.896875s for the speed range from 70km / h to 60km / h; 26.989375s for the speed range from 60km / h to 50km / h; 30.509375s for the speed range from 50km / h to 40km / h; 35.39375s for the speed range from 40km / h to 30km / h; and 39.145s for the speed range from 30km / h to 20km / h. There were a total of 11 speed ranges.

[0163] According to an embodiment of this disclosure, taking the first speed range from 75 km / h to 65 km / h as an example, V1 = 75 km / h = 20.8333 m / s, V2 = 65 km / h = 18.0556 m / s, V3 = (V1 + V2) / 2 = 19.4444 m / s, t1 = 21.605625 s, the first equation is listed according to formula (4) as shown in formula (13) below.

[0164]

[0165] According to embodiments of this disclosure, the same logic applies to the remaining speed ranges, resulting in a total of 11 equations to solve for these four road resistance coefficients. The solution is: C′ d =0.99939, f′ co1 =0.0065911, fco2 = -0.00004935, e = 11.0819. Substituting the solved road resistance coefficient into formula (1), the target resistance determination function of the vehicle can be obtained. At the same time, the sliding resistance value of the vehicle under arbitrary mass can be calculated through the target resistance determination function, and the calculation accuracy can be obtained by comparing it with the sliding resistance value obtained through the sliding test. According to formula (11), the calculation error value of this method is 0.95%.

[0166] Figure 6(a) schematically illustrates a comparison of the method for determining vehicle coasting resistance when the vehicle is fully loaded and the results of coasting tests according to an embodiment of the present disclosure; Figure 6(b) schematically illustrates a comparison of the method for determining vehicle coasting resistance when the vehicle is 80% loaded and the results of coasting tests according to an embodiment of the present disclosure; Figure 6(c) schematically illustrates a comparison of the method for determining vehicle coasting resistance when the vehicle is 60% loaded and the results of coasting tests according to an embodiment of the present disclosure; Figure 6(d) schematically illustrates a comparison of the method for determining vehicle coasting resistance when the vehicle is 40% loaded and the results of coasting tests according to an embodiment of the present disclosure; Figure 6(e) schematically illustrates a comparison of the method for determining vehicle coasting resistance when the vehicle is 20% loaded and the results of coasting tests according to an embodiment of the present disclosure; Figure 6(f) schematically illustrates a comparison of the method for determining vehicle coasting resistance when the vehicle is 0% loaded and the results of coasting tests according to an embodiment of the present disclosure.

[0167] like Figures 6(a) to 6(f) As shown, the sliding resistance values ​​of the vehicle at different speeds under 80%, 60%, 40%, 20%, and 0% load were calculated using two methods: the method for determining vehicle sliding resistance and the sliding test method.

[0168] According to embodiments of this disclosure, in order to distinguish the calculation results of the two methods, the coasting resistance value obtained by the coasting test method is called the coasting test value, and the coasting resistance value determined by the method for determining vehicle coasting resistance is called the calculated value.

[0169] According to the embodiments of this disclosure, the error value between the sliding resistance value obtained by the method for determining vehicle sliding resistance and the vehicle sliding resistance value obtained by the sliding test is obtained by formula (11). The calculation results are shown in Table 2. It can be seen from Table 2 that the effect is good.

[0170] Table 2

[0171]

[0172] Figure 7 The diagram schematically illustrates a data flow diagram of a method for determining vehicle coasting resistance according to an embodiment of the present disclosure;

[0173] like Figure 7 As shown, a coasting test 710 is conducted on a target vehicle with a target mass of 720 to obtain the correlation between the coasting resistance and the driving speed of the target vehicle with a target mass of 720. Through the correlation 720 and the coasting kinetic energy method 730, the coasting resistance value of the target vehicle with the current vehicle mass is obtained 740.

[0174] Figure 8 The diagram schematically illustrates a data flow graph of another method for determining vehicle coasting resistance according to an embodiment of the present disclosure.

[0175] like Figure 8 As shown, it is determined whether the current mass of the vehicle is the target value. If the current mass of the vehicle is not the target value, the attribute information 810 is input into the resistance parameter prediction model 820 to obtain the resistance parameter 830. Based on the resistance parameter 830, the correlation 840 between the sliding resistance and the driving speed of the target vehicle with the target mass is obtained. Through the correlation 840 and the sliding kinetic energy method 850, the sliding resistance value 860 of the target vehicle with the current vehicle mass is obtained.

[0176] According to an embodiment of this disclosure, when the current parameters of the vehicle are the target values, the sliding resistance value of the target vehicle can be obtained based on the resistance parameter 830 and formula (2).

[0177] Based on the aforementioned method for determining vehicle coasting resistance and the method for predicting resistance parameters, this disclosure also provides a device for determining vehicle coasting resistance and a device for predicting resistance parameters. The following will be combined with... Figures 9-10 The device is described in detail.

[0178] Figure 9 A schematic block diagram of a device for determining vehicle gliding resistance according to an embodiment of the present disclosure is shown.

[0179] like Figure 9 As shown, the vehicle skidding resistance determination device 900 of this embodiment includes an acquisition module 910, a parameter determination module 920, a relationship determination module 930, a function determination module 940, and a resistance determination module 950.

[0180] The acquisition module 910 is used to determine the target vehicle's attribute information, vehicle driving information, and current vehicle mass in response to a detection request for detecting the sliding resistance of the target vehicle.

[0181] The parameter determination module 920 is used to input attribute information into a trained drag parameter prediction model to obtain drag parameters when the target vehicle meets preset conditions. The drag parameter prediction model is used to predict the drag parameters corresponding to the target vehicle with a target vehicle mass.

[0182] The relationship determination module 930 is used to obtain the correlation between gliding resistance and driving speed based on the resistance parameters, wherein the correlation corresponds to the target vehicle with the vehicle mass as the target value.

[0183] The function determination module 940 is used to determine the target resistance determination function corresponding to the target vehicle based on the correlation and attribute information.

[0184] The resistance determination module 950 is used to input vehicle driving information and the current mass of the vehicle into the target resistance determination function to obtain the sliding resistance value of the target vehicle.

[0185] Figure 10 A schematic block diagram of a training apparatus for a drag parameter prediction model according to an embodiment of the present disclosure is shown.

[0186] like Figure 10 As shown, the training device 1000 for the resistance parameter prediction model in this embodiment includes an input module 1010, a loss value determination module 1020, and an adjustment module 1030.

[0187] The input module 1010 is used to input sample data into the resistance parameter prediction model to obtain the test resistance parameters. The sample data is obtained when the vehicle mass is the target value.

[0188] The loss value determination module 1020 is used to obtain the loss value based on the test resistance parameters and the real resistance parameters corresponding to the sample data.

[0189] The adjustment module 1030 is used to adjust the hyperparameters in the resistance parameter prediction model based on the loss value, so as to obtain the trained resistance parameter prediction model.

[0190] According to embodiments of this disclosure, any multiple modules among the acquisition module 910, parameter determination module 920, relationship determination module 930, function determination module 940, and resistance determination module 950, or the input module 1010, loss value determination module 1020, and adjustment module 1030, can be combined into one module, or any one of these modules can be split into multiple modules. Alternatively, at least some of the functions of one or more of these modules can be combined with at least some of the functions of other modules and implemented in one module. According to embodiments of this disclosure, at least one of the following modules—acquisition module 910, parameter determination module 920, relationship determination module 930, function determination module 940, and resistance determination module 950, or input module 1010, loss value determination module 1020, and adjustment module 1030—can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable method of integrating or packaging the circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three methods. Alternatively, at least one of the following modules—acquisition module 910, parameter determination module 920, relationship determination module 930, function determination module 940, and resistance determination module 950, or input module 1010, loss value determination module 1020, and adjustment module 1030—can be at least partially implemented as a computer program module, which, when run, can perform corresponding functions.

[0191] Figure 11 A block diagram of an electronic device suitable for implementing a method for determining vehicle coasting resistance and a method for training a resistance parameter prediction model, according to an embodiment of the present disclosure, is shown schematically.

[0192] like Figure 11 As shown, an electronic device 1100 according to an embodiment of the present disclosure includes a processor 1101, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1102 or a program loaded from a storage portion 1108 into a random access memory (RAM) 1103. The processor 1101 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 1101 may also include onboard memory for caching purposes. The processor 1101 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0193] RAM 1103 stores various programs and data required for the operation of electronic device 1100. Processor 1101, ROM 1102, and RAM 1103 are interconnected via bus 1104. Processor 1101 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 1102 and / or RAM 1103. It should be noted that the programs may also be stored in one or more memories other than ROM 1102 and RAM 1103. Processor 1101 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in said one or more memories.

[0194] According to embodiments of this disclosure, the electronic device 1100 may further include an input / output (I / O) interface 1105, which is also connected to a bus 1104. The electronic device 1100 may also include one or more of the following components connected to the input / output (I / O) interface 1105: an input section 1106 including a keyboard, mouse, etc.; an output section 1107 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1108 including a hard disk, etc.; and a communication section 1109 including a network interface card such as a LAN card, modem, etc. The communication section 1109 performs communication processing via a network such as the Internet. A drive 1110 is also connected to the input / output (I / O) interface 1105 as needed. A removable medium 1111, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 1110 as needed so that computer programs read from it can be installed into the storage section 1108 as needed.

[0195] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0196] According to embodiments of this disclosure, the computer-readable storage medium can be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0197] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code enables the computer system to implement the method for determining vehicle coasting resistance and the method for training the resistance parameter prediction model provided in embodiments of this disclosure.

[0198] According to embodiments of this disclosure, program code for executing computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages.

[0199] Those skilled in the art will understand that the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways, even if such combinations or combinations are not explicitly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0200] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. The scope of this disclosure is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A method for determining the sliding resistance of a vehicle, comprising: In response to a detection request for detecting the skid resistance of a target vehicle, the attribute information, vehicle driving information, and current mass of the target vehicle are determined. Based on the attribute information and the current mass of the vehicle, if it is determined that the target vehicle meets the preset conditions, the attribute information is input into a trained drag parameter prediction model to obtain the drag parameter. The drag parameter prediction model is used to predict the drag parameter corresponding to the target vehicle with a target mass. Based on the aforementioned resistance parameters, the correlation between gliding resistance and driving speed is obtained, wherein the correlation corresponds to the target vehicle with a target vehicle mass. Based on the correlation and attribute information, a target resistance determination function corresponding to the target vehicle is determined. The vehicle driving information and the current mass of the vehicle are input into the target resistance determination function to obtain the sliding resistance value of the target vehicle; The step of determining the target resistance determination function corresponding to the target vehicle based on the association relationship and the attribute information includes: Based on the aforementioned correlation and multiple preset speed ranges, the travel time for each of the multiple preset speed ranges is obtained; Based on the driving time of each of the multiple preset speed ranges, the attribute information, and the preset road resistance coefficient, an initial resistance determination function corresponding to each of the multiple preset speed ranges is obtained. Based on the initial resistance determination function corresponding to each of the multiple preset speed ranges and the target kinetic energy value corresponding to each of the multiple preset speed ranges, the coefficient value of the road resistance coefficient for the target vehicle is determined; Based on the coefficient values, a target resistance determination function corresponding to the target vehicle is determined.

2. The method according to claim 1, wherein, The preset speed range includes boundary speed values; The step of determining the road resistance coefficient for the target vehicle based on the initial resistance determination function corresponding to each of the plurality of preset speed ranges and the target kinetic energy value corresponding to each of the plurality of preset speed ranges includes: Based on the boundary velocity values ​​of each of the multiple preset velocity intervals and the target value, determine the target kinetic energy value corresponding to each of the multiple preset velocity intervals; Based on the target kinetic energy values ​​corresponding to the multiple preset speed ranges and the initial resistance determination functions corresponding to the multiple preset speed ranges, a set of coefficient-solving equations is obtained. The system of equations for solving the coefficients is then solved to obtain the coefficient values ​​of the road resistance coefficient.

3. The method according to claim 2, wherein, The attribute information includes windward area value, temperature value, and pressure value; The step of obtaining the initial resistance determination function corresponding to each of the plurality of preset speed ranges based on the travel time of each preset speed range, the attribute information, and the preset road resistance coefficient includes: Based on the boundary speed values ​​of each of the multiple preset speed ranges and the driving time of each of the multiple preset speed ranges, the driving distance value of each of the multiple preset speed ranges is determined; The air density is determined based on the temperature and pressure values. Based on the air density, the windward area value, the travel distance values ​​of each of the multiple preset speed ranges, and the preset road resistance coefficient, an initial resistance determination function corresponding to each of the multiple preset speed ranges is obtained.

4. The method according to claim 1, wherein, The process of obtaining the correlation between gliding resistance and travel speed based on the resistance parameters includes: Based on the resistance parameters and multiple preset driving speeds, the gliding resistance corresponding to the multiple preset driving speeds is obtained; Based on the gliding resistance corresponding to the plurality of preset driving speeds and the plurality of preset driving speeds, the correlation between the gliding resistance and the driving speed is obtained.

5. The method according to claim 1, wherein, The preset conditions include: a first sub-preset condition and a second sub-preset condition, wherein the first sub-preset condition includes: there is no target resistance determination function corresponding to the target vehicle in the database; the second sub-preset condition includes: the current mass of the vehicle is not equal to the target value.

6. The method according to claim 4, further comprising: Based on the attribute information, determine whether the target vehicle meets the first sub-preset condition; If it is determined that the target vehicle does not meet the first sub-preset condition, the current mass of the vehicle is compared with the target value to determine whether the target vehicle meets the second sub-preset condition. If the target vehicle satisfies both the first sub-preset condition and the second sub-preset condition, then the target vehicle is determined to satisfy the preset condition.

7. The method according to claim 1, wherein the target resistance determination function is as shown in the following formula (1): ；（1） in, F represents the sliding resistance, A represents the frontal area, ρ represents the air density, and V represents the vehicle speed. C d +d, C d Where d is the air drag coefficient, and d is a constant. f co1 +b, f co1 Here, b is the first rolling resistance coefficient, and f is a constant. co2 is the second rolling resistance coefficient, m is the vehicle mass, g is the gravitational acceleration, and e is a constant.

8. A training method for a resistance parameter prediction model, comprising: The sample data is input into the resistance parameter prediction model to obtain the test resistance parameters, wherein the sample data is obtained when the vehicle mass is the target value; The loss value is obtained based on the test resistance parameters and the actual resistance parameters corresponding to the sample data; Based on the loss value, the hyperparameters in the resistance parameter prediction model are adjusted to obtain a trained resistance parameter prediction model, wherein the trained resistance parameter prediction model is used in the method of any one of claims 1 to 7.

9. A device for determining the sliding resistance of a vehicle, comprising: The acquisition module is used to determine the attribute information, vehicle driving information and current mass of the target vehicle in response to a detection request for detecting the sliding resistance of the target vehicle. The parameter determination module is used to input the attribute information into a trained drag parameter prediction model to obtain drag parameters when the target vehicle meets the preset conditions. The drag parameter prediction model is used to predict the drag parameters corresponding to the target vehicle with a target vehicle mass. The relationship determination module is used to obtain the correlation between gliding resistance and driving speed based on the resistance parameters, wherein the correlation corresponds to the target vehicle with a target vehicle mass. The function determination module is used to determine the target resistance determination function corresponding to the target vehicle based on the association relationship and the attribute information; The resistance determination module is used to input the vehicle driving information and the current mass of the vehicle into the target resistance determination function to obtain the sliding resistance value of the target vehicle; The function determination module is further configured to: obtain the driving time of each of the multiple preset speed ranges based on the correlation and multiple preset speed ranges; obtain the initial resistance determination function corresponding to each of the multiple preset speed ranges based on the driving time of each of the multiple preset speed ranges, the attribute information, and the preset road resistance coefficient; determine the coefficient value of the road resistance coefficient for the target vehicle based on the initial resistance determination function corresponding to each of the multiple preset speed ranges and the target kinetic energy value corresponding to each of the multiple preset speed ranges; and determine the target resistance determination function corresponding to the target vehicle based on the coefficient value.

Images