Vehicle load monitoring method and device

Abstract

The invention provides a vehicle load monitoring method and device, and the method comprises the steps: obtaining sliding data based on the driving data of a vehicle, wherein the sliding data is the driving data of the vehicle under a sliding working condition; the sliding data is cleaned; performing de-timing processing on the cleaned sliding data to obtain sliding data fragments; and inputting the average acceleration, the square of the average vehicle speed and the average sliding resistance of each sliding data fragment as input features into a trained SVR model to obtain the vehicle load output by the SVR model. The method provided by the embodiment of the invention can accurately monitor the vehicle load.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle load monitoring, and particularly relates to a vehicle load monitoring method and device. Background Art

[0002] Vehicle overloading not only damages highway construction, but also increases the risk of driving. Many serious traffic accidents are caused by overloading. In addition, for the development and iteration of automotive products, the high-cost collection of load data will also bring a series of problems to the calibration design of vehicle manufacturers.

[0003] Existing load monitoring generally obtains the vehicle load by weighing the vehicle. It is necessary to arrange weighbridge facilities, which is costly, and the time and location for obtaining load data are limited. Summary of the Invention

[0004] Embodiments of the present invention provide a vehicle load monitoring method and device to at least solve some of the above technical problems existing in the prior art.

[0005] In a first aspect, embodiments of the present invention provide a vehicle load monitoring method, including:

[0006] Obtaining coasting data based on the driving data of the vehicle, where the coasting data is the driving data of the vehicle under coasting conditions;

[0007] Cleaning the coasting data;

[0008] Performing detrending processing on the cleaned coasting data to obtain coasting data segments;

[0009] Taking the average acceleration, the square of the average vehicle speed, and the average coasting resistance of each coasting data segment as input features and inputting them into a trained SVR model to obtain the vehicle load output by the SVR model.

[0010] In an optional embodiment, obtaining coasting data based on the driving data of the vehicle includes:

[0011] The driving data includes driving condition parameters. When the driving condition parameters meet the coasting conditions, the corresponding driving data is coasting data.

[0012] In an optional embodiment, the driving condition parameters include motor speed, motor torque, throttle pedal opening, and brake pedal opening. When the motor speed is greater than 0 rpm, the motor torque is less than or equal to 0 Nm, and the throttle pedal and brake pedal openings are equal to 0, the driving condition parameters meet the coasting conditions.

[0013] In an optional embodiment, the driving condition parameters meeting the coasting conditions further include:

[0014] The driving speed of the driving data in this frame is not greater than the driving speed of the driving data in the previous frame.

[0015] In an alternative embodiment, when the driving condition parameter satisfies the coasting condition, it further includes:

[0016] The time difference between two adjacent frames of driving data should be within a set time range.

[0017] In an alternative embodiment, performing a de-temporalization process on the cleaned coasting data to obtain coasting data segments includes:

[0018] For a segment of the coasting data, slicing it into multiple consecutive data segments, and the duration of each data segment is a set duration;

[0019] Calculating the average acceleration, the square of the average vehicle speed, and the average coasting resistance for each data segment.

[0020] In an alternative embodiment, it further includes optimizing the parameters of the SVR model by using the ABC artificial bee colony.

[0021] In an alternative embodiment, optimizing the parameters of the SVR model by using the ABC artificial bee colony includes:

[0022] Parameter initialization and import of the fitness function;

[0023] Randomly generating S initial solutions, and performing a loop search on all the initial solutions to generate new solutions;

[0024] Continuously narrowing the search range of the optimal solution by calculating the fitness of the new solutions;

[0025] Obtaining the optimal solution of the fitness function, and backtracking to the SVR model for iterative optimization.

[0026] In an alternative embodiment, training the SVR model includes:

[0027] Training and validating the SVR model by using a dataset cross-combination method.

[0028] In a second aspect, an embodiment of the present invention provides a vehicle load monitoring device, including:

[0029] An extraction module, configured to obtain coasting data based on the driving data of the vehicle, where the coasting data is the driving data of the vehicle under a coasting condition;

[0030] A cleaning module, configured to clean the coasting data;

[0031] A slicing module, configured to perform a de-temporalization process on the cleaned coasting data to obtain coasting data segments;

[0032] The prediction module takes the average acceleration, the square of the average vehicle speed, and the average coasting resistance of each coasting data segment as input features and inputs them into the trained SVR model to obtain the vehicle load output by the SVR model.

[0033] In a third aspect, an embodiment of the present invention provides an electronic device, including:

[0034] At least one processor; and

[0035] A memory communicatively connected to the at least one processor; wherein,

[0036] The memory stores information executable by the at least one processor, and the information is executed by the at least one processor so that the at least one processor can execute the method described in the embodiments of the present invention.

[0037] In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium storing computer information, and the computer information is used to cause a computer to execute the method described in the present invention.

[0038] One embodiment of the present invention has the following advantages or beneficial effects:

[0039] In the vehicle load monitoring method according to the embodiment of the present invention, coasting data can be obtained based on the driving data of the vehicle, and the coasting data is the driving data of the vehicle under the coasting condition; the coasting data is cleaned; the cleaned coasting data is de-temporized to obtain coasting data segments; the average acceleration, the square of the average vehicle speed, and the average coasting resistance of each coasting data segment are used as input features and input into the trained SVR model to obtain the vehicle load output by the SVR model. Calculating the vehicle load using coasting data can obtain the vehicle load conveniently and quickly. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] By referring to the accompanying drawings and describing its exemplary embodiments in detail, the above and other features and advantages of the present invention will become more apparent.

[0041] Figure 1 is a flowchart showing the process of a vehicle load monitoring method according to an exemplary embodiment;

[0042] Figure 2 is a schematic diagram showing the composition structure of a vehicle load monitoring device according to an exemplary embodiment;

[0043] Figure 3 is a schematic diagram showing the composition structure of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0044] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. Like reference numerals in the figures denote like or similar structures and thus their detailed description will be omitted.

[0045] The terms "a", "an", "the", and "said" are used to denote the presence of one or more elements / components / etc.; the terms "comprising" and "having" are used to mean an open inclusion and mean that there may be additional elements / components / etc. in addition to the listed elements / components / etc.

[0046] See Figure 1 , an embodiment of the present invention provides a method for monitoring vehicle load, including:

[0047] S10. Obtain coasting data based on the driving data of the vehicle, where the coasting data is the driving data of the vehicle under coasting conditions;

[0048] S20. Clean the coasting data;

[0049] S30. Desequentialize the cleaned coasting data to obtain coasting data segments;

[0050] S40. Take the average acceleration, the square of the average vehicle speed, and the average coasting resistance of each coasting data segment as input features and input them into a trained SVR model to obtain the vehicle load output by the SVR model.

[0051] In the embodiment of the present invention, based on the driving data under coasting conditions, the vehicle load obtained through the SVR model is less interfered and the obtained vehicle load is relatively accurate. Cleaning the coasting data can eliminate the interference of noise data on model prediction and improve the accuracy. Desequentializing the coasting data can improve the stability of the driving data, and further improve the accuracy of the subsequent SVR model in monitoring vehicle load data.

[0052] In the embodiment of the present invention, the driving data required for training the SVR model and the driving data required for predicting the vehicle load can be obtained through vehicle CAN data.

[0053] The method of the present invention can be applied to the in-vehicle unit, and all steps are executed on the in-vehicle unit. It can also be applied to the server or cloud data platform, and all steps are executed on the server or cloud data platform. Applying the method of the present invention to the server or motion data platform can improve computing power, relieve the computing pressure on the in-vehicle unit, and reduce the requirements for the hardware configuration of the in-vehicle unit. The method of the present invention can also be that some steps are applied to the in-vehicle unit and some steps are applied to the server or cloud data platform. In an exemplary embodiment, the SVR model can be set on the in-vehicle unit to monitor the vehicle load on the in-vehicle unit, or the SVR model can be set on the server or cloud data platform to monitor the vehicle load through the SVR model on the server or cloud data platform.

[0054] When monitoring the vehicle load, the driving data of the vehicle is obtained in real time, and the vehicle load can be monitored in real time.

[0055] Clean the driving data to remove noise data such as missing or abnormal relevant data, so as to eliminate the interference of the noise data on the training and prediction of the SVR model and improve the accuracy. The data related to the method of the embodiment of the present invention in the driving data may include, for example, motor speed, motor torque, accelerator pedal, brake pedal, etc. If the data of one of them is missing or abnormal, the corresponding driving data is deleted.

[0056] For example, the cloud data platform collects the vehicle's CAN data, cleans the obtained vehicle driving data, and removes relevant signal items, such as driving data with noise points such as missing values and abnormal values in motor speed, motor torque, accelerator pedal, brake pedal, etc.

[0057] In the embodiment of the present invention, obtaining the coasting data can be screened from the continuous driving data during driving. Specifically, in the implementation, the continuous driving data with the vehicle speed from equal to 0 to greater than 0 and then back to equal to 0 is the driving data of one driving process. The coasting data in one driving process is screened out from the driving data of this driving process.

[0058] In some embodiments, obtaining the coasting data based on the driving data of the vehicle includes: the driving data includes driving condition parameters, and when the driving condition parameters meet the coasting condition, the corresponding driving data is the coasting data. The driving data includes driving condition parameters, and the corresponding driving condition can be determined according to the driving condition parameters. The driving conditions may include, for example, coasting condition, acceleration condition, braking condition, etc. According to the driving condition data, it can be determined whether the driving condition corresponding to the driving data is the coasting condition.

[0059] When an electric vehicle has regenerative braking, a relatively high requirement for real-time load monitoring is needed. The method of the embodiment of the present invention can be used for monitoring the load of an electric vehicle. By screening the coasting data and predicting the vehicle load based on this, the accuracy can be improved, and small changes in the load can be reflected.

[0060] In some embodiments, the driving condition parameters may include motor speed, motor torque, accelerator pedal opening, and brake pedal opening. According to the above driving condition parameters, it can be determined whether the corresponding driving condition is a coasting condition. In an exemplary embodiment, when the motor speed is greater than 0 rpm, the motor torque is less than or equal to 0 Nm, and the accelerator pedal and brake pedal openings are equal to 0, it can be determined that the driving condition corresponding to the driving data is a coasting condition, and its driving condition parameters meet the coasting conditions. The motor speed being greater than 0 rpm can eliminate reverse data, and the motor torque being less than or equal to 0 can ensure that the vehicle is in the energy recovery process. The accelerator pedal and brake pedal openings being equal to 0 can ensure that the vehicle driving force and braking force are 0, meeting the vehicle coasting state.

[0061] In some embodiments, for the driving condition parameters to meet the coasting conditions, it further includes: the driving speed of this frame of driving data is not greater than the driving speed of the previous frame of driving data. The driving data during a driving process is continuous in time. By comparing the driving speeds in two adjacent frames of driving data and screening the driving data with a driving speed not greater than the previous frame, it is possible to avoid screening the driving data of the vehicle driving downhill.

[0062] In some embodiments, for the driving condition parameters to meet the coasting conditions, it further includes: the time difference between two adjacent frames of driving data should be within a set time range. The time difference between two adjacent frames of driving data being within the set time range can ensure the continuity of the time of the driving data. In an exemplary embodiment, the set time range can be [1 s, 3 s). When screening the coasting data, the time difference between two frames of data should be greater than or equal to 1 s and less than 3 s.

[0063] In some embodiments, performing a de-temporalization process on the cleaned coasting data to obtain coasting data segments, including:

[0064] For a segment of coasting data, slicing it into multiple consecutive data segments, and the duration of each data segment is a set duration;

[0065] Calculating the average acceleration, the square of the average vehicle speed, and the average coasting resistance for each data segment.

[0066] Generally, it can be considered that the vehicle load remains unchanged during the same driving process. There may be multiple segments of coasting data during the vehicle driving process. Therefore, the duration of the selected coasting data is not necessarily the same. In the embodiments of the present invention, a de-temporalization operation is performed on each segment of coasting data to eliminate the influence of the coasting duration feature on the SVR model and avoid overfitting of the SVR model. The length of each data segment can be, for example, 4s. For a segment of coasting data, it can be evenly sliced into multiple consecutive data segments, each data segment having a duration of 4s. Discard the data segments with a duration less than 4s, and calculate the average acceleration, the square of the average vehicle speed, and the average coasting resistance required by the model for each data segment.

[0067] Training the SVR model may include: using the average acceleration, the square of the average vehicle speed, and the average coasting resistance of each coasting data segment as the input features of the SVR model, and using the vehicle load as the output feature of the SVR model. The vehicle load corresponding to the above-mentioned coasting data segment is known. By training the SVR model with the known vehicle load and the average acceleration, the square of the average vehicle speed, and the average coasting resistance obtained from the corresponding coasting data segment, it can be used for real-time prediction of the vehicle load. The obtaining step of the coasting data segment may be the same as the obtaining step of the coasting data during vehicle load monitoring. In a specific implementation, the specific steps may include: obtaining coasting data based on the driving data of the vehicle, where the coasting data is the driving data of the vehicle under the coasting condition; cleaning the coasting data; performing de-temporalization processing on the cleaned coasting data to obtain coasting data segments; calculating the average acceleration, the square of the average vehicle speed, and the average coasting resistance based on the coasting data segments. Since the vehicle load is known, there are corresponding vehicle load data respectively.

[0068] Based on the input features calculated from the coasting data segments, such as the average acceleration, the square of the average vehicle speed, and the average coasting resistance, and the corresponding vehicle load, they can be divided into a training set and a validation set. The data in the training set is used to train the SVR model, and the data in the validation set is used to validate the SVR model.

[0069] In some embodiments, the method of the embodiments of the present invention further includes: using the ABC artificial bee colony to optimize the parameters of the SVR model. When training the SVR model, the ABC artificial bee colony can be used to optimize the parameters of the SVR model. Through the local optimization behavior of each artificial bee individual, the global optimal value can finally emerge in the group, which can improve the convergence speed.

[0070] In some embodiments, using the ABC artificial bee colony to optimize the parameters of the SVR model includes:

[0071] Parameter initialization and fitness function import;

[0072] Randomly generate S initial solutions, perform cyclic search on all initial solutions and generate new solutions;

[0073] Continuously narrow the search range of the optimal solution by calculating the fitness of the new solution;

[0074] Obtain the optimal solution of the fitness function and go back to the SVR model for iterative optimization.

[0075] In some embodiments, training the SVR model includes: training and verifying the SVR model by cross-combining data sets. In a specific implementation, the data can be divided into multiple equal parts, one of which is selected as a verification set, and the remaining parts are selected as training sets, and the SVR model is trained and verified until all parts are used as verification sets. Alternatively, a specified number of data can be selected as a verification set, and the remaining data can be selected as a training set, and the SVR model is trained and verified until all data are selected as a verification set. Of course, the specific method of training and verifying the SVR model by cross-combining data sets is not limited to the above examples.

[0076] In some embodiments, the input of the SVR model is standardized (StandardScaler) to eliminate the dimensional differences between features.

[0077] In some embodiments, the coasting data is divided into a plurality of coasting data segments, and the average acceleration, the square of the average vehicle speed, and the average coasting resistance of each coasting data segment are input into a trained SVR model to obtain a plurality of vehicle loads. The average value of the vehicle load obtained by using the plurality of coasting data segments divided by the coasting data may be used as the final value of the vehicle load monitoring. In a specific implementation, the average value of the load results between the 5% and 95% percentiles of all the coasting segments divided by the coasting data may be calculated as the prediction result of the vehicle load corresponding to the travel data. The monitoring results of the vehicle load may be stored in a cloud data platform.

[0078] The method of the embodiment of the present invention can effectively promote the development of vehicle load calibration design and safety monitoring in the automotive field, accelerate the upgrading of related industries, and while launching corresponding products according to different load requirements, it can also provide corresponding safety auxiliary basis for transportation.

[0079] See also Figure 2, an embodiment of the present invention provides a vehicle load monitoring device, including an extraction module, a cleaning module, a slicing module, and a prediction module. The extraction module is used to obtain coasting data based on the driving data of the vehicle, and the coasting data is the driving data of the vehicle under the coasting condition; the cleaning module is used to clean the coasting data; the slicing module is used to perform detrending processing on the cleaned coasting data to obtain coasting data segments; the prediction module takes the average acceleration, the square of the average vehicle speed, and the average coasting resistance of each coasting data segment as input features and inputs them into a trained SVR model to obtain the vehicle load output by the SVR model.

[0080] The vehicle load monitoring device according to the embodiment of the present invention can implement the methods of the above embodiments, and the descriptions of the above method embodiments can be used to understand and explain the device of the embodiment of the present invention. For the purpose of simplicity and saving space, it will not be repeated here.

[0081] According to an embodiment of the present invention, the present invention also provides an electronic device and a readable storage medium.

[0082] FIG. 3 shows a schematic block diagram of an electronic device 400 that can be used to implement the embodiments of the present invention. The electronic device 400 is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0083] As Figure 3 shown, the electronic device 400 includes a computing unit 401, which can execute various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 402 or a computer program loaded from a storage unit 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the electronic device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other through a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0084] Multiple components in the electronic device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, an optical disc, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the electronic device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0085] The computing unit 401 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 401 executes the various methods and processes described above, such as the gas hot water heating and clothes drying machine control method. For example, in some embodiments, the gas hot water heating and clothes drying machine control method can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as the storage unit 408. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 400 via the ROM 402 and / or the communication unit 409. When the computer program is loaded into the RAM 403 and executed by the computing unit 401, one or more steps of the gas hot water heating and clothes drying machine control method described above can be executed. Alternatively, in other embodiments, the computing unit 401 can be configured to execute the gas hot water heating and clothes drying machine control method in any other suitable way (e.g., by means of firmware).

[0086] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs, which can be executed and / or interpreted on a programmable system including at least one programmable processor, and the programmable processor can be a special or general-purpose programmable processor, can receive data and information from a storage system, at least one input device, and at least one output device, and transmit the data and information to the storage system, the at least one input device, and the at least one output device.

[0087] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing devices, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowchart and / or block diagram are implemented. The program codes can be executed entirely on the machine, partially on the machine, executed partially on the machine as an independent software package and partially on a remote machine, or executed entirely on a remote machine or server.

[0088] In the context of the present invention, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an information execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0089] In order to provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0090] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), and the Internet.

[0091] A computer system can include a client and a server. The client and the server are generally far from each other and typically interact through a communication network. The client - server relationship is created by computer programs running on respective computers and having a client - server relationship with each other. The server can be a cloud server, a server of a distributed system, or a server incorporating blockchain.

[0092] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this invention can be achieved. No limitation is imposed herein.

[0093] Furthermore, 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, features defined with "first" and "second" can explicitly or implicitly include at least one of such features. In the description of this invention, "a plurality of" means two or more unless otherwise specifically defined.

[0094] In the embodiments of this invention, the term "a plurality of" means two or more unless otherwise clearly defined.

[0095] In the description of this specification, the description of terms such as "an embodiment", "a preferred embodiment", etc. means 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 embodiments of this invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or instance. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0096] The above are only the preferred embodiments of the embodiments of the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, various modifications and variations can be made to the embodiments of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present invention shall be included within the protection scope of the embodiments of the present invention.

Claims

1. A vehicle load monitoring method, characterized in that: include: Acquiring coasting data based on the driving data of the vehicle, wherein the coasting data is the driving data of the vehicle under the coasting condition; Cleaning the taxiing data; De-sequencing the cleaned taxiing data to obtain taxiing data segments; The average acceleration, the square of the average vehicle speed and the average sliding resistance of each sliding data segment are input as input features into the trained SVR model to obtain the vehicle load output by the SVR model.

2. The vehicle load monitoring method according to claim 1, characterized in that: The sliding data is obtained based on the vehicle's driving data, including: The driving data includes driving condition parameters. When the driving condition parameters meet the coasting condition, the corresponding driving data is coasting data.

3. The vehicle load monitoring method according to claim 2, characterized in that: The driving condition parameters include motor speed, motor torque, accelerator pedal opening and brake pedal opening. When the motor speed is greater than 0rpm, the motor torque is less than or equal to 0nm, and the accelerator pedal and brake pedal opening are equal to 0, the driving condition parameters meet the gliding conditions.

4. The vehicle load monitoring method according to claim 1, characterized in that: The driving condition parameters satisfy the coasting condition, and further include: The driving speed of the driving data of this frame is not greater than the driving speed of the driving data of the previous frame.

5. The vehicle load monitoring method according to claim 4, characterized in that: The driving condition parameters satisfy the coasting condition, and further include: The time difference between two adjacent frames of driving data should be within the set time range.

6. The vehicle load monitoring method according to claim 1, characterized in that: The cleaned taxiing data is de-timed to obtain taxiing data segments, including: For a segment of the sliding data, slicing is performed into a plurality of continuous data segments, and the duration of each data segment is a set duration; For each data segment, the average acceleration, the square of the average vehicle speed, and the average sliding resistance are calculated.

7. The vehicle load monitoring method according to claim 1, characterized in that: The method also includes optimizing the parameters of the SVR model by using an ABC artificial bee colony.

8. The vehicle load monitoring method according to claim 1, characterized in that: The parameters of the SVR model are optimized using the ABC artificial bee colony, including: Parameter initialization and fitness function import; Randomly generate S initial solutions, perform cyclic search on all initial solutions and generate new solutions; Continuously narrow the search range of the optimal solution by calculating the fitness of the new solution; Obtain the optimal solution of the fitness function and go back to the SVR model for iterative optimization.

9. The vehicle load monitoring method according to claim 1, characterized in that: Training the SVR model includes: The SVR model is trained and verified by using a cross-combination of data sets.

10. A vehicle load monitoring device, characterized in that: include: An extraction module, used for acquiring coasting data based on the driving data of the vehicle, wherein the coasting data is the driving data of the vehicle under the coasting condition; A cleaning module, used for cleaning the taxiing data; A slicing module, used for de-serializing the cleaned taxiing data to obtain taxiing data segments; The prediction module inputs the average acceleration, the square of the average vehicle speed and the average sliding resistance of each sliding data segment as input features into the trained SVR model to obtain the vehicle load output by the SVR model.

Images