Vehicle CO2 emission prediction method, device, equipment and medium
By acquiring and preprocessing vehicle data, and using neural network models to predict CO2 emissions in vehicle controllers, the problem of inaccurate CO2 emissions in the prior art is solved, and more efficient and accurate measurements are achieved.
Patent Information
- Application Number
- CN202411056842.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-02
- Publication Date
- 2024-12-17
AI Technical Summary
The vehicle CO2 emissions converted through fuel consumption tests in the prior art are inaccurate, resulting in much smaller measurement results than the actual fuel consumption and CO2 emissions.
By obtaining the vehicle's speed and on-board diagnostic system data, pre-processing and inputting the CO2 emission prediction model, using a long-term and short-term memory algorithm to build a neural network model, deploying it in the microcontroller of the vehicle's controller to output the vehicle's CO2 emissions.
The measurement accuracy and efficiency of vehicle CO2 emissions are improved, ensuring that the measurement results are consistent with the actual trend and the relative error is small.
Smart Images
Figure CN119152594A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of automobile technology, and in particular to a vehicle CO2 emission prediction method, device, equipment and computer-readable storage medium. Background Art
[0002] As the number of vehicles continues to increase, CO2 emissions from vehicle exhaust have also increased dramatically, causing serious pollution to the environment. How to quickly and accurately measure vehicle CO2 emissions has become an urgent problem to be solved. In the related art, a fuel consumption test is conducted on the vehicle at a test site, and the vehicle CO2 emissions are converted based on the fuel consumption test results. However, the test road environment in the test site is very different from the actual road environment, and the fuel consumption operating condition curve used in the test cannot reflect the actual operating conditions well, which ultimately leads to the fuel consumption test results obtained from the test being far less than the actual fuel consumption of the vehicle, that is, the fuel consumption test results are inaccurate. Further, the vehicle CO2 emissions converted based on the fuel consumption test results are also inaccurate. Summary of the invention
[0003] The present application provides a vehicle CO2 emission prediction method, device, equipment and computer-readable storage medium, which can solve the technical problem in the prior art that the vehicle CO2 emission is converted according to the fuel consumption test results, resulting in inaccurate vehicle CO2 emission.
[0004] In a first aspect, an embodiment of the present application provides a vehicle CO2 emission prediction method, the vehicle CO2 emission prediction method comprising:
[0005] Get the vehicle's speed and on-board diagnostic system data;
[0006] determining an acceleration of the vehicle based on the vehicle speed;
[0007] Preprocessing the vehicle speed and the on-board diagnostic system data to obtain preprocessed vehicle speed and preprocessed on-board diagnostic system data;
[0008] Input the acceleration, pre-processed vehicle speed and pre-processed on-board diagnostic system data into a CO2 emission prediction model to output vehicle CO2 emissions;
[0009] Among them, the CO2 emission prediction model is deployed in the microcontroller of the vehicle controller.
[0010] In combination with the first aspect, in one implementation, the vehicle speed is preprocessed, and the corresponding formula is:
[0011] V' = log(V);
[0012] Among them, V is the vehicle speed, and V' is the vehicle speed after preprocessing.
[0013] In combination with the first aspect, in one implementation, the on-board diagnostic system data includes engine speed and coolant temperature, and the on-board diagnostic system data is preprocessed, and the corresponding formula is:
[0014]
[0015] Wherein, RPM is the engine speed, RPM' is the engine speed after preprocessing, CoolTemp is the coolant temperature, CoolTemp' is the coolant temperature after preprocessing, a is the first coefficient, and b is the second coefficient.
[0016] In combination with the first aspect, in one implementation, the process of constructing the CO2 emission prediction model includes:
[0017] Building a neural network model based on a long short-term memory algorithm and training the neural network model;
[0018] Convert the format of the trained neural network model to the target format to obtain a model in the target format;
[0019] The model in the target format is deployed in the single chip microcomputer of the vehicle controller to obtain a CO2 emission prediction model.
[0020] In combination with the first aspect, in one implementation, the target format is a tflite format, and the single-chip microcomputer is an STM32 single-chip microcomputer.
[0021] In a second aspect, an embodiment of the present application provides a vehicle CO2 emission prediction device, the vehicle CO2 emission prediction device comprising:
[0022] An acquisition module, used to acquire vehicle speed and on-board diagnostic system data of the vehicle;
[0023] a determination module, configured to determine an acceleration of the vehicle based on the vehicle speed;
[0024] A preprocessing module, used for preprocessing the vehicle speed and the on-board diagnostic system data to obtain preprocessed vehicle speed and preprocessed on-board diagnostic system data;
[0025] The input-output module is used to input the acceleration, pre-processed vehicle speed and pre-processed on-board diagnostic system data into the CO2 emission prediction model and output the vehicle CO2 emission; wherein the CO2 emission prediction model is deployed in the single-chip microcomputer of the vehicle controller.
[0026] In conjunction with the second aspect, in one implementation, the preprocessing module is specifically configured to preprocess the vehicle speed according to the following formula:
[0027] V' = log(V);
[0028] Among them, V is the vehicle speed, and V' is the vehicle speed after preprocessing.
[0029] In combination with the second aspect, in one implementation, the on-board diagnostic system data includes engine speed and coolant temperature, and the preprocessing module is specifically used to preprocess the on-board diagnostic system data according to the following formula, and the corresponding formula is:
[0030]
[0031] Wherein, RPM is the engine speed, RPM' is the engine speed after preprocessing, CoolTemp is the coolant temperature, CoolTemp' is the coolant temperature after preprocessing, a is the first coefficient, and b is the second coefficient.
[0032] In conjunction with the second aspect, in one embodiment, the vehicle CO2 emission prediction device further includes a construction module for constructing a CO2 emission prediction model. The construction process of constructing the CO2 emission prediction model includes:
[0033] Building a neural network model based on a long short-term memory algorithm and training the neural network model;
[0034] Convert the format of the trained neural network model to the target format to obtain a model in the target format;
[0035] The model in the target format is deployed in the single chip microcomputer of the vehicle controller to obtain a CO2 emission prediction model.
[0036] In combination with the second aspect, in one implementation, the target format is a tflite format, and the single-chip microcomputer is an STM32 single-chip microcomputer.
[0037] In a third aspect, an embodiment of the present application provides a vehicle CO2 emission prediction device, comprising a processor, a memory, and a vehicle CO2 emission prediction program stored in the memory and executable by the processor, wherein when the vehicle CO2 emission prediction program is executed by the processor, the steps of the vehicle CO2 emission prediction method as described in any one of the first aspects are implemented.
[0038] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a vehicle CO2 emission prediction program is stored. When the vehicle CO2 emission prediction program is executed by a processor, the steps of the vehicle CO2 emission prediction method as described in any one of the first aspects are implemented.
[0039] The beneficial effects brought by the technical solution provided in the embodiments of the present application include:
[0040] By acquiring the vehicle speed and on-board diagnostic system data of the vehicle; then determining the acceleration of the vehicle based on the vehicle speed; preprocessing the vehicle speed and the on-board diagnostic system data to obtain the preprocessed vehicle speed and the preprocessed on-board diagnostic system data; finally, inputting the acceleration, the preprocessed vehicle speed and the preprocessed on-board diagnostic system data into a CO2 emission prediction model to output the vehicle CO2 emissions; wherein the CO2 emission prediction model is deployed in a single-chip microcomputer of a vehicle controller, which can improve the accuracy and efficiency of the measured vehicle CO2 emissions. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] Figure 1 This is a flow chart of the first embodiment of the vehicle CO2 emission prediction method of the present application;
[0042] Figure 2 A schematic diagram of the comparison results of the actual value and the predicted value of the instantaneous CO2 emissions in the first 2000s is provided for an embodiment of the present application;
[0043] Figure 3 A comparison chart of the error between the actual total CO2 emissions and the predicted total CO2 emissions provided in one embodiment of the present application;
[0044] Figure 4 This is a schematic diagram of the functional modules of an embodiment of a vehicle CO2 emission prediction device of the present application;
[0045] Figure 5 This is a schematic diagram of the hardware structure of the vehicle CO2 emission prediction device involved in the embodiment of the present application. DETAILED DESCRIPTION
[0046] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0047] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.
[0048] In a first aspect, an embodiment of the present application provides a vehicle CO2 emission prediction method.
[0049] In one embodiment, referring to Figure 1 , Figure 1This is a flow chart of the first embodiment of the vehicle CO2 emission prediction method of the present application. Figure 1 As shown, the vehicle CO2 emission prediction method includes:
[0050] Step 110, obtaining vehicle speed and on-board diagnostic system data;
[0051] The on-board diagnostics (OBD) data include but are not limited to engine speed and coolant temperature.
[0052] In a specific implementation, the vehicle controller obtains the vehicle speed from a speed sensor arranged on the vehicle, obtains the vehicle engine speed from a speed sensor arranged on the vehicle engine, and obtains the coolant temperature from a temperature sensor arranged in the vehicle engine coolant tank.
[0053] Step 120: determining the acceleration of the vehicle based on the vehicle speed;
[0054] Further, the vehicle controller determines the acceleration of the vehicle based on the vehicle speed, wherein the acceleration of the vehicle is determined based on the vehicle speed, and the corresponding formula is as follows:
[0055]
[0056] Where, V is the speed of the vehicle, A is the acceleration of the vehicle, V i+1 is the vehicle speed at time i+1, V i-1 is the vehicle speed at time i-1. It should be noted that V i+1 and V i-1 The unit is km / h. The 7.2 in the above formula is to convert km / h to m / s 2 Required parameters.
[0057] Step 130, preprocessing the vehicle speed and the on-board diagnostic system data to obtain preprocessed vehicle speed and preprocessed on-board diagnostic system data;
[0058] Furthermore, since the directly acquired values of vehicle speed, engine speed, coolant temperature, etc. are relatively large, in order to facilitate calculation, the vehicle controller preprocesses the vehicle speed and the on-board diagnostic system data to reduce these values, thereby obtaining the preprocessed vehicle speed and preprocessed on-board diagnostic system data.
[0059] Step 140: input the acceleration, the pre-processed vehicle speed and the pre-processed on-board diagnostic system data into a CO2 emission prediction model, and output the vehicle CO2 emission;
[0060] Among them, the CO2 emission prediction model is deployed in the microcontroller of the vehicle controller, and the microcontroller includes but is not limited to the STM32 microcontroller.
[0061] It can be understood that the CO2 emission prediction model is a trained neural network model used to measure vehicle CO2 emissions. The input of the CO2 emission prediction model is acceleration, pre-processed vehicle speed and pre-processed on-board diagnostic system data, and the output of the CO2 emission prediction model is vehicle CO2 emissions.
[0062] After obtaining the acceleration, preprocessed vehicle speed and preprocessed on-board diagnostic system data, the vehicle controller inputs the acceleration, preprocessed vehicle speed and preprocessed on-board diagnostic system data into the CO2 emission prediction model and outputs the vehicle CO2 emissions, which can improve the accuracy and efficiency of the measured vehicle CO2 emissions.
[0063] In this embodiment, the vehicle speed and on-board diagnostic system data are obtained; then based on the vehicle speed, the acceleration of the vehicle is determined; the vehicle speed and the on-board diagnostic system data are preprocessed to obtain the preprocessed vehicle speed and the preprocessed on-board diagnostic system data; finally, the acceleration, the preprocessed vehicle speed and the preprocessed on-board diagnostic system data are input into a CO2 emission prediction model to output the vehicle CO2 emissions; wherein the CO2 emission prediction model is deployed in the single-chip microcomputer of the vehicle controller, which can improve the accuracy and efficiency of the measured vehicle CO2 emissions.
[0064] Furthermore, in one embodiment, the vehicle speed is pre-processed, and the corresponding formula is:
[0065] V' = log(V);
[0066] Among them, V is the vehicle speed, and V' is the vehicle speed after preprocessing.
[0067] In this embodiment, the value of the vehicle speed is reduced by a logarithmic function, so that the efficiency of measuring the CO2 emission of the vehicle can be improved.
[0068] Furthermore, in one embodiment, the on-board diagnostic system data includes engine speed and coolant temperature, and the on-board diagnostic system data is preprocessed, and the corresponding formula is:
[0069]
[0070] Among them, RPM is the engine speed, RPM' is the engine speed after preprocessing, CoolTemp is the coolant temperature, CoolTemp' is the coolant temperature after preprocessing, a is the first coefficient, b is the second coefficient, and the values of a and b can be flexibly set according to actual needs.
[0071] In this embodiment, the efficiency of measuring the CO2 emissions of the vehicle can be improved by multiplying the on-board diagnostic system data by a certain coefficient to reduce the value of the on-board diagnostic system data.
[0072] Furthermore, in one embodiment, the process of constructing the CO2 emission prediction model includes:
[0073] Step 210: Building a neural network model based on a long short-term memory algorithm and training the neural network model;
[0074] In the specific implementation, based on the long-short term memory (LSTM) algorithm, a neural network model is built through tensorflow, which is an open source framework for machine learning and deep learning.
[0075] The neural network model is trained, and the training data is obtained by carrying an on-board emission test device on a sample vehicle and conducting an on-board emission test on an actual road. The obtained training data includes vehicle speed, engine speed, coolant temperature and CO2 emissions, wherein the CO2 emissions are obtained by the on-board emission test device. Further, the obtained vehicle speed, engine speed and coolant temperature are preprocessed to reduce the values. In addition, the acceleration of the vehicle is determined by the vehicle speed.
[0076] A set of data corresponding to each moment includes acceleration, vehicle speed, pre-processed engine speed and pre-processed coolant temperature. Exemplarily, the data of the first second is taken as the starting data point, the window step is 5 seconds, and the interval between the starting data points of adjacent windows is 1 second. The sliding window is divided until the last data point, thereby forming a training data set consisting of multiple window data. The training data set is divided into a validation set and a training set, which account for 20% and 80% of the total training set respectively. The batch size of the model training set is 64, the optimizer is Adam, the initial learning rate is 0.002, and the loss function is selected as the mean absolute error. The learning rate decays to 0.98 times the original value every 500 training times. The total round of model training is set to 500. To prevent overfitting, the Early Stop strategy can also be used.
[0077] Step 220: convert the format of the trained neural network model into a target format to obtain a model in the target format;
[0078] Furthermore, after the neural network model is trained, the format of the trained neural network model is exported and converted into a target format to obtain a model in the target format; wherein, the target format is a format that can be deployed in a vehicle controller microcontroller, including but not limited to a tflite format.
[0079] Step 230: deploy the model in the target format in the single chip microcomputer of the vehicle controller to obtain a CO2 emission prediction model.
[0080] Furthermore, the model in the target format is deployed in a single-chip microcomputer of a vehicle controller such as STM32 through the tensorflowlite micro library, thereby obtaining a CO2 emission prediction model.
[0081] In this embodiment, firstly, a neural network model is built based on the long short-term memory algorithm, and the neural network model is trained; further, the format of the trained neural network model is converted into a target format to obtain a model in the target format; then, the model in the target format is deployed in the single-chip microcomputer of the vehicle controller to obtain a CO2 emission prediction model, thereby building a CO2 emission prediction model through deep learning calculation, laying the foundation for efficiently and accurately measuring the vehicle CO2 emissions.
[0082] In order to verify the accuracy of this application, four gasoline vehicles of different types that meet the National VI emission standards were selected for actual road emission tests. Each vehicle was tested twice with different driving behaviors, where different driving behaviors can be smooth driving behaviors and aggressive driving behaviors. The CO2 instantaneous emissions under smooth driving behaviors and aggressive driving behaviors were predicted using the trained CO2 emission prediction model, and the actual emissions were measured using on-board emission test equipment. A set of predicted data was randomly selected, and the actual and predicted values of CO2 instantaneous emissions were compared. Figure 2 A schematic diagram of the comparison results of the actual value and predicted value of the instantaneous CO2 emissions in the first 2000s is provided for an embodiment of the present application. Figure 2 It can be seen that the overall trend of the predicted value of CO2 instantaneous emissions and the actual emissions can be consistent, and in most of the time, the two are basically consistent. Each vehicle was tested twice, and the four vehicles were tested a total of 8 times. Figure 3 This is a comparison chart of the error between the actual total CO2 emissions and the predicted total CO2 emissions provided by an embodiment of the present application. Figure 3 It can be seen that the predicted value of total CO2 emissions is basically consistent with the measured value, with a small relative error. According to the experimental results, it can be seen that the CO2 emission prediction model has a high prediction accuracy.
[0083] In a second aspect, an embodiment of the present application also provides a vehicle CO2 emission prediction device.
[0084] In one embodiment, referring to Figure 4 , Figure 4 This is a functional module diagram of an embodiment of a vehicle CO2 emission prediction device of the present application. Figure 4As shown, the vehicle CO2 emission prediction device 400 includes:
[0085] The acquisition module 410 is used to acquire the vehicle speed and on-board diagnostic system data of the vehicle;
[0086] A determination module 420, configured to determine the acceleration of the vehicle based on the vehicle speed;
[0087] A preprocessing module 430, configured to preprocess the vehicle speed and the on-board diagnostic system data to obtain a preprocessed vehicle speed and preprocessed on-board diagnostic system data;
[0088] The input-output module 440 is used to input the acceleration, pre-processed vehicle speed and pre-processed on-board diagnostic system data into the CO2 emission prediction model and output the vehicle CO2 emission; wherein the CO2 emission prediction model is deployed in the single-chip microcomputer of the vehicle controller.
[0089] Furthermore, in one embodiment, the preprocessing module 430 is specifically used to preprocess the vehicle speed according to the following formula:
[0090] V' = log(V);
[0091] Among them, V is the vehicle speed, and V' is the vehicle speed after preprocessing.
[0092] Further, in one embodiment, the on-board diagnostic system data includes engine speed and coolant temperature, and the pre-processing module 430 is specifically used to pre-process the on-board diagnostic system data according to the following formula, and the corresponding formula is:
[0093]
[0094] Wherein, RPM is the engine speed, RPM' is the engine speed after preprocessing, CoolTemp is the coolant temperature, CoolTemp' is the coolant temperature after preprocessing, a is the first coefficient, and b is the second coefficient.
[0095] Furthermore, in one embodiment, the vehicle CO2 emission prediction device further includes a construction module, wherein the construction module is used to construct a CO2 emission prediction model. The construction process of constructing the CO2 emission prediction model includes:
[0096] Building a neural network model based on a long short-term memory algorithm and training the neural network model;
[0097] Convert the format of the trained neural network model to the target format to obtain a model in the target format;
[0098] The model in the target format is deployed in the single chip microcomputer of the vehicle controller to obtain a CO2 emission prediction model.
[0099] Furthermore, in one embodiment, the target format is a tflite format, and the single-chip microcomputer is an STM32 single-chip microcomputer.
[0100] Among them, the functional implementation of each module in the above-mentioned vehicle CO2 emission prediction device corresponds to the various steps in the above-mentioned vehicle CO2 emission prediction method embodiment, and its functions and implementation processes are no longer repeated here.
[0101] In a third aspect, an embodiment of the present application provides a vehicle CO2 emission prediction device, which may be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.
[0102] Reference Figure 5 , Figure 5 Schematic diagram of the hardware structure of the vehicle CO2 emission prediction device involved in the embodiment of the present application. In the embodiment of the present application, the vehicle CO2 emission prediction device may include a processor, a memory, a communication interface and a communication bus.
[0103] The communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.
[0104] The communication interface includes input / output (I / O) interface, physical interface and logical interface, etc., which are used to realize the interconnection of devices inside the vehicle CO2 emission prediction device, and the interface used to realize the interconnection of the vehicle CO2 emission prediction device with other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, an optical fiber interface, an ATM interface, etc.; the user device can be a display, a keyboard, etc.
[0105] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.
[0106] The processor may be a general-purpose processor, and the general-purpose processor may call the vehicle CO2 emission prediction program stored in the memory and execute the vehicle CO2 emission prediction method provided in the embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the vehicle CO2 emission prediction program is called may refer to the various embodiments of the vehicle CO2 emission prediction method of the present application, which will not be repeated here.
[0107] Those skilled in the art will understand that Figure 5 The hardware structure shown in the figure does not constitute a limitation on the present application, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.
[0108] In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium.
[0109] The computer-readable storage medium of the present application stores a vehicle CO2 emission prediction program, wherein when the vehicle CO2 emission prediction program is executed by a processor, the steps of the vehicle CO2 emission prediction method as described above are implemented.
[0110] Among them, the method implemented when the vehicle CO2 emission prediction program is executed can refer to the various embodiments of the vehicle CO2 emission prediction method of the present application, and will not be repeated here.
[0111] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.
[0112] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.
[0113] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.
[0114] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.
[0115] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.
[0116] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.
[0117] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.
Claims
1. A vehicle CO2 emission prediction method, characterized in that: The vehicle CO2 emission prediction method comprises: Get the vehicle's speed and on-board diagnostic system data; determining an acceleration of the vehicle based on the vehicle speed; Preprocessing the vehicle speed and the on-board diagnostic system data to obtain preprocessed vehicle speed and preprocessed on-board diagnostic system data; Input the acceleration, pre-processed vehicle speed and pre-processed on-board diagnostic system data into a CO2 emission prediction model to output vehicle CO2 emissions; Among them, the CO2 emission prediction model is deployed in the microcontroller of the vehicle controller.
2. The vehicle CO2 emission prediction method according to claim 1, characterized in that: The corresponding formula for preprocessing the vehicle speed is: V' = log(V); Among them, V is the vehicle speed, and V' is the vehicle speed after preprocessing.
3. The vehicle CO2 emission prediction method according to claim 1, characterized in that: The on-board diagnostic system data includes engine speed and coolant temperature. The on-board diagnostic system data is preprocessed, and the corresponding formula is: Wherein, RPM is the engine speed, RPM' is the engine speed after preprocessing, CoolTemp is the coolant temperature, CoolTemp' is the coolant temperature after preprocessing, a is the first coefficient, and b is the second coefficient.
4. The vehicle CO2 emission prediction method according to claim 1, characterized in that: The construction process of the CO2 emission prediction model includes: Building a neural network model based on a long short-term memory algorithm and training the neural network model; Convert the format of the trained neural network model to the target format to obtain a model in the target format; The model in the target format is deployed in the single chip microcomputer of the vehicle controller to obtain a CO2 emission prediction model.
5. The vehicle CO2 emission prediction method according to claim 1, characterized in that: The target format is tflite format, and the single-chip microcomputer is an STM32 single-chip microcomputer.
6. A vehicle CO2 emission prediction device, characterized in that: The vehicle CO2 emission prediction device comprises: An acquisition module, used to acquire vehicle speed and on-board diagnostic system data of the vehicle; a determination module, configured to determine an acceleration of the vehicle based on the vehicle speed; A preprocessing module, used for preprocessing the vehicle speed and the on-board diagnostic system data to obtain preprocessed vehicle speed and preprocessed on-board diagnostic system data; The input-output module is used to input the acceleration, pre-processed vehicle speed and pre-processed on-board diagnostic system data into the CO2 emission prediction model and output the vehicle CO2 emission; wherein the CO2 emission prediction model is deployed in the single-chip microcomputer of the vehicle controller.
7. The vehicle CO2 emission prediction device according to claim 6, characterized in that: The preprocessing module is specifically used to preprocess the vehicle speed according to the following formula: V' = log(V); Among them, V is the vehicle speed, and V' is the vehicle speed after preprocessing.
8. The vehicle CO2 emission prediction device according to claim 6, characterized in that: The on-board diagnostic system data includes engine speed and coolant temperature. The preprocessing module is specifically used to preprocess the on-board diagnostic system data according to the following formula, and the corresponding formula is: Wherein, RPM is the engine speed, RPM' is the engine speed after preprocessing, CoolTemp is the coolant temperature, CoolTemp' is the coolant temperature after preprocessing, a is the first coefficient, and b is the second coefficient.
9. A vehicle CO2 emission prediction device, characterized in that: The vehicle CO2 emission prediction device includes a processor, a memory, and a vehicle CO2 emission prediction program stored in the memory and executable by the processor, wherein when the vehicle CO2 emission prediction program is executed by the processor, the steps of the vehicle CO2 emission prediction method as described in any one of claims 1 to 5 are implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a vehicle CO2 emission prediction program, wherein when the vehicle CO2 emission prediction program is executed by a processor, the steps of the vehicle CO2 emission prediction method according to any one of claims 1 to 5 are implemented.