Vehicle emission parameter optimization methods, systems, electronic devices and storage media

Abstract

This invention provides a method, system, electronic device, and storage medium for optimizing vehicle emission parameters. The method first collects test data from the vehicle to be calibrated and divides the test data into training data samples and test data samples. Then, it uses the training data samples to train a learning model for each emission type and uses the test data samples to test the trained learning model until a preset termination condition is met, thus obtaining an emission data prediction model for that emission type. Next, for each emission type, based on the emission data prediction model and test data, the influence weight of each control parameter on the prediction result for that emission type is obtained. Finally, based on the influence weights, the control parameters to be optimized for that emission type are determined for optimizing and / or calibrating the control parameters of the vehicle to be calibrated. This invention can shorten the calibration optimization time and improve calibration efficiency.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and in particular to a method, system, electronic device, and storage medium for optimizing vehicle emission parameters. Background Technology

[0002] Calibration is the process of optimizing software data after the engine, vehicle, system algorithms (control strategies), and peripheral components are determined, in order to achieve satisfactory vehicle performance, meet customer requirements, and comply with national standards. Vehicle performance includes drivability, power, economy, durability, environmental adaptability, and emissions. Among these, emissions performance is a mandatory indicator stipulated by national standards. Therefore, during the product development of vehicle controllers, it is necessary to conduct cyclical emissions tests according to the relevant regulations on exhaust emissions to calibrate the engine and vehicle control parameters to meet the requirements of national standards. However, vehicle emissions calibration is not only complex in terms of operating conditions, large in volume of test data, numerous control parameters, and uncertainties in the relationships between these parameters; it is also affected by various factors such as vehicle status, control parameters, and operating conditions. For example, it needs to simultaneously meet multiple standards such as PN, NOx, CO, THC, and NMHC. Therefore, emissions optimization is highly complex and difficult, requiring significant manpower and time, and is extremely dependent on the experience of engineers.

[0003] When optimizing vehicle emissions during test cycles, for areas with high levels of a certain emission (such as NOx), the common practice in existing technologies is as follows: Calibration engineers analyze the operating characteristics of the area (usually transient operating conditions with continuously changing vehicle states), determine the control parameters related to the current emissions in that area based on their own calibration experience, and adjust the combination of control parameters according to their experience to reduce the emission (such as NOx) and prevent other emissions (such as CO) from increasing significantly. Emissions tests are then repeated to observe the effect of parameter adjustments on the emission (such as NOx) and other emissions. Therefore, completing a full vehicle emissions parameter optimization often requires dozens of parameter adjustments and vehicle testing iterations. This process is not only cumbersome but also inefficient. With increasingly stringent emission requirements, emissions projects face significant challenges due to high difficulty and tight deadlines, and there is a substantial shortage of emissions equipment and human resources.

[0004] Therefore, how to provide a method for optimizing vehicle emission parameters to shorten calibration time and improve calibration efficiency has become one of the technical problems that urgently need to be solved by those skilled in the art.

[0005] It should be noted that the information disclosed in the background section of this invention is intended only to enhance the understanding of the general background of this invention, and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0006] The purpose of this invention is to address the problems of cumbersome and inefficient vehicle emission operation processes in existing technologies by providing a method, system, electronic device, and storage medium for optimizing vehicle emission parameters. This invention analyzes vehicle emission patterns by combining learning models and emission calibration, which can significantly shorten calibration optimization time, thereby improving calibration efficiency, reducing the average number of equipment resources used per project, and saving manpower and equipment resources.

[0007] To achieve the above objectives, the present invention provides a method for optimizing vehicle emission parameters, comprising:

[0008] Test data of the vehicle to be calibrated is collected and divided into training data samples and test data samples; wherein each piece of test data includes emission data and control parameters when the emission data is collected;

[0009] A learning model is constructed for each type of emission data, and the learning model is trained using the training data sample and tested using the test data sample until a preset termination condition is met, so as to obtain the emission data prediction model for that type of emission.

[0010] For each type of emission, the influence weight of each control parameter on the prediction result of that emission type is obtained based on the emission data prediction model for that emission type and the test data.

[0011] Based on the influence weights, the control parameters to be optimized for this emission type are determined in order to optimize and / or calibrate the control parameters of the vehicle to be calibrated.

[0012] Optionally, the method for collecting test data of the vehicle to be calibrated includes:

[0013] For each type of emission from the vehicle to be calibrated, a preset number of emission tests are conducted, and several test data points are collected according to a preset sample collection cycle.

[0014] The test data collected at the same time point are integrated to obtain test data for multiple sample points.

[0015] Optionally, the step of constructing a learning model for each emission type of the emission data, training the learning model using the training data samples, and testing the trained learning model using the test data samples until a preset termination condition is met, to obtain an emission data prediction model for that emission type, includes:

[0016] For each of the emission types, perform the following steps:

[0017] S210: Use the control parameters collected during the emission data collection as model input variables, use the emission data as model output variables, and determine the regression strategy and initial values ​​of the model parameters for the learning model;

[0018] S220: Input the training data samples into the learning model, obtain the prediction results of the training data samples according to the initial values ​​of the model parameters, and calculate the value of the loss function according to the prediction results of the training data samples and the emission data of the training data samples; and adjust the model parameters of the learning model according to the value of the loss function and the first preset error threshold to obtain the pre-trained learning model.

[0019] S230: Input the test data sample into the pre-trained learning model, obtain the prediction result of the test data sample, and calculate the value of the loss function based on the prediction result of the test data sample and the emission data of the test data sample; if the value of the loss function is less than or equal to the second preset error threshold, or the number of training iterations of the learning model is greater than or equal to the preset number of iterations, then the training ends, and the pre-trained learning model is used as the emission data prediction model; otherwise, adjust the model parameters of the learning model, update the initial values ​​of the model parameters of the learning model to the adjusted model parameters, and return to step S220.

[0020] Optionally, the value of the loss function is also calculated using the following formula:

[0021]

[0022] In the formula, Loss is the value of the loss function, n is the number of sample points, and C i T represents the prediction result of the emission data prediction model at the i-th sample point. i The test data refers to the emission data at the i-th sample point.

[0023] Optionally, it also includes:

[0024] Different regression strategies are selected for the learning model, and steps S220 to S230 are repeated for each regression strategy. The regression strategy that minimizes the value of the loss function is taken as the emission data prediction model. The regression strategy includes a regression method and hyperparameters.

[0025] or

[0026] Adjust the allocation ratio of the training data samples and the test data samples, and repeat steps S220 to S230 based on each allocation ratio, and use the model parameters with the minimum loss function as the model parameters of the emission data prediction model.

[0027] Optionally, obtaining the influence weight distribution of each control parameter on the prediction result of the emission type includes:

[0028] Obtain the total impact of each control parameter on the prediction result and the single-point impact of each control parameter on the prediction result;

[0029] The influence of the entire set includes: the influence weight of each control parameter on the prediction result for all the sample points;

[0030] The single-point influence includes: for each of the sample points, the influence weight of each of the control parameters on the prediction result.

[0031] Optionally, determining the control parameters to be optimized for the emission type based on the influence weight distribution includes:

[0032] For each type of emission, if the emission data for that type of emission is determined to exceed a preset emission threshold, then a number of control parameters to be adjusted are determined based on a preset optimization strategy and the influence weights of all the control parameters.

[0033] Optionally, determining a plurality of control parameters to be adjusted based on a preset optimization strategy and the influence weights of all the control parameters includes:

[0034] The control parameters are sorted according to their weight in relation to the prediction results;

[0035] Adjust the quantity according to the preset parameters, and then take the control parameter with the largest influence weight as the control parameter to be adjusted.

[0036] Optionally, before adjusting the control strategy and / or the value of the control parameter, the method further includes:

[0037] Determine whether the influence weight of the control parameter to be optimized on the entire set of emission types with the opposite mechanism to the emission type exceeds a preset influence weight threshold. If not, adjust the control strategy and / or the value of the control parameter. If so, adjust the control strategy and / or the value of the control parameter according to the influence weight of the control parameter on the emission type and the influence weight of the control parameter on emission types with the opposite mechanism to the emission type.

[0038] Optionally, based on the influence weights, the control parameters to be optimized for this emission type are determined to optimize and / or calibrate the control parameters of the vehicle to be calibrated, including:

[0039] Adjusting the control strategy of the control parameters and / or the value of the control parameters;

[0040] The adjusted control parameters are input into the emission data prediction model to obtain the adjusted prediction results, and / or directly applied to the vehicle calibration process to obtain the adjusted emission data.

[0041] Based on the adjusted prediction results and / or the adjusted emission data, the control parameters of the vehicle to be calibrated are further optimized or the calibration of the control parameters of the vehicle to be calibrated is completed.

[0042] To achieve the above objectives, the present invention also provides a vehicle emission calibration system, wherein the vehicle calibration system optimizes emission parameters using any of the vehicle emission parameter optimization methods described above, or includes a vehicle emission parameter optimization device for optimizing emission parameters; wherein the vehicle emission parameter optimization device includes:

[0043] The test data acquisition unit is configured to collect test data of the vehicle to be calibrated and divide the test data into training data samples and test data samples; wherein each piece of test data includes emission data and control parameters when the emission data is collected;

[0044] The prediction model training unit is configured to construct a learning model for each type of emission data, train the learning model using the training data samples, and test the trained learning model using the test data samples until a preset termination condition is met, so as to obtain the emission data prediction model for that type of emission.

[0045] The control parameter influence weight acquisition unit is configured to, for each type of emission, acquire the influence weight of each control parameter on the prediction result of that emission type based on the emission data prediction model for that emission type and the test data.

[0046] The emission parameter optimization unit is configured to determine the control parameters to be optimized for the emission type based on the influence weights, so as to optimize and / or calibrate the control parameters of the vehicle to be calibrated.

[0047] To achieve the above objectives, the present invention also provides an electronic device, which includes a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, it implements the vehicle emission parameter optimization method described in any of the above claims.

[0048] To achieve the above objectives, the present invention also provides a readable storage medium storing a computer program, which, when executed by a processor, implements the vehicle emission parameter optimization method described in any of the preceding claims.

[0049] Compared with existing technologies, the vehicle emission parameter optimization method, system, electronic device, and storage medium provided by this invention have the following advantages:

[0050] The vehicle emission parameter optimization method provided by this invention includes the following steps: First, test data of the vehicle to be calibrated is collected, and the test data is divided into training data samples and test data samples; wherein, each piece of test data includes emission data and control parameters when the emission data is collected; then, a learning model for each emission type of the emission data is constructed, and the learning model is trained using the training data samples and tested using the test data samples until a preset termination condition is met to obtain an emission data prediction model for that emission type; next, for each emission type, the influence weight of each control parameter on the prediction result of that emission type is obtained based on the emission data prediction model for that emission type and the test data; finally, the control parameters to be optimized for that emission type are determined based on the influence weights to optimize and / or calibrate the control parameters of the vehicle to be calibrated. With this configuration, the vehicle emission parameter optimization method provided by this invention can use the actual test data of the vehicle to be calibrated as test data, and both the training data samples and the test data samples come from the vehicle to be calibrated, thus laying a good foundation for the reliability of the emission data prediction model. Furthermore, the vehicle emission parameter optimization method provided by this invention, based on the test data, uses the emission data prediction model to learn the emission patterns of the vehicle and obtains the influence weight of the control parameters on the prediction results of emission types. This can help to quickly locate the key emission control parameters of the entire emission cycle (test and calibration) and the key emission control parameters of a single operating point (sample point), thereby significantly shortening the calibration optimization time, improving calibration efficiency, reducing the average number of equipment resources used per project, and saving manpower and equipment resources.

[0051] Since the vehicle emission calibration system, electronic equipment and storage medium provided by this invention belong to the same inventive concept as the vehicle emission parameter optimization method provided by this invention, they have at least the same beneficial effects, and will not be described in detail here. Attached Figure Description

[0052] Figure 1 This is a schematic diagram of the overall process of a vehicle emission parameter optimization method provided in one embodiment of the present invention;

[0053] Figure 2 Provided for one embodiment Figure 1 A detailed flowchart of step S100;

[0054] Figure 3 This is an example graph showing the emission data (PN number) of a vehicle in a certain test cycle;

[0055] Figure 4 Provided for one embodiment Figure 1 A detailed flowchart of step S200;

[0056] Figure 5 A specific example diagram illustrating the influence weights of all control parameters on the entire set of emissions for a given emission type;

[0057] Figure 6 A specific example diagram illustrating the influence weights of all control parameters on a single point of an emission type.

[0058] Figure 7 Provided for one embodiment Figure 1 Detailed flowchart of step S400;

[0059] Figure 8 This is a block diagram of a vehicle emission parameter optimization device provided in one embodiment of the second embodiment of the present invention;

[0060] Figure 9 This is a block diagram of the electronic device provided in Embodiment 4 of the present invention.

[0061] The reference numerals in the attached figures are as follows:

[0062] 110 - Test data acquisition unit, 120 - Prediction model training unit, 130 - Control parameter influence weight acquisition unit, 140 - Emission parameter optimization unit.

[0063] 210 - Processor, 220 - Communication interface, 230 - Memory, 240 - Communication bus. Detailed Implementation

[0064] The following detailed description, in conjunction with the accompanying drawings, further illustrates the vehicle emission parameter optimization method, system, electronic equipment, and storage medium proposed in this invention. The advantages and features of this invention will become clearer from the following description. It should be noted that the drawings are in a very simplified form and use non-precise scales, used only to facilitate and clarify the illustration of the embodiments of this invention. Please refer to the drawings to make the objectives, features, and advantages of this invention more apparent and understandable. It should be understood that the structures, proportions, sizes, etc., depicted in the accompanying drawings are only for the purpose of assisting those skilled in the art in understanding and reading the content disclosed in the specification, and are not intended to limit the implementation conditions of this invention. Any modifications to the structure, changes in proportions, or adjustments to the size, provided that the effects and objectives achieved by this invention are the same or similar, should still fall within the scope of the technical content disclosed in this invention. Specific design features of the invention disclosed herein, including, for example, specific dimensions, orientations, positions, and shapes, will be determined in part by the specific application and usage environment. Furthermore, in the embodiments described below, the same reference numerals are sometimes used across different drawings to denote the same parts or parts having the same function, omitting repeated descriptions. In this specification, similar reference numerals and letters are used to denote similar items; therefore, once an item is defined in one figure, it need not be discussed further in subsequent figures. Furthermore, if the methods described herein involve a series of steps, and the order of these steps presented herein is not necessarily the only possible order in which they can be performed, some of the described steps may be omitted and / or other steps not described herein may be added to the method.

[0065] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. The singular forms “a,” “an,” and “the” include plural objects. The term “or” is generally used to mean “and / or,” the term “several” is generally used to mean “at least one,” and the term “at least two” is generally used to mean “two or more.” Furthermore, the terms “first,” “second,” and “third” are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated.

[0066] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this invention and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0067] In the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0068] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can include direct contact between the first and second features, or contact between the first and second features through another feature between them. Furthermore, "above," "over," and "on top" of the second feature includes the first feature directly above or diagonally above the second feature, or simply indicates that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature includes the first feature directly below or diagonally below the second feature, or simply indicates that the first feature is at a lower horizontal level than the second feature.

[0069] The core idea of ​​this invention is to provide a method, system, electronic device and storage medium for optimizing vehicle emission parameters, so as to solve the problems of cumbersome and inefficient vehicle emission operation processes in the prior art.

[0070] To realize the above ideas, the inventors of this invention, through extensive investigation and research and continuous in-depth practical verification, creatively proposed a method for optimizing vehicle emission parameters by combining learning models and emission calibration to analyze the emission patterns of the whole vehicle. This method aims to shorten the calibration optimization time, improve calibration efficiency, reduce the average amount of equipment resources used per project, and alleviate the problem of insufficient manpower and equipment.

[0071] The following provides a detailed description of a method, system, electronic device, and storage medium for optimizing vehicle emission parameters proposed in this invention.

[0072] Example 1

[0073] This embodiment provides a method for optimizing vehicle emission parameters. For details, please refer to [link / reference needed]. Figure 1 The diagram illustrates the overall process of a vehicle emission parameter optimization method according to an embodiment of the present invention. Figure 1 As can be seen, the vehicle emission parameter optimization method provided in this embodiment includes:

[0074] S100: Collect test data of the vehicle to be calibrated, and divide the test data into training data samples and test data samples; wherein, each piece of test data includes emission data and control parameters when the emission data was collected;

[0075] S200: Construct a learning model for each type of emission data, train the learning model using the training data sample, and test the trained learning model using the test data sample until a preset termination condition is met, so as to obtain an emission data prediction model for that type of emission.

[0076] S300: For each type of emission, based on the emission data prediction model for that type of emission and the test data, obtain the influence weight of each control parameter on the prediction result of that type of emission;

[0077] S400: Based on the influence weight, determine the control parameters to be optimized for this emission type, so as to optimize and / or calibrate the control parameters of the vehicle to be calibrated.

[0078] With this configuration, the vehicle emission parameter optimization method provided by this invention can use the actual test data of the vehicle to be calibrated as test data. Both the training data samples and the test data samples come from the vehicle to be calibrated, thus laying a solid foundation for the reliability of the emission data prediction model. Furthermore, the vehicle emission parameter optimization method provided by this invention, based on the test data, uses the emission data prediction model to learn the emission patterns of the vehicle and obtains the influence weights of the control parameters on the prediction results of emission types. This helps to quickly locate the key emission control parameters of the entire emission cycle (testing and calibration) and the key emission control parameters of a single operating point (sample point), thereby significantly shortening the calibration optimization time, improving calibration efficiency, reducing the average number of equipment resources used per project, and saving manpower and equipment resources.

[0079] Specifically, in one preferred embodiment, the emission data includes the emission amount and / or emission concentration for each of the emission types. More specifically, the emission types include, but are not limited to, PN and NO. X The parameters include, but are not limited to, fuel injection parameters and intake parameters. Further, in other embodiments, each piece of test data may also include vehicle status, including but not limited to engine speed, engine temperature, and engine load.

[0080] Preferably, in one exemplary embodiment, please refer to Figure 2 It schematically illustrates a detailed flowchart of step S100 provided in one embodiment. From Figure 2 It can be seen that the method for collecting test data of the vehicle to be calibrated in step S100 includes:

[0081] S110: For each type of emission of the vehicle to be calibrated, conduct emission tests a preset number of times and collect several test data according to a preset sample collection cycle;

[0082] S120: Integrate the test data collected at the same time to obtain test data for multiple sample points.

[0083] Therefore, the vehicle emission parameter optimization method provided by this invention uses the actual test data of the vehicle to be calibrated as the test data, and both the training data samples and the test data samples come from the vehicle to be calibrated, thus laying a good foundation for the reliability of the emission data prediction model.

[0084] Specifically, please see Figure 3 It schematically provides an example diagram of the emission data (PN number) of the whole vehicle in a certain test cycle. Figure 3 In the graph, the horizontal axis represents the duration of the test cycle, and the vertical axis on the left represents one of the emission types. Figure 3 (Taking PN as an example) Emission data for each sample point are shown in the black bars in the figure; the right-hand vertical axis in the figure represents one of the emission types ( Figure 3 The emission data (cumulative over the entire test cycle) of the entire set (using PN as an example) is shown by the dashed line in the figure. From Figure 3 It can be seen that the emissions of PN are different at different times. Therefore, it is necessary to optimize the control parameters and reduce the emissions of this type of pollutant for sample points where the emissions exceed the limits specified in relevant regulations.

[0085] It should be specifically noted that this invention does not limit the value of the preset number of tests for different emission types. In actual data collection, the number of tests for different emission types can be the same or different, and this invention does not limit this. Furthermore, in implementing the vehicle emission parameter optimization method provided by this invention, emission data for all emission types of the vehicle to be calibrated can be collected in the same test cycle, or the emission types of the vehicle to be calibrated can be collected separately in multiple test cycles, and this invention also does not limit this. Furthermore, this invention does not limit the specific value of the preset sample collection period. In practical applications, it can be reasonably set according to specific circumstances. For example, in one embodiment, the preset sample collection period can be 0.5s, and in another embodiment, the preset sample collection period can be 1s.

[0086] As those skilled in the art will understand, the emission data and the control parameters used to collect the emission data are obtained by different acquisition elements. Therefore, as a preferred embodiment, step S120 of the vehicle emission parameter optimization method provided by the present invention, which integrates the test data at the same sample acquisition time to obtain test data for multiple sample points, specifically includes:

[0087] The emission data and control parameters of the test data collected at the same time are packaged together as the test data of that sample point. Thus, a test data sample set consisting of several test data can be obtained according to different collection times.

[0088] Furthermore, it should be specifically noted that, as those skilled in the art will understand, the vehicle emission parameter optimization method provided by this invention does not limit the operating condition type of the vehicle to be calibrated. The operating condition type includes, but is not limited to, idling, acceleration, constant speed, and deceleration conditions. Further, this invention does not limit the allocation ratio of the training data samples and test data samples. For example, in one embodiment, 80% of the test data sample set is used as the training data samples for training the learning model described below, and the remaining 20% ​​of the test data sample set is used as the test data samples for testing the learning model. In another embodiment, 85% of the test data sample set is used as the training data samples for training the learning model described below, and the remaining 15% of the test data sample set is used as the test data samples for testing the learning model.

[0089] Preferably, in one exemplary embodiment, for the specific training method of the emission data prediction model for each of the emission types, please refer to [link to documentation]. Figure 4 It schematically illustrates one embodiment of the provided... Figure 1 A detailed flowchart of step S200. From Figure 4 As can be seen, step S200, which involves constructing a learning model for each emission type of the emission data, training the learning model using the training data samples, and testing the trained learning model using the test data samples until a preset termination condition is met, to obtain an emission data prediction model for that emission type, includes:

[0090] S210: Use the control parameters collected during the emission data collection as model input variables, use the emission data as model output variables, and determine the regression strategy and initial values ​​of the model parameters for the learning model;

[0091] S220: Input the training data samples into the learning model, obtain the prediction results of the training data samples according to the initial values ​​of the model parameters, and calculate the value of the loss function according to the prediction results of the training data samples and the emission data of the training data samples; and adjust the model parameters of the learning model according to the value of the loss function and the first preset error threshold to obtain the pre-trained learning model.

[0092] S230: Input the test data sample into the pre-trained learning model, obtain the prediction result of the test data sample, and calculate the value of the loss function based on the prediction result of the test data sample and the emission data of the test data sample; if the value of the loss function is less than or equal to the second preset error threshold, or the number of training iterations of the learning model is greater than or equal to the preset number of iterations, then the training ends, and the pre-trained learning model is used as the emission data prediction model; otherwise, adjust the model parameters of the learning model, update the initial values ​​of the model parameters of the learning model to the adjusted model parameters, and return to step S220.

[0093] With this configuration, the vehicle emission parameter optimization method provided by the present invention trains an emission data prediction model based on the training data sample and the test data sample. This fully utilizes the emission data prediction model's ability to learn complex patterns and can automatically predict emission data based on the control parameters. This not only reduces the dependence of vehicle emission calibration on engineers' experience, but also significantly reduces the actual calibration operations required for the vehicle to be calibrated due to control parameter adjustments. It also reduces the average amount of equipment resources used per project and alleviates the problem of insufficient manpower and equipment.

[0094] It should be specifically noted that, as those skilled in the art will understand, the purpose of training the learning model using the training data samples is to make the prediction results of the obtained emission data prediction model as close as possible to the emission data of the training sample data. The purpose of validating the learning model using the test sample data is to improve the reliability of the obtained emission data prediction model, thereby enabling more accurate emission data prediction based on the adjusted control parameters and the emission data prediction model, thus reducing the economic, labor, and time costs of actual vehicle calibration for the vehicle to be calibrated. Furthermore, as those skilled in the art will understand, the training process of the emission data prediction model is a multi-iterative process. Therefore, the training can be terminated by setting a number of iterations; that is, when the number of training iterations of the learning model is greater than or equal to a preset number of iterations, the training of the learning model is considered complete, and the learning model at this point can be used as the emission data prediction model.

[0095] Furthermore, since the training data sample is limited, and the learning model needs to learn on a certain amount of data to achieve robustness, the training data sample can be augmented to increase robustness and thus enhance the generalization ability of the emission data prediction model. Specifically, the optimized control parameters and prediction results of the vehicle to be calibrated obtained in step S400, along with the final determined control parameters and emission data of the vehicle to be calibrated, can be used to augment the training data sample, thereby iteratively optimizing the emission data prediction model (i.e., using the emission data prediction model obtained in the previous test cycle as the initial learning model for continued training and optimization).

[0096] More specifically, as one exemplary embodiment, the method for optimizing vehicle emission parameters provided by the present invention further includes calculating the value of the loss function in step S230 using the following formula:

[0097]

[0098] In the formula, Loss is the value of the loss function, n is the number of sample points, and C i T represents the prediction result of the emission data prediction model at the i-th sample point. i The test data refers to the emission data at the i-th sample point.

[0099] As those skilled in the art will understand, the training process of a learning model is essentially a process of minimizing the loss function (evaluation function). The vehicle emission parameter optimization method provided by this invention can set a first preset error threshold and a second preset error threshold for the value of the loss function: that is, when the value of the loss function of the initially trained learning model on the training data samples is less than or equal to the first preset error threshold and the value of the loss function on the test data samples is less than or equal to the second preset error threshold, the initially trained learning model is considered to have learned the generation pattern of the emission type well, and is considered to have been trained well. The initially trained learning model obtained at this time is then used as the emission data prediction model. Therefore, the emission data prediction model provided by this invention provides reliable predictions of emission data, thus laying a good foundation for subsequently obtaining the influence weight of each control parameter on the prediction result of the emission type.

[0100] Preferably, in one exemplary embodiment, the vehicle emission parameter optimization method provided by the present invention further includes:

[0101] Different regression strategies are selected for the learning model, and steps S220 to S230 are repeated for each regression strategy. The regression strategy that minimizes the value of the loss function is taken as the emission data prediction model. The regression strategy includes a regression method and hyperparameters.

[0102] It should be specifically noted that, as those skilled in the art will understand, appropriate regression strategies (regression algorithms) and hyperparameters (different regression strategies have different hyperparameters) can be selected for the learning model (machine learning) according to actual needs. The regression algorithm is a supervised algorithm, used to establish a mapping relationship between model input variables ("control parameters," independent variables) and model output variables ("emission data," dependent variables). The training process of the learning model, after determining the regression strategy, involves constructing an algorithmic model (function) to map the attributes ("control parameters") to the labels ("emission data"). During the algorithm's learning process, it attempts to find a function that best fits the relationship between the parameters. Furthermore, this invention does not limit the regression strategy; selectable regression algorithms include, but are not limited to, linear regression, multinomial regression, and random forest regression. Moreover, the regression strategies for the emission data prediction models for different emission types can be the same or different; this invention does not impose any limitations in this regard.

[0103] Therefore, the vehicle emission parameter optimization method provided by this invention, in order to obtain a better emission data prediction model, can select different regression algorithms or different hyperparameters for each type of emission, and then compare the optimal evaluation value of the loss function of the emission data prediction model trained based on different regression strategies (e.g., the smallest value of the loss function) as the final emission data prediction model, thereby further improving the prediction accuracy of the emission data prediction model.

[0104] It should be further explained that, as those skilled in the art will understand, learning models generally have two types of parameters: one type needs to be learned and estimated from the data, called model parameters, which are the parameters of the learning model itself. For example, the weighting coefficients (slope) and the bias term (intercept) of a linear regression line are model parameters. The other type is the tuning parameters in the learning algorithm, which need to be set manually and are called hyperparameters. For example, the regularization coefficient λ, and the depth of the tree in a decision tree model.

[0105] Furthermore, as another preferred embodiment, the allocation ratio of the training data samples and the test data samples can be adjusted, and steps S220 to S230 can be repeated based on each allocation ratio, so that the model parameters with the minimum loss function are used as the model parameters of the emission data prediction model.

[0106] Preferably, in one exemplary embodiment, step S300, obtaining the influence weight distribution of each control parameter on the prediction result of the emission type, includes:

[0107] Obtain the total influence of each control parameter on the prediction result and the single-point influence of each control parameter on the prediction result; wherein, the total influence includes: the influence weight of each control parameter on the prediction result for all the sample points; the single-point influence includes: the influence weight of each control parameter on the prediction result for each sample point.

[0108] With this configuration, the vehicle emission parameter optimization method provided in this embodiment can help to quickly locate the key emission control parameters of the entire emission cycle (testing and calibration) and the key emission control parameters of a single operating point (sample point) by automatically acquiring the total impact of each control parameter on the prediction result and the single-point impact of each control parameter on the prediction result. This can significantly shorten the calibration optimization time, improve the calibration efficiency, reduce the average number of equipment resources used per project, and save manpower and equipment resources.

[0109] Specifically, please see Figure 5 and Figure 6 ,in, Figure 5 A specific example diagram illustrating the influence weights of all model input variables on the entire set of emissions for a given emission type; Figure 6 A specific example diagram illustrating the impact weights of all model input variables on the single-point effects of a particular emission type. From Figure 5 and Figure 6 It is evident that the influence weights of different model input variables differ for both the overall impact and the single-point impact. More specifically, single-point impacts are categorized as positive and negative. A positive weight for the single-point impact of a model input variable indicates that, compared to all operating points (sample points, hereinafter the same), this model input variable increases emissions at that operating point. Conversely, a negative weight indicates that, compared to all operating points, this model input variable decreases emissions at that operating point. For a given operating point, the sum of the single-point impacts of all variables reflects the emission level at that current operating point.

[0110] It should be noted that, in one preferred embodiment, the model input variables may include one or both of control parameters and vehicle status. When optimizing control parameters, the model input variables that have a greater weight in influencing the emission type and contain control parameters should be selected for adjustment.

[0111] Therefore, preferably, in one exemplary embodiment, step S400, which involves determining the control parameters to be optimized for the emission type based on the influence weight distribution, includes:

[0112] For each type of emission, if the emission data for that type of emission is determined to exceed a preset emission threshold, then a number of control parameters to be adjusted are determined based on a preset optimization strategy and the influence weights of all the control parameters.

[0113] The vehicle emission parameter optimization method provided in this embodiment automatically determines several control parameters to be adjusted based on a preset optimization strategy and the influence weights of all the control parameters. This helps to shorten calibration optimization time, improve calibration efficiency, reduce the average amount of equipment resources used per project, and alleviate the problem of insufficient manpower and equipment.

[0114] Specifically, please see Figure 7 It schematically illustrates one embodiment of the provided... Figure 1 A detailed flowchart of step S400. From Figure 7 It can be seen that step S400 determines several control parameters to be adjusted based on the preset optimization strategy and the influence weights of all the control parameters, including:

[0115] S410: Sort the control parameters according to the magnitude of their influence weight on the prediction results;

[0116] S420: Adjust the quantity according to the preset parameters, and sequentially take the control parameter with the largest influence weight as the control parameter to be adjusted.

[0117] Specifically, for ease of understanding, the following explanation uses an example where each model input variable includes control parameters. The overall effect is used to determine the total impact of each model input variable on each emission type. Throughout the test cycle, if a certain emission (e.g., NO...) x When the weight of the emission type (e.g., NOx) is high, several model input variables (i.e., control parameters) with significant weights influencing the entire set of emission types can be identified. These control parameters represent the main influencing factors for that emission type within the loop (e.g., NOx, NOx, NOx, NOx). Figure 5For variables 1 / 7 / 9 / 16 in the data, optimize the control strategy or parameter values ​​for these control parameters before the next test. For operating points with high emissions (e.g., PN), obtain the single-point impact of each variable at that operating point. Several input variables with positive and large impact weights have a significant impact on the emission (e.g., PN) and are the main influencing variables for high emissions at that point (e.g., ...). Figure 6 The variables 7 / 8 / 21 in the table are the control parameters that need to be adjusted and calibrated first.

[0118] Optionally, before adjusting the control strategy and / or the value of the control parameter, the method further includes:

[0119] Determine whether the influence weight of the control parameter to be optimized on the entire set of emission types with the opposite mechanism to the emission type exceeds a preset influence weight threshold. If not, adjust the control strategy and / or the value of the control parameter. If so, adjust the control strategy and / or the value of the control parameter according to the influence weight of the control parameter on the emission type and the influence weight of the control parameter on emission types with the opposite mechanism to the emission type.

[0120] With this configuration, the vehicle emission parameter optimization method provided in this embodiment can effectively avoid negative impacts on other emission types by adjusting the emission data of one emission type before adjusting the control parameters. This is achieved by determining whether the influence weight of the control parameter to be optimized on the entire set of emission types with the opposite mechanism to the emission type exceeds a preset influence weight threshold. This further improves the efficiency of calibration work.

[0121] For example, if a certain emission (such as NOx) is high throughout the entire test cycle, multiple model input variables with significant impact on the entire set of values ​​for that emission (such as NOx) can be identified by using the influence weight distribution. Figure 5 The variables in the table are 1 / 7 / 9 / 16. However, if there are emissions with opposite production mechanisms (such as CO), it is necessary to combine the influence weights of the entire set of variables of the emissions with opposite production mechanisms (such as CO). If the aforementioned control parameter has a relatively small impact on CO, it can be judged that the control parameter has a large impact on NOx and a small impact on CO. The control strategy or parameter value can be optimized and adjusted for the control parameter before the next test. If it also has a large impact on CO, it can be judged that the control parameter has a large impact on both NOx and CO. Adjustment should be cautious.

[0122] Preferably, please continue to see Figure 7In one exemplary embodiment, step S400 determines the control parameters to be optimized for the emission type based on the influence weights, in order to optimize and / or calibrate the control parameters of the vehicle to be calibrated, including:

[0123] S430: Adjust the control strategy of the control parameters and / or the value of the control parameters;

[0124] S440: Input the adjusted control parameters into the emission data prediction model to obtain the adjusted prediction results, and / or directly apply them to the vehicle calibration process to obtain the adjusted emission data;

[0125] S450: Based on the adjusted prediction results and / or the adjusted emission data, continue to optimize the control parameters of the vehicle to be calibrated or complete the calibration of the control parameters of the vehicle to be calibrated.

[0126] Therefore, the vehicle emission parameter optimization method provided in this embodiment adjusts the control strategy and / or the values ​​of the control parameters; the adjusted control parameters are then input into the emission data prediction model to obtain the adjusted prediction results, and / or directly applied to the vehicle calibration process to obtain the adjusted emission data. Finally, based on the adjusted prediction results and / or the adjusted emission data, the control parameters of the vehicle to be calibrated are further optimized or the calibration of the control parameters of the vehicle to be calibrated is completed. This iterative optimization of the emission data prediction model and the combination of the learning model with calibration can further shorten the calibration optimization time, improve calibration efficiency, reduce the average number of equipment resources used per project, and save manpower and equipment resources.

[0127] It should be noted that, as those skilled in the art will understand, although the above embodiments are described using emission cycle testing and calibration as an example to illustrate the vehicle emission parameter optimization method provided by the present invention, it is obvious that the vehicle emission parameter optimization method provided by the present invention is not limited to emission cycle testing and calibration, but can also be applied to emission calibration under other operating conditions.

[0128] Example 2

[0129] Based on the same inventive concept, this embodiment provides a vehicle emission calibration system. The vehicle emission calibration system provided in this embodiment optimizes emission parameters using the vehicle emission parameter optimization method described in any embodiment one, or includes a vehicle emission parameter optimization device for optimizing emission parameters. Specifically, please refer to... Figure 8 A schematic block diagram of a vehicle emission parameter optimization device according to one embodiment is shown. Figure 8As can be seen, the vehicle emission parameter optimization device includes: a test data acquisition unit 110, a prediction model training unit 120, a control parameter influence weight acquisition unit 130, and an emission parameter optimization unit 140.

[0130] Specifically, the test data acquisition unit 110 is configured to collect test data of the vehicle to be calibrated and divide the test data into training data samples and test data samples; wherein each piece of test data includes emission data and control parameters when the emission data was collected. The prediction model training unit 120 is configured to construct a learning model for each emission type of the emission data, train the learning model using the training data samples, and test the trained learning model using the test data samples until a preset termination condition is met, so as to obtain an emission data prediction model for that emission type. The control parameter influence weight acquisition unit 130 is configured to, for each emission type, obtain the influence weight of each control parameter on the prediction result of that emission type based on the emission data prediction model for that emission type and the test data. The emission parameter optimization unit 140 is configured to determine the control parameters to be optimized for that emission type based on the influence weights, so as to optimize and / or calibrate the control parameters of the vehicle to be calibrated.

[0131] Since the vehicle emission calibration system provided in this embodiment is similar in basic principle to the vehicle emission parameter optimization method provided in Embodiment 1 of this invention, the description is relatively brief. For detailed information on the vehicle emission parameter optimization device, please refer to the relevant description in Embodiment 1. Therefore, the vehicle emission calibration system provided by this invention can use the actual test data of the vehicle to be calibrated as test data. Both the training data samples and the test data samples come from the vehicle to be calibrated, thus laying a good foundation for the reliability of the emission data prediction model. Furthermore, the vehicle emission calibration system provided by this invention, based on the test data, uses the emission data prediction model to learn the emission patterns of the vehicle and obtains the influence weights of the control parameters on the prediction results of emission types. This helps to quickly locate the key emission control parameters of the entire emission cycle (testing and calibration) and the key emission control parameters of a single operating point (sample point), thereby significantly shortening the calibration optimization time, improving calibration efficiency, reducing the average number of equipment resources used per project, and saving manpower and equipment resources.

[0132] Example 3

[0133] This embodiment provides an electronic device; please refer to [reference needed]. Figure 9 The diagram illustrates a block structure of an electronic device according to an embodiment of the present invention. Figure 9As shown, the electronic device includes a processor 210 and a memory 230. The memory 230 stores a computer program. When the computer program is executed by the processor 210, it implements the vehicle emission parameter optimization method described above. Since the electronic device provided in this embodiment and the vehicle emission parameter optimization method provided in Embodiment 1 above belong to the same inventive concept, they have at least the same beneficial effects. To avoid redundancy, they will not be listed here. Please refer to the relevant description in Embodiment 1 above for details.

[0134] Specifically, such as Figure 9 As shown, the electronic device also includes a communication interface 220 and a communication bus 240, wherein the processor 210, the communication interface 220, and the memory 230 communicate with each other via the communication bus 240. The communication bus 240 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus 240 can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not indicate that there is only one bus or one type of bus. The communication interface 220 is used for communication between the aforementioned electronic device and other devices.

[0135] The processor 210 referred to in this invention can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor 210 is the control center of the electronic device, connecting various parts of the entire electronic device through various interfaces and lines.

[0136] The memory 230 can be used to store the computer program. The processor 210 implements various functions of the electronic device by running or executing the computer program stored in the memory 230 and calling the data stored in the memory 230.

[0137] The memory 230 may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0138] Example 4

[0139] Based on the same inventive concept, this embodiment provides a readable storage medium storing a computer program, which, when executed by a processor, can implement the vehicle emission parameter optimization method described above.

[0140] The readable storage medium of this embodiment can be any combination of one or more computer-readable media. The readable medium can be a computer-readable signal medium or a computer-readable storage medium. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable computer hard disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device.

[0141] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0142] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0143] In summary, compared with the prior art, the vehicle emission parameter optimization method, system, electronic device and storage medium provided by the present invention have the following advantages:

[0144] It should be noted that the apparatus and methods disclosed in the embodiments herein can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments herein. In this regard, each block in a flowchart or block diagram may represent a module, program, or part of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system to perform the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0145] In addition, the functional modules in the various embodiments of this article can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0146] The above description is merely a description of preferred embodiments of the present invention and is not intended to limit the scope of the invention in any way. Any changes or modifications made by those skilled in the art based on the above disclosure are within the protection scope of the present invention. Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the present invention and its equivalents, the present invention also intends to include these modifications and variations.

Claims

1. A method for optimizing vehicle emission parameters, characterized in that, include: Test data of the vehicle to be calibrated is collected and divided into training data samples and test data samples; wherein each piece of test data includes emission data and control parameters when the emission data is collected; A learning model is constructed for each type of emission data, and the learning model is trained using the training data sample and tested using the test data sample until a preset termination condition is met, so as to obtain the emission data prediction model for that type of emission. For each type of emission, the influence weight of each control parameter on the prediction result of that emission type is obtained based on the emission data prediction model for that emission type and the test data. Based on the influence weights, the control parameters to be optimized for this type of emission are determined in order to optimize and / or calibrate the control parameters of the vehicle to be calibrated. The step of determining the control parameters to be optimized for the emission type based on the influence weights includes: for each emission type, if it is determined that the emission data of the emission type exceeds a preset emission threshold, then a number of control parameters to be adjusted are determined based on a preset optimization strategy and the influence weights of all the control parameters.

2. The method for optimizing vehicle emission parameters according to claim 1, characterized in that, The method for collecting test data from the vehicle to be calibrated includes: For each type of emission from the vehicle to be calibrated, a preset number of emission tests are conducted, and several test data points are collected according to a preset sample collection cycle. The test data collected at the same time point are integrated to obtain test data for multiple sample points.

3. The method for optimizing vehicle emission parameters according to claim 2, characterized in that, The process of constructing a learning model for each emission type of the emission data, training the learning model using the training data samples, and testing the trained learning model using the test data samples, until a preset termination condition is met, to obtain an emission data prediction model for that emission type, includes: For each of the emission types, perform the following steps: S210: Use the control parameters collected when collecting the emission data as model input variables, use the emission data as model output variables, and determine the regression strategy and initial values ​​of the model parameters of the learning model; S220: Input the training data samples into the learning model, obtain the prediction results of the training data samples according to the initial values ​​of the model parameters, and calculate the value of the loss function according to the prediction results of the training data samples and the emission data of the training data samples; and adjust the model parameters of the learning model according to the value of the loss function and the first preset error threshold to obtain the pre-trained learning model. S230: Input the test data sample into the pre-trained learning model, obtain the prediction result of the test data sample, and calculate the value of the loss function based on the prediction result of the test data sample and the emission data of the test data sample; if the value of the loss function is less than or equal to the second preset error threshold, or the number of training iterations of the learning model is greater than or equal to the preset number of iterations, then the training ends, and the pre-trained learning model is used as the emission data prediction model; otherwise, adjust the model parameters of the learning model, update the initial values ​​of the model parameters of the learning model to the adjusted model parameters, and return to step S220.

4. The method for optimizing vehicle emission parameters according to claim 3, characterized in that, It also includes calculating the value of the loss function using the following formula: In the formula, The value of the loss function, The number of sample points. For the emission data prediction model in the first... The prediction results for each of the sample points For the test data in the first Emission data for each of the sample points.

5. The method for optimizing vehicle emission parameters according to claim 3, characterized in that, Also includes: Different regression strategies are selected for the learning model, and steps S220 to S230 are repeated for each regression strategy. The regression strategy that minimizes the value of the loss function is taken as the emission data prediction model. The regression strategy includes a regression method and hyperparameters. or Adjust the allocation ratio of the training data samples and the test data samples, and repeat steps S220 to S230 based on each allocation ratio, and use the model parameters with the minimum loss function as the model parameters of the emission data prediction model.

6. The method for optimizing vehicle emission parameters according to claim 1, characterized in that, The step of obtaining the influence weight of each control parameter on the prediction result of the emission type includes: Obtain the total impact of each control parameter on the prediction result and the single-point impact of each control parameter on the prediction result; The influence of the entire set includes: the influence weight of each control parameter on the prediction result for all the sample points; The single-point influence includes: for each of the sample points, the influence weight of each of the control parameters on the prediction result.

7. The method for optimizing vehicle emission parameters according to claim 1, characterized in that, The step of determining several control parameters to be adjusted based on a preset optimization strategy and the influence weights of all the control parameters includes: The control parameters are sorted according to their weight in relation to the prediction results; Adjust the quantity according to the preset parameters, and then take the control parameter with the largest influence weight as the control parameter to be adjusted.

8. The method for optimizing vehicle emission parameters according to claim 7, characterized in that, Before adjusting the control strategy and / or the value of the control parameters, the method further includes: Determine whether the influence weight of the control parameter to be optimized on the entire set of emission types with the opposite mechanism to the emission type exceeds a preset influence weight threshold. If not, adjust the control strategy and / or the value of the control parameter. If so, adjust the control strategy and / or the value of the control parameter according to the influence weight of the control parameter on the emission type and the influence weight of the control parameter on emission types with the opposite mechanism to the emission type.

9. The method for optimizing vehicle emission parameters according to claim 1, characterized in that, The step of determining the control parameters to be optimized for the emission type based on the influence weight, in order to optimize and / or calibrate the control parameters of the vehicle to be calibrated, includes: Adjusting the control strategy of the control parameters and / or the value of the control parameters; The adjusted control parameters are input into the emission data prediction model to obtain the adjusted prediction results, and / or directly applied to the vehicle calibration process to obtain the adjusted emission data. Based on the adjusted prediction results and / or the adjusted emission data, the control parameters of the vehicle to be calibrated are further optimized or the calibration of the control parameters of the vehicle to be calibrated is completed.

10. A vehicle emission calibration system, characterized in that, The vehicle emission parameter optimization is performed using the vehicle emission parameter optimization method as described in any one of claims 1-9, or by using a vehicle emission parameter optimization device; wherein the vehicle emission parameter optimization device includes: The test data acquisition unit is configured to collect test data of the vehicle to be calibrated and divide the test data into training data samples and test data samples; wherein each piece of test data includes emission data and control parameters when the emission data is collected; The prediction model training unit is configured to construct a learning model for each type of emission data, train the learning model using the training data samples, and test the trained learning model using the test data samples until a preset termination condition is met, so as to obtain the emission data prediction model for that type of emission. The control parameter influence weight acquisition unit is configured to, for each type of emission, acquire the influence weight of each control parameter on the prediction result of that emission type based on the emission data prediction model for that emission type and the test data. An emission parameter optimization unit is configured to determine the control parameters to be optimized for the emission type based on the influence weights, so as to optimize and / or calibrate the control parameters of the vehicle to be calibrated; wherein, determining the control parameters to be optimized for the emission type based on the influence weights includes: for each emission type, if it is determined that the emission data of the emission type exceeds a preset emission threshold, then determining a number of control parameters to be adjusted based on a preset optimization strategy and the influence weights of all the control parameters.

11. An electronic device, characterized in that, It includes a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, it implements the vehicle emission parameter optimization method according to any one of claims 1 to 9.

12. A readable storage medium, characterized in that, The readable storage medium stores a computer program, which, when executed by a processor, implements the vehicle emission parameter optimization method according to any one of claims 1 to 9.

Images