Tail gas emission control method, device and equipment and vehicle

Abstract

The invention relates to the field of intelligent vehicles, and provides a tail gas emission control method, device and equipment and a vehicle. The method comprises the following steps: acquiring tail gas change characteristics of a target vehicle and weather forecast in a preset future time period; inputting the tail gas change characteristics and the weather forecast into a pre-trained tail gas emission prediction model for analysis, and determining an emission prediction result in a preset future time period; wherein the emission prediction result is the tail gas emission range of the target vehicle in the future time period; and in the driving process of the preset future time period, according to the tail gas emission range in the preset future time period in the emission prediction result, target parameters of tail gas emission corresponding to the tail gas emission range in the preset future time period are called, and tail gas emission of a target vehicle is controlled based on the target parameters of the tail gas emission. According to the technical scheme provided by the invention, the polyhedron and weather adaptability of the prediction result generated by the model can be effectively improved, and the flexibility of tail gas emission management is improved.

Description

Technical Field

[0001] The present application relates to the field of smart vehicle technology, and in particular to an exhaust emission control method, device, equipment and vehicle. Background Art

[0002] With the continuous development and innovation of productivity and new technologies, vehicle manufacturing is constantly progressing towards intelligence. Today's vehicles are equipped with a variety of intelligent functions to help them perform assisted driving and energy conservation and emission reduction.

[0003] For energy-saving and emission-reduction related functions, especially exhaust gas purification systems, the existing technologies often treat exhaust gas based on fixed parameters and cannot adapt to complex and changing driving environments and vehicle conditions. Therefore, how to further improve the ability of vehicle exhaust gas treatment has become one of the key research focuses of technicians in related fields. Summary of the invention

[0004] In view of this, the purpose of the present application is to propose an exhaust emission control method, device, equipment and vehicle to solve the problem of single exhaust gas purification method and poor flexibility in the prior art.

[0005] Based on the above purpose, the present application provides a method for controlling exhaust emissions, comprising:

[0006] Obtain the exhaust gas change characteristics of the target vehicle and the weather forecast for a preset future period;

[0007] Input the exhaust gas variation characteristics and weather forecast into a pre-trained exhaust gas emission prediction model for analysis to determine the emission prediction result within a preset future period; wherein the emission prediction result is the exhaust gas emission range of the target vehicle within the future period;

[0008] During driving in a preset future time period, according to the exhaust emission range in the preset future time period in the emission prediction result, the target parameters of exhaust emission corresponding to the exhaust emission range in the preset future time period are retrieved, and the exhaust emission of the target vehicle is controlled based on the exhaust emission target parameters.

[0009] Optionally, the exhaust emission prediction model includes an input layer, a hidden layer and an output layer, and the exhaust emission change characteristics and weather forecast are input into the pre-trained exhaust emission prediction model for analysis to determine the emission prediction results within a preset future period, including:

[0010] The exhaust gas change characteristics and weather forecast are input into the hidden layer through the input layer to obtain the hidden layer results;

[0011] The hidden layer results are output through the output layer of the exhaust emission model to obtain the emission prediction results.

[0012] The above implementation mode, through the prediction model, not only takes into account the characteristic factors of exhaust gas changes that may exist in the target vehicle during driving, but also takes into account the impact of weather changes on exhaust gas, triggering from multiple angles to ensure the comprehensiveness and accuracy of the calculation of emission prediction results.

[0013] Optionally, the exhaust emission prediction model is determined by the following method:

[0014] Construct a preset initial model, which includes an input layer, a hidden layer, and an output layer;

[0015] Obtain exhaust gas change characteristic data and historical weather data of the target vehicle in a historical period, as well as emission results corresponding to the exhaust gas change characteristic data and historical weather data;

[0016] The exhaust gas change characteristic data and historical weather data are input into the hidden layer through the input layer for processing to obtain the processing results;

[0017] Output the processing results through the output layer of the preset initial model to obtain the training results;

[0018] Compare the training results with the emission results to determine the adjustment parameters of the preset initial model;

[0019] The preset initial model is adjusted according to the adjustment parameters to obtain the exhaust emission prediction model.

[0020] In the above implementation, different hidden layers in the pre-trained exhaust emission model process different types of data respectively, analyze the exhaust change characteristics and weather data respectively, and the obtained prediction results can also characterize the possibility of future exhaust emissions under the conditions of exhaust changes and weather influences, and can effectively and accurately analyze the exhaust emission conditions that may be generated when the vehicle is driving in the corresponding period from the exhaust change characteristics of the target vehicle and the corresponding weather forecast as the exhaust emission prediction results. The emission prediction results also conform to the exhaust emission laws of the target vehicle during driving and the exhaust emission changes caused by weather changes, and can effectively improve the versatility and weather adaptability of the prediction results generated by the model.

[0021] Optionally, the acquiring of the exhaust gas change characteristics of the target vehicle includes:

[0022] Obtain the exhaust emission data and current operating condition information of the target vehicle;

[0023] Determine the driving habit characteristics of the target user using the target vehicle based on the current working condition information;

[0024] According to driving habit characteristics and exhaust emission data, the exhaust emission change characteristics of the target vehicle are determined.

[0025] The above implementation method provides a practical solution for determining the exhaust gas change characteristics, which helps to improve the accuracy of exhaust gas prediction.

[0026] Optionally, the current operating condition information includes vehicle operating conditions and environmental operating conditions;

[0027] Determining the driving habit characteristics of the target user using the target vehicle according to the current operating condition information includes:

[0028] Based on a preset time domain analysis algorithm, the vehicle operating condition and the environmental operating condition are analyzed respectively, and the vehicle operating condition change information and the environmental operating condition change information arranged according to a preset time series are obtained respectively;

[0029] Determining a first correlation relationship between vehicle operating condition change information and environmental operating condition change information according to a preset time sequence;

[0030] The first association relationship is taken as the driving habit feature.

[0031] Using the time dimension as a medium, the vehicle operating condition change information under time domain analysis is correlated with the environmental condition change information, so as to explore how changes in environmental conditions affect the user's driving control of the vehicle, thereby accurately obtaining the user's driving habits, providing basic conditions for the subsequent determination of exhaust gas change characteristics, and helping to improve the accuracy and practicality of exhaust emission management.

[0032] Optionally, determining the exhaust gas change characteristics of the target vehicle according to the driving habit characteristics and the exhaust gas emission data includes:

[0033] Analyze the exhaust emission data based on a preset time domain analysis algorithm to obtain exhaust emission change data arranged according to a preset time series;

[0034] Determining a second correlation relationship between the exhaust emission change data and the driving habit characteristics according to a preset time series;

[0035] The second correlation is used as the exhaust gas change feature.

[0036] By linking changes in environmental conditions, vehicle operating conditions, and exhaust emissions to form a causal relationship, the exhaust emission prediction model can be effectively helped to improve its model accuracy, which in turn helps to improve the model's prediction accuracy for emission prediction results.

[0037] Optionally, the method further includes:

[0038] During the driving process in the preset future period, determine the current driving time point and determine the emission prediction result at the current driving time point;

[0039] Obtaining preset exhaust emission standards, using the exhaust emission standards to correct emission prediction results, and determining the exhaust emission adjustment amount at the current driving time point;

[0040] Determine the working parameters of the exhaust gas purifier at the current driving time point according to the exhaust gas emission adjustment amount;

[0041] According to the working parameters, the exhaust gas purifier is controlled to treat the exhaust gas.

[0042] In the above implementation, on the one hand, exhaust emission management according to the emission prediction results can effectively improve the flexibility of exhaust emissions to adapt to weather changes and user driving habits; on the other hand, corrections according to exhaust emission standards can ensure that exhaust emissions do not exceed the standards, thereby achieving the goal of energy conservation and emission reduction.

[0043] Based on the same purpose, the present application also provides an exhaust emission control device, comprising:

[0044] A data acquisition module is used to obtain the exhaust gas change characteristics of the target vehicle and the weather forecast for a preset future period;

[0045] A result prediction module is used to input the exhaust gas change characteristics and weather forecast into a pre-trained exhaust gas emission prediction model for analysis to determine the emission prediction result within a preset future period; wherein the emission prediction result is the exhaust gas emission range of the target vehicle within the future period;

[0046] The emission control module is used to retrieve the target parameters of exhaust emissions corresponding to the exhaust emission range within the preset future time period according to the exhaust emission range within the preset future time period in the emission prediction results during driving in the preset future time period, and control the exhaust emissions of the target vehicle based on the exhaust emission target parameters.

[0047] Based on the same purpose, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method provided in any embodiment of the present application when executing the program.

[0048] Based on the same purpose, the present application also provides a vehicle, which includes the above-mentioned electronic device, so that the vehicle executes the method provided in any embodiment of the present application.

[0049] As can be seen from the above, in the technical solution of the embodiment of the present application, the exhaust gas change characteristics of the target vehicle and the obtained weather forecast for the preset future period are input into the exhaust gas emission prediction model to obtain the emission prediction result of the exhaust gas in the future period. When the target vehicle is driving in the period, the exhaust gas emission management is performed according to the emission prediction result. The exhaust gas emission prediction model is trained for the exhaust gas change characteristics and weather data, which enables the model to obtain the recognition and analysis capabilities for the exhaust gas change characteristics and weather data, and can effectively and accurately analyze the exhaust gas emission conditions that may be generated when the vehicle is driving in the corresponding period from the exhaust gas change characteristics of the target vehicle and the corresponding weather forecast as the exhaust gas emission prediction result. The emission prediction result also conforms to the exhaust gas emission law of the target vehicle during driving and the exhaust gas emission changes caused by weather changes. The working parameters of the exhaust gas purifier are determined according to the emission prediction results, so that the exhaust gas purifier has a specific basis for the treatment of the exhaust gas, and these bases are related to the exhaust gas changes and weather changes of the current vehicle driving, which improves the accuracy of the exhaust gas treatment and can effectively improve the multi-faceted and weather adaptability of the prediction results generated by the model. By performing exhaust control according to the emission prediction results, corresponding adjustments can be made according to different emission patterns and weather conditions, thereby improving the flexibility of exhaust emission management. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0051] Figure 1 A schematic diagram of a process for controlling exhaust gas emissions provided in an embodiment of the present application;

[0052] Figure 2 A schematic diagram of the structure of an exhaust emission control device provided in an embodiment of the present application;

[0053] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0055] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be the usual meanings understood by people with ordinary skills in the field to which the present application belongs. The "first", "second" and similar words used in the embodiments of the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0056] Before explaining the implementation schemes of the various embodiments of the present application, a brief description of the methods of exhaust emission management in the prior art is first given. At present, for traditional power vehicles, that is, fuel vehicles, and new energy extended-range vehicles with fuel capacity, relevant exhaust gas treatment devices, such as exhaust gas purifiers, are provided on the vehicles. However, the traditional exhaust gas purification process is often based on fixed parameters and is difficult to cope with complex and changeable driving environments and vehicle conditions. Therefore, the embodiments and implementation methods of the present application propose the following methods to improve the flexibility and adaptability of exhaust gas treatment.

[0057] Figure 1 The exhaust emission control method provided in the embodiment of the present application can be applied to the case of controlling the exhaust emission of a vehicle. The exhaust emission control method provided in the embodiment of the present application can be executed by an exhaust emission control device, which can be integrated into an electronic device by means of hardware and / or software, such as integrated into a vehicle controller. Figure 1 , the method provided in the embodiment of the present application comprises the following steps:

[0058] S110, obtaining exhaust gas change characteristics of the target vehicle and a weather forecast for a preset future period.

[0059] Among them, the target vehicle can be any vehicle that needs to be exhaust gas controlled, for example, it can be a traditional energy vehicle or a new energy extended-range vehicle. The embodiment of the present application does not limit the information such as the model of the target vehicle. The exhaust gas change characteristics can be characteristic information of the target vehicle exhaust gas changing with time or the driving mode of the vehicle. The exhaust gas change characteristics can record the changes in exhaust gas emissions during the driving process of the current vehicle, such as the change in data such as particulate matter emissions and harmful gas concentrations, and can record the changes of these data with time or the driving mode of the vehicle. The preset future time period can be a certain time period when the target vehicle is driving on the way in the future. The weather forecast can be the weather condition information in the future period. The weather forecast can be directly obtained through weather software. The embodiment of the present application does not limit the method and means of obtaining the exhaust gas change characteristics and weather forecast. It can be understood that the weather has an impact on the emission of exhaust gas, for example, the change in temperature and humidity causes the combustion process of the vehicle fuel to change, and the corresponding harmful gases and particulate matter produced also have certain differences. Therefore, considering the change in weather helps to improve the accuracy of exhaust gas emission management.

[0060] S120. Input the exhaust gas variation characteristics and weather forecast into a pre-trained exhaust gas emission prediction model for analysis to determine the emission prediction result within a preset future time period; wherein the emission prediction result is the exhaust gas emission range of the target vehicle within the future time period;.

[0061] Among them, the exhaust emission prediction model can be a model pre-trained for exhaust gas change characteristic data and weather data. The model inputs exhaust gas change characteristics and weather forecasts, and outputs emission prediction results for the exhaust gas emissions of the target vehicle in a preset future period. The exhaust emission prediction model can be a pre-trained neural network model, and the embodiment of the present application does not limit the model structure of the exhaust emission model. The emission prediction result can be a prediction of the exhaust emissions of the target vehicle traveling in a preset future period. The emission prediction result is actually the result of predicting the range of exhaust emissions in the future period.

[0062] S130. During driving in a preset future time period, according to the exhaust emission range in the preset future time period in the emission prediction result, the target parameters of exhaust emission corresponding to the exhaust emission range in the preset future time period are retrieved, and the exhaust emission of the target vehicle is controlled based on the exhaust emission target parameters.

[0063] It is understandable that, since the emission prediction result can be a prediction of the exhaust emissions of the target vehicle traveling in a preset future period, the vehicle can be controlled according to the emission prediction result to control the exhaust emissions during the driving process of the corresponding future period, so that the exhaust emissions in the period meet the emission prediction result. Among them, the target parameter of the exhaust emission can be a parameter basis for controlling the exhaust emission, for example, it can be the working parameter of the exhaust purifier of the vehicle, etc., and the embodiment of the present application is not limited to this. According to the emission prediction result, the range threshold of the exhaust emission in the future period can be determined. It is understandable that there can be a preset corresponding relationship between the exhaust emission range and the corresponding working parameter of how to control the exhaust gas, and the corresponding relationship can be determined by relevant technical personnel based on a large number of experiments and pre-stored in a database or other library table. Therefore, the exhaust emission of the target vehicle can be controlled by calling the control parameters of the exhaust emission in the future period corresponding to the exhaust emission range, for example, calling the working parameters of the exhaust purifier to adjust the working mode of the exhaust purifier, etc.

[0064] In the technical solution of the embodiment of the present application, the exhaust gas change characteristics of the target vehicle and the obtained weather forecast for the preset future period are input into the exhaust gas emission prediction model to obtain the exhaust gas emission prediction result for the future period. When the target vehicle is driving in the period, the exhaust gas emission management is performed according to the emission prediction result. The exhaust gas emission prediction model is trained for the exhaust gas change characteristics and weather data, which enables the model to obtain the recognition and analysis capabilities for the exhaust gas change characteristics and weather data, and can effectively and accurately analyze the exhaust gas emission conditions that may be generated when the vehicle is driving in the corresponding period from the exhaust gas change characteristics of the target vehicle and the corresponding weather forecast as the exhaust gas emission prediction result. The emission prediction result also conforms to the exhaust gas emission law of the target vehicle during driving and the exhaust gas emission changes caused by weather changes. The working parameters of the exhaust gas purifier are determined according to the emission prediction results, so that the exhaust gas purifier has a specific basis for the treatment of the exhaust gas, and these bases are related to the exhaust gas changes and weather changes of the current vehicle driving, which improves the accuracy of the exhaust gas treatment and can effectively improve the multi-faceted and weather adaptability of the prediction results generated by the model. By performing exhaust control according to the emission prediction results, corresponding adjustments can be made according to different emission patterns and weather conditions, thereby improving the flexibility of exhaust emission management.

[0065] In the above embodiments, the exhaust emission prediction model plays a key role. The following describes how to use this exhaust emission prediction model. Compared with other prediction models, the exhaust emission prediction model mentioned in the embodiments of the present application analyzes exhaust changes and weather changes through multiple hidden layers in the model, thereby determining the law of exhaust changes and the impact of weather changes on exhaust emissions, and then determining how to affect future exhaust emissions. In an optional embodiment, the exhaust emission prediction model includes an input layer, a hidden layer, and an output layer. S120 inputs the exhaust change characteristics and weather forecasts into a pre-trained exhaust emission prediction model for analysis to determine the emission prediction results within a preset future time period, which may include:

[0066] S121. Input the exhaust gas change characteristics and weather forecast into the hidden layer through the input layer to obtain the hidden layer results.

[0067] The exhaust gas change characteristics and weather forecast are input into the hidden layer, and after calculation by each algorithm in the hidden layer, the calculation result of the hidden layer is obtained, which is also the hidden layer result.

[0068] Exemplarily, the exhaust gas change characteristics are input into the first hidden layer through the input layer to obtain the first prediction result. Among them, the exhaust emission prediction model may include multiple hidden layers, and different hidden layers may adopt different structures or algorithms, which are not limited in the embodiments of the present application. Among them, the first hidden layer is used to process the exhaust gas change characteristics, perform feature extraction and transformation operations on the exhaust gas change characteristics, so as to provide the subsequent output layer with high-level features corresponding to the exhaust gas emission changes, that is, the first prediction result.

[0069] The weather forecast is input into the second hidden layer through the input layer to obtain the second prediction result. Similar to the previous steps, the second hidden layer is used to process the weather forecast data, perform feature extraction and transformation on the weather forecast, and provide the subsequent output layer with high-level features corresponding to weather changes, that is, the second prediction result. The first prediction result and the second prediction result belong to the same hidden layer results.

[0070] S122, the hidden layer result is output through the output layer of the exhaust emission model to obtain an emission prediction result. Exemplarily, the first prediction result and the second prediction result are output through the output layer of the exhaust emission model to obtain an emission prediction result.

[0071] The first prediction result and the second prediction result are combined in the output layer of the model to obtain the final emission prediction result. The first prediction result and the second prediction result can be weighted and output. Because the neurons in each hidden layer in the model have their own weights, they are combined and processed by weighted output. For example, a bias item can be set on the basis of the weighted sum for output. Since the first hidden layer and the second hidden layer process different data types, their corresponding bias items are also different. The use of bias items can enable the neural network to better fit the data for output. For example, an activation function can be used for combination. The activation function is used to perform a nonlinear transformation on the above weighted sum result. Different activation functions can capture different types of nonlinear relationships and improve the model's ability to fit the data. The structure of the output layer can be set according to the processing methods of the two prediction results, which is not limited in the embodiments of the present application.

[0072] In the above implementation, the exhaust emission prediction model trained in advance is used to analyze the exhaust gas change characteristics and weather forecasts respectively, so as to determine the emission prediction results corresponding to the preset future time period. The exhaust emission prediction model has the ability to identify and analyze the exhaust gas change characteristics and weather data, and can effectively and accurately analyze the exhaust gas change characteristics of the target vehicle and the corresponding weather forecast to obtain the exhaust gas emissions that may be generated when the vehicle is driving in the corresponding time period as the exhaust gas emission prediction result. Different hidden layers in the pre-trained exhaust emission model process different types of data respectively, analyze the exhaust gas change characteristics and weather data respectively, and the obtained prediction results can characterize the possibility of future exhaust gas emissions under the conditions of exhaust gas changes and weather influences, not only considering the characteristic factors of exhaust gas changes that may exist in the target vehicle during driving, but also considering the impact of weather changes on exhaust gas, triggering from multiple angles to ensure the comprehensiveness and accuracy of the calculation of emission prediction results.

[0073] Before using the exhaust emission prediction model mentioned in the above embodiment, the model is first trained to enable the model to have the ability to predict exhaust emissions. During the training process, the exhaust emission change characteristic data and weather data within the historical period are used to train different hidden layers of the model respectively, so that different hidden layers can generate prediction results for exhaust gas changes and weather data respectively, and then the prediction results in the model training process are compared with the pre-marked correct results, and the parameters of the model are adjusted based on the deviation between the two. The model parameters are continuously corrected in the same way during the subsequent training process, so that the prediction results are closer and closer to the correct results. In an optional embodiment, the exhaust emission prediction model is determined by the following method:

[0074] A1. Construct a preset initial model, which includes an input layer, a hidden layer, and an output layer.

[0075] Among them, the preset initial model can be an untrained initial model, for example, it can be an untrained neural network model, which includes an input layer, a hidden layer and an output layer. Of course, the model can include multiple hidden layers, and different hidden layers are used to enable the model to obtain processing capabilities for different data after training. It should be particularly noted that the input layer, hidden layer and output layer described in this embodiment are untrained, and need to be distinguished from the input layer, hidden layer and output layer in the exhaust emission prediction model that has been trained in the aforementioned embodiment.

[0076] A2. Obtain exhaust gas change characteristic data and historical weather data of the target vehicle within a historical period, as well as emission results corresponding to the exhaust gas change characteristic data and historical weather data.

[0077] Among them, the historical period can be any time period in which the target vehicle has a driving record in the past. Just because there is a driving record in the historical period, there is exhaust emission when the vehicle is driving, and there is also exhaust change. Therefore, it is necessary to obtain the exhaust change characteristic data within the historical period and the weather data within the historical period (that is, the historical weather data). At the same time, there are subsequent emission data of the target vehicle in the future corresponding to the historical period. These subsequent emission data can be used as the emission results to mark the exhaust change characteristic data of the historical period and the prediction results corresponding to the historical weather data, that is, the emission results can be understood as the prediction results with correct labels corresponding to the exhaust change characteristic data of the historical period and the historical weather data. It is equivalent to providing the preset initial model with samples for training and / or testing and the labeled results corresponding to the samples.

[0078] A3. Input the exhaust gas change characteristic data and the historical weather data into the hidden layer through the input layer for processing to obtain a processing result.

[0079] The model may include multiple hidden layers. Exemplarily, the exhaust gas change characteristic data is input into the first hidden layer through the input layer for processing to obtain a first processing result.

[0080] The first hidden layer is trained using the exhaust gas variation characteristic data. After the exhaust gas variation characteristic data is analyzed in the first hidden layer, a corresponding processing result, that is, a first processing result, can be obtained.

[0081] The historical weather data is input into the second hidden layer through the input layer for processing to obtain a second processing result.

[0082] Similar to A3 above, the second hidden layer is trained using historical weather data. After the second hidden layer analyzes the historical weather data, a corresponding processing result, that is, a second processing result, can be obtained.

[0083] A4. Output the processing result through the output layer of the preset initial model to obtain the training result.

[0084] Through the integration of the output layer, the first processing result and the second processing result are combined and outputted to obtain a training result jointly determined by the exhaust gas change characteristic data and the historical weather data.

[0085] A5. Compare the training results with the emission results to determine the adjustment parameters of the preset initial model.

[0086] As introduced in A2, the emission results have already been marked with labels, which are used to mark the correct sample results. The training results obtained by analyzing the preset visual model in the aforementioned steps are compared with the emission results with labels. Exemplarily, the training results and the emission results can be calculated by a loss function. A loss function is a function used to measure the difference between the model prediction results and the true labels. It takes the output of the model and the correct label as input, and outputs a scalar value to represent the size of the difference. Determine the various parameters that need to be adjusted to obtain the correct result from the preset initial model, such as weights, biases, etc. Exemplarily, the parameters of the model are adjusted by gradient descent. Gradient descent is an optimization algorithm that updates model parameters based on a loss function. The parameters (injected weights and biases, etc.) are updated along the direction of the fastest decrease of the loss function (i.e., the opposite direction of the gradient) to reduce the loss value.

[0087] A6. Adjust the preset initial model according to the adjustment parameters to obtain the exhaust emission prediction model.

[0088] It should be noted that the exhaust gas change characteristic data and historical weather data within the historical period, as well as the emission results corresponding to the exhaust gas change characteristic data and historical weather data have multiple sets of sample data. After each set of data is trained on the model, various parameters can be further adjusted to make the model's prediction of exhaust emissions more and more accurate. After certain conditions are met, the training is completed, and the preset initial model is trained to become an exhaust gas emission prediction model. Of course, the so-called reaching of certain conditions can mean that all the data used for training participate in the training, or that the effect of the model has reached a certain degree of convergence, etc., and the embodiments of the present application are not limited to this.

[0089] In the above implementation, the preset initial model is trained using the exhaust gas change characteristic data and weather data of the historical period, so that the model can obtain the ability to identify and analyze the exhaust gas change characteristics and weather data, thereby training the exhaust gas emission prediction model, so that the exhaust gas emission prediction model can effectively and accurately analyze the exhaust gas change characteristics of the target vehicle and the corresponding weather forecast to obtain the exhaust gas emissions that may be generated when the vehicle is driving in the corresponding period as the exhaust gas emission prediction result. The emission prediction result also conforms to the exhaust gas emission law of the target vehicle during driving and the exhaust gas emission changes caused by weather changes, which can effectively improve the versatility and weather adaptability of the prediction results generated by the model.

[0090] As one of the input quantities of the exhaust emission prediction model, the exhaust gas variation characteristic is of great significance for exhaust emission management. In an optional implementation, the step of obtaining the exhaust gas variation characteristic of the target vehicle in S110 may include:

[0091] S111. Acquire tail gas emission data and current operating condition information of the target vehicle.

[0092] Among them, the exhaust emission data can be the specific quantitative data of the exhaust gas emitted by the target vehicle, for example, it can include but is not limited to the concentration, temperature and flow rate of harmful gases, as well as the emission of pollutants and particulate matter, etc., and the embodiments of the present application are not exhaustive here. The current operating condition information can be various operating condition information of the target vehicle currently traveling on the road, for example, it can include but is not limited to vehicle operating conditions and environmental operating conditions, etc. The vehicle operating condition can be the working condition data of the target vehicle itself, for example, it can include but is not limited to vehicle speed, steering, power output, etc. The environmental operating condition can be the environmental condition data in which the target vehicle is traveling, for example, it can include but is not limited to current weather conditions, road conditions, traffic flow and road network data, etc. The exhaust emission data can be directly obtained by various exhaust emission detection sensors arranged in the target vehicle, and the current operating condition information can also be directly or indirectly obtained by the target vehicle, which is not limited in the present application.

[0093] S112: Determine driving habit characteristics of a target user using the target vehicle based on current operating condition information.

[0094] Among them, the target user can be a person who uses the target vehicle, and the driving habit feature can be the operation preference information of the target user when driving the target vehicle, such as when to like acceleration, when to like braking, how to choose to operate the target vehicle in the face of what road conditions or environmental changes, etc. By analyzing the working condition information, it is determined what kind of working condition changes have occurred in the vehicle when the target user faces changes in road conditions and weather changes, so as to know what kind of operation orientation the target user has taken in the face of these changes in road conditions and weather changes, that is, the user's driving habits. Exemplarily, the vehicle working condition and environmental working condition of the current working condition information are corresponded in time series, that is, as time changes, what changes have occurred in the environment (road conditions and weather) around the vehicle, and what changes have occurred in the driving of the vehicle when time changes and environmental changes (such as acceleration, deceleration, and the length of time to maintain a certain speed, etc.). It is also possible to determine what kind of driving operation has occurred in the vehicle when facing different road conditions and weather, and record the user's driving operation when these road conditions and weather changes, which is equivalent to obtaining the user's driving habits.

[0095] S113. Determine the exhaust gas change characteristics of the target vehicle according to the driving habit characteristics and the exhaust gas emission data.

[0096] It is understandable that it is precisely because of the target user's operation of the target vehicle that the exhaust emissions change. Therefore, the user's driving habit characteristics and exhaust emission data are compared to determine the pattern or correspondence of the target vehicle's exhaust emissions changing with driving operations as the exhaust emission change characteristics.

[0097] In the above implementation, the driving habit characteristics of the target user using the target vehicle are determined based on the current working condition information, and the exhaust gas change characteristics are further determined based on the driving habit characteristics and the exhaust gas emission data. The determination of the user's driving habits can help the vehicle identify the user's operating habits when driving the vehicle in different working conditions, and the changes in vehicle operation are closely related to the changes in exhaust gas generation and emission, thereby inferring the change characteristics of the exhaust gas, providing a practical solution for determining the exhaust gas change characteristics, and helping to improve the accuracy of exhaust gas prediction.

[0098] Based on the above embodiments, how to determine the driving habit characteristics is explained. In an optional implementation, the current working condition information includes vehicle working conditions and environmental working conditions;

[0099] Determining the driving habit characteristics of the target user using the target vehicle according to the current operating condition information in S112 may include:

[0100] B1. Based on a preset time domain analysis algorithm, the vehicle operating condition and the environmental operating condition are analyzed respectively to obtain vehicle operating condition change information and environmental operating condition change information arranged according to a preset time series.

[0101] It is understandable that as long as the target vehicle is on the road, the vehicle operating conditions, environmental conditions and emission conditions of the vehicle are changing in real time, and on the time scale, various operating conditions and emission conditions can be compared with each other. Therefore, a preset time domain analysis algorithm is used to analyze the vehicle operating conditions, such as arranging the vehicle operating condition data in chronological order, determining a time period for calculation, i.e., an observation time window, and extracting key feature information of the vehicle operating condition data within this time period, such as mean, variance, peak value, wave crest, wave trough and crossover rate, etc. By analyzing these data, the characteristics of the vehicle operating condition changing with time can be obtained, and the vehicle operating condition change information arranged according to the preset time series can be obtained, i.e., the trend of the vehicle operating condition changing with time; similarly, the preset start-up analysis algorithm is used to analyze the environmental conditions, and the environmental condition change information arranged according to the preset time series can be obtained, i.e., the trend of the environmental conditions changing with time.

[0102] B2. Determine a first correlation between the vehicle operating condition change information and the environmental operating condition change information according to a preset time sequence; and use the first correlation as a driving habit feature.

[0103] It is understandable that changes in vehicle operating conditions will be affected by changes in environmental conditions. Changes in vehicle operating conditions and environmental conditions that occur within the same time range can be made to correspond to each other in a time series. Therefore, according to a preset time series, the vehicle operating condition change information and the environmental condition change information are associated to obtain a first association relationship that can reflect how the target user controls the target vehicle in the face of changes in environmental conditions, causing changes in the vehicle operating condition of the target vehicle. The first association relationship is used as a driving habit feature.

[0104] Specifically, the current operating condition information includes data such as vehicle speed, acceleration, and power output, and changes in these data within a certain time range can be determined. The road condition information and weather information within the corresponding time range in the current operating condition information can determine what changes have occurred in data such as vehicle speed, acceleration, and power output when the road condition information and weather information change at a certain moment within the time range. The vehicle's speed, acceleration, and power output data are all caused by the operating habits of the target user who controls the target vehicle, and therefore the driving habit characteristics of the target user are obtained.

[0105] In the above implementation, by performing time domain analysis on the vehicle operating condition and the environmental condition, the changes in the vehicle operating condition in the time dimension and the changes in the environmental condition in the time dimension are obtained respectively. Since the time dimension is consistent, the correlation between the vehicle operating condition change information and the environmental condition change information can be obtained. Through the time dimension as a medium, the vehicle operating condition change information under the time domain analysis is correlated with the environmental condition change information, so as to explore how the changes in environmental conditions affect the user's driving control of the vehicle, thereby accurately obtaining the user's driving habits, providing basic conditions for the subsequent determination of the exhaust gas change characteristics, and is conducive to improving the accuracy and practicality of exhaust emission management.

[0106] Based on the determination of the driving habit characteristics in the aforementioned implementation, it is necessary to further calculate the exhaust gas change characteristics. Then, in an optional implementation, the determination of the exhaust gas change characteristics of the target vehicle according to the driving habit characteristics and the exhaust gas emission data in S113 may include:

[0107] C1. Analyze the exhaust emission data based on a preset time domain analysis algorithm to obtain exhaust emission change data arranged according to a preset time series.

[0108] Among them, the exhaust emission data also changes with time. Through time domain analysis, the change of exhaust emission distributed according to the time dimension, that is, the exhaust emission change data, is obtained. It should be noted that the time domain analysis algorithm described in each embodiment of the present application can adopt any one of the relevant technologies, and the present application does not limit this.

[0109] C2. Determine a second correlation between the exhaust emission change data and the driving habit characteristics according to a preset time series; and use the second correlation as the exhaust emission change characteristic.

[0110] It is understandable that, similar to the aforementioned embodiment, the target user's driving habits affect his operation when driving the target vehicle, and these driving operations in turn affect the change in exhaust emissions. Because the time dimension is consistent, the second correlation between the exhaust emission change data and the driving habit characteristics can be determined as the exhaust change characteristics, that is, how the change in exhaust emissions is affected by driving habits or driving operations in the time dimension. So far, changes in environmental conditions cause users to manipulate the vehicle, resulting in changes in vehicle conditions, which to a certain extent reflects the user's driving habits, and changes in the user's control of the vehicle cause changes in exhaust emissions, thereby determining the exhaust change characteristics.

[0111] In the above implementation, the exhaust emission data is analyzed in the time domain to obtain the change of exhaust emissions over time, and the change is correlated with the driving habit characteristics in the time dimension to obtain the influence of driving habits or user operations on the change of exhaust emissions. This provides a practical solution for determining the exhaust change characteristics, and connects the changes in environmental conditions, vehicle conditions and exhaust emissions in series to form a causal relationship, which can effectively help the exhaust emission prediction model improve its model accuracy, and thus help improve the model's prediction accuracy of emission prediction results.

[0112] On the basis of the above-mentioned embodiments, exhaust gas emission is carried out based on the emission prediction results obtained by the prediction model, which has practical significance for exhaust gas emission management. In an optional embodiment, the method may also include:

[0113] S141. During driving in a preset future time period, determine the current driving time point and determine the emission prediction result at the current driving time point.

[0114] The current driving time point may be a time point at which emission prediction and exhaust gas treatment need to be continued, and may be any time within a preset future time period. During the predicted future time period, the vehicle is moving, and the emission prediction result corresponding to the driving time point is determined according to the exhaust gas emission prediction model introduced in the above-mentioned embodiments and implementation methods.

[0115] S142: Obtain a preset exhaust emission standard, use the exhaust emission standard to correct the emission prediction result, and determine the exhaust emission adjustment amount at the current driving time point.

[0116] The exhaust emission standard may be a restriction requirement for vehicle exhaust emissions (e.g., a national standard, etc.). After the emission prediction result is obtained according to the exhaust emission prediction model, exhaust emission management can actually be performed according to the emission prediction result. However, in order to prevent the situation of exceeding the exhaust emission standard, the exhaust emission standard is used to modify the emission prediction result that may exceed the standard, thereby determining how much the exhaust emission adjustment amount corresponding to the modification is reduced.

[0117] S143: Determine the operating parameters of the exhaust gas purifier at the current driving time point according to the exhaust gas emission adjustment amount.

[0118] On the basis of determining the exhaust emission adjustment amount in the aforementioned steps, determine in which working model the exhaust purifier of the target vehicle at the driving time point should work, so that the exhaust emission can meet the emission prediction results and the requirements of the exhaust emission standards. The operating parameters of the exhaust purifier may include but are not limited to the operating temperature of the purifier, the catalyst activity index, and the filtering standard of the filter material, etc., which are not exhaustively listed in the embodiments of the present application. Exemplarily, the exhaust emission adjustment amount may include the adjustment amount of particulate emissions and the adjustment amount of harmful gas emissions. It is understandable that in order to reduce particulate emissions and harmful gas emissions, the operating temperature of the exhaust purifier, the catalyst, and the working intensity index of the exhaust purifier can all be adjusted accordingly so that the reduced particulate emissions and harmful gas emissions can indeed meet the above-mentioned exhaust emission adjustment amount.

[0119] S144. Control the exhaust gas purifier to treat the exhaust gas according to the working parameters.

[0120] The working mode of the exhaust purifier is adjusted according to the working parameters determined in the above steps to treat the exhaust gas, so as to control the emission of particulate matter and toxic gases, so as to achieve comprehensive management of exhaust gas emissions.

[0121] In the above implementation, the emission prediction results and the exhaust emission standards are double limits or double guarantees for exhaust emission management. On the one hand, exhaust emission management according to the emission prediction results can effectively improve the flexibility of exhaust emissions to adapt to weather changes and user driving habits; on the other hand, corrections according to the exhaust emission standards can ensure that exhaust emissions do not exceed the standards, thereby achieving the purpose of energy conservation and emission reduction.

[0122] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the described method.

[0123] It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0124] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides an exhaust emission control device.

[0125] Figure 2 A schematic diagram of the structure of an exhaust emission control device provided in an embodiment of the present application, referring to Figure 2 The exhaust emission control device 200 includes a data acquisition module 210, a result prediction module 220 and an emission control module 230, wherein:

[0126] The data acquisition module 210 is used to acquire the exhaust gas change characteristics of the target vehicle and the weather forecast within a preset future period;

[0127] The result prediction module 220 is used to input the exhaust gas change characteristics and weather forecast into the pre-trained exhaust gas emission prediction model for analysis to determine the emission prediction result within a preset future period; wherein the emission prediction result is the exhaust gas emission range of the target vehicle within the future period;

[0128] The emission control module 230 is used to retrieve the target parameters of exhaust emissions corresponding to the exhaust emission range within the preset future time period according to the exhaust emission range within the preset future time period in the emission prediction results during driving in the preset future time period, and control the exhaust emissions of the target vehicle based on the exhaust emission target parameters.

[0129] In the technical solution of the embodiment of the present application, the exhaust gas change characteristics of the target vehicle and the obtained weather forecast for the preset future period are input into the exhaust gas emission prediction model to obtain the exhaust gas emission prediction result for the future period. When the target vehicle is driving in the period, the exhaust gas emission management is performed according to the emission prediction result. The exhaust gas emission prediction model is trained for the exhaust gas change characteristics and weather data, which enables the model to obtain the recognition and analysis capabilities for the exhaust gas change characteristics and weather data, and can effectively and accurately analyze the exhaust gas emission conditions that may be generated when the vehicle is driving in the corresponding period from the exhaust gas change characteristics of the target vehicle and the corresponding weather forecast as the exhaust gas emission prediction result. The emission prediction result also conforms to the exhaust gas emission law of the target vehicle during driving and the exhaust gas emission changes caused by weather changes. The working parameters of the exhaust gas purifier are determined according to the emission prediction results, so that the exhaust gas purifier has a specific basis for the treatment of the exhaust gas, and these bases are related to the exhaust gas changes and weather changes of the current vehicle driving, which improves the accuracy of the exhaust gas treatment and can effectively improve the multi-faceted and weather adaptability of the prediction results generated by the model. By performing exhaust control according to the emission prediction results, corresponding adjustments can be made according to different emission patterns and weather conditions, thereby improving the flexibility of exhaust emission management.

[0130] In an optional implementation, the exhaust emission prediction model includes an input layer, a hidden layer, and an output layer, and the result prediction module 220 may include:

[0131] A hidden layer result determination unit is used to input the exhaust gas change characteristics and weather forecast into the hidden layer through the input layer to obtain the hidden layer result;

[0132] The emission prediction result determination unit is used to output the hidden layer result through the output layer of the exhaust emission model to obtain the emission prediction result.

[0133] In an optional implementation, the exhaust emission control device 200 may include a model training module, and the model training module may include:

[0134] A model building unit, used to build a preset initial model, the preset initial model includes an input layer, a hidden layer and an output layer;

[0135] A sample acquisition unit, used to acquire exhaust gas change characteristic data and historical weather data of a target vehicle in a historical period, as well as emission results corresponding to the exhaust gas change characteristic data and historical weather data;

[0136] A processing result determination unit is used to input the exhaust gas change characteristic data and the historical weather data into the hidden layer through the input layer for processing to obtain a processing result;

[0137] A training result determination unit, used for outputting the processing result through an output layer of a preset initial model to obtain a training result;

[0138] An adjustment parameter determination unit, used to compare the training results with the emission results and determine the adjustment parameters of the preset initial model;

[0139] The model adjustment unit is used to adjust the preset initial model according to the adjustment parameters to obtain the exhaust emission prediction model.

[0140] In an optional implementation, the data acquisition module 210 may include:

[0141] An exhaust gas operating condition acquisition unit, used to acquire exhaust gas emission data and current operating condition information of a target vehicle;

[0142] A driving habit determination unit, used to determine the driving habit characteristics of a target user using a target vehicle according to current working condition information;

[0143] The change characteristic determination unit is used to determine the exhaust change characteristics of the target vehicle according to the driving habit characteristics and the exhaust emission data.

[0144] In an optional implementation, the current operating condition information includes vehicle operating conditions and environmental operating conditions;

[0145] The driving habit determination unit may include:

[0146] The working condition analysis subunit is used to analyze the vehicle working condition and the environmental working condition based on a preset time domain analysis algorithm, and obtain the vehicle working condition change information and the environmental working condition change information arranged according to a preset time series;

[0147] The first association relationship determination subunit determines the first association relationship between the vehicle operating condition change information and the environmental operating condition change information according to a preset time sequence; and uses the first association relationship as a driving habit feature.

[0148] In an optional implementation, the change feature determination unit may include:

[0149] An emission change determination subunit, used to analyze the exhaust emission data based on a preset time domain analysis algorithm to obtain exhaust emission change data arranged according to a preset time series;

[0150] The second correlation determination subunit is used to determine the second correlation between the exhaust emission change data and the driving habit characteristics according to a preset time sequence; and use the second correlation as the exhaust emission change characteristic.

[0151] In an optional implementation, the device 200 may further include:

[0152] A prediction result determination unit, used to determine the current driving time point during the driving process in a preset future period, and determine the emission prediction result at the current driving time point;

[0153] An emission adjustment amount determination unit, used to obtain a preset exhaust emission standard, use the exhaust emission standard to correct the emission prediction result, and determine the exhaust emission adjustment amount at the current driving time point;

[0154] A working parameter determination unit, used to determine the working parameters of the exhaust gas purifier at the current driving time point according to the exhaust gas emission adjustment amount;

[0155] The exhaust gas treatment unit is used to control the exhaust gas purifier to treat the exhaust gas according to the working parameters.

[0156] For the convenience of description, the above device is described in terms of functions divided into various modules. Of course, when implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0157] The device of the above embodiment is used to implement the corresponding exhaust emission control method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0158] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the exhaust emission control method described in any of the above embodiments is implemented.

[0159] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application, Figure 3 A specific electronic device hardware structure is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.

[0160] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0161] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0162] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0163] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0164] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0165] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0166] The electronic device of the above embodiment is used to implement the corresponding exhaust emission control method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0167] Based on the same inventive concept, corresponding to any of the above embodiments and methods, the present application further provides a vehicle, the vehicle comprising:

[0168] A memory for storing executable program codes;

[0169] A processor is used to call and run the executable program code from the memory so that the vehicle executes the method provided in any embodiment of the present application.

[0170] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the exhaust emission control method described in any of the above embodiments.

[0171] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0172] The computer instructions stored in the storage medium of the above embodiments are used to enable the computer to execute the exhaust emission control method described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0173] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application (including the claims) is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0174] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power supply / ground connection with the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform to be implemented in the embodiments of the present application (that is, these details should be fully within the scope of understanding of those skilled in the art). In the case of elaborating specific details (e.g., circuits) to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or when these specific details are changed. Therefore, these descriptions should be considered to be illustrative rather than restrictive.

[0175] Although the present application has been described in conjunction with specific embodiments of the present application, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0176] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the scope of protection of the present application.

Claims

1. A method for controlling exhaust emissions, characterized in that: The method comprises: Obtain the exhaust gas change characteristics of the target vehicle and the weather forecast for a preset future period; Input the exhaust gas variation characteristics and the weather forecast into a pre-trained exhaust gas emission prediction model for analysis to determine the emission prediction result within the preset future period; wherein the emission prediction result is the exhaust gas emission range of the target vehicle within the future period; During driving in a preset future time period, according to the exhaust emission range in the preset future time period in the emission prediction result, the target parameters of exhaust emission corresponding to the exhaust emission range in the preset future time period are retrieved, and the exhaust emission of the target vehicle is controlled based on the target parameters of exhaust emission.

2. The method according to claim 1, characterized in that The exhaust emission prediction model includes an input layer, a hidden layer and an output layer. The exhaust emission change characteristics and the weather forecast are input into the pre-trained exhaust emission prediction model for analysis to determine the emission prediction result within the preset future period, including: Inputting the exhaust gas variation characteristics and the weather forecast into the hidden layer through the input layer to obtain a hidden layer result; The hidden layer result is output through the output layer of the exhaust emission model to obtain the emission prediction result.

3. The method according to claim 1, characterized in that The tail gas emission prediction model is determined by the following method: Constructing a preset initial model, wherein the preset initial model includes an input layer, a hidden layer, and an output layer; Acquire exhaust gas change characteristic data and historical weather data of the target vehicle in a historical period, and emission results corresponding to the exhaust gas change characteristic data and the historical weather data; Inputting the exhaust gas change characteristic data and the historical weather data into the hidden layer through the input layer for processing to obtain a processing result; Outputting the processing result through the output layer of the preset initial model to obtain a training result; Comparing the training result with the emission result to determine adjustment parameters of the preset initial model; The preset initial model is adjusted according to the adjustment parameters to obtain the exhaust emission prediction model.

4. The method according to claim 1, characterized in that The step of obtaining the exhaust gas change characteristics of the target vehicle includes: Acquiring tail gas emission data and current operating condition information of the target vehicle; Determining driving habit characteristics of a target user using the target vehicle according to the current operating condition information; According to the driving habit characteristics and the exhaust emission data, the exhaust emission change characteristics of the target vehicle are determined.

5. The method according to claim 4, characterized in that The current operating condition information includes vehicle operating conditions and environmental operating conditions; The determining, based on the current operating condition information, driving habit characteristics of a target user using the target vehicle includes: Based on a preset time domain analysis algorithm, the vehicle operating condition and the environmental operating condition are analyzed respectively, and vehicle operating condition change information and environmental operating condition change information arranged according to a preset time series are obtained respectively; Determining a first correlation relationship between the vehicle operating condition change information and the environmental operating condition change information according to the preset time sequence; The first association relationship is used as a driving habit feature.

6. The method according to claim 4, characterized in that The step of determining the exhaust gas change characteristics of the target vehicle according to the driving habit characteristics and the exhaust gas emission data includes: Analyzing the exhaust emission data based on a preset time domain analysis algorithm to obtain exhaust emission change data arranged according to a preset time series; Determining a second correlation relationship between the exhaust emission change data and the driving habit characteristics according to the preset time sequence; The second correlation relationship is used as the exhaust gas change feature.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: During driving in a preset future time period, determining a current driving time point and determining the emission prediction result at the current driving time point; Obtaining a preset exhaust emission standard, using the exhaust emission standard to correct the emission prediction result, and determining an exhaust emission adjustment amount at a current driving time point; Determining the operating parameters of the exhaust gas purifier at the current driving time point according to the exhaust gas emission adjustment amount; According to the working parameters, the exhaust gas purifier is controlled to perform exhaust gas treatment.

8. An exhaust emission control device, characterized in that: The device comprises: A data acquisition module is used to obtain the exhaust gas change characteristics of the target vehicle and the weather forecast for a preset future period; A result prediction module is used to input the exhaust gas change characteristics and the weather forecast into a pre-trained exhaust gas emission prediction model for analysis to determine the emission prediction result within the preset future period; wherein the emission prediction result is the exhaust gas emission range of the target vehicle within the future period; The emission control module is used to retrieve the target parameters of exhaust emissions corresponding to the exhaust emission range within the preset future time period according to the exhaust emission range within the preset future time period in the emission prediction result during driving in the preset future time period, and control the exhaust emissions of the target vehicle based on the exhaust emission target parameters.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

10. A vehicle, characterized in that: The vehicle comprises: the electronic device as claimed in claim 9, The vehicle is enabled to execute the method according to any one of claims 1 to 7.

Images