A method, device, equipment and storage medium for constructing a DPF model

Abstract

The present application discloses a method, device, equipment and storage medium for constructing a DPF model, relating to the technical field of engine aftertreatment. The method includes: obtaining a set of historical vehicle road spectrum data, and dividing the set of historical vehicle road spectrum data into a first vehicle road spectrum data subset and a second vehicle road spectrum data subset according to a set ratio; generating a diesel particulate filter (DPF) model according to the first vehicle road spectrum data subset; adjusting the DPF model according to the second vehicle road spectrum data subset to obtain a target DPF model; predicting DPF overload warning for vehicles within N days according to the target DPF model to obtain a prediction result, and determining the vehicle overload accuracy rate of the prediction result, where N is an integer greater than 1; if the vehicle overload accuracy rate of the prediction result meets a set threshold, it is determined that the construction of the target DPF model is completed, so as to optimize the construction of the DPF model and improve the accuracy rate of DPF overload warning when using the model.

Description

Technical Field

[0001] This application relates to the technical field of engine after-treatment systems, and in particular, to a method, device, equipment, and storage medium for constructing a DPF model. Background Art

[0002] With the development of the automotive industry and the improvement of environmental protection requirements, the country's requirements for vehicle emissions are becoming increasingly stringent. More stringent requirements are put forward for the particulate emissions of diesel engines, and the limit requirements for various pollutants in emission regulations are also becoming more and more strict. As an important part of the off-engine purification system, the engine after-treatment system plays an important role in reducing the content of exhaust pollutants.

[0003] The Diesel Particulate Filter (DPF) is the most effective way to purify the particulate emissions of diesel engines. The exhaust emission substances captured by the DPF are then burned out during the operation of the vehicle, which can effectively reduce the emissions of particulate matter. Specifically, the DPF first captures the particulate matter in the exhaust gas, and then oxidizes the captured particulate matter to regenerate the DPF. DPF regeneration means that during the long-term operation of the DPF, the increase in particulate matter in the DPF will gradually cause an increase in the engine back pressure, resulting in a decline in engine performance. Therefore, the deposited particulate matter needs to be removed regularly to restore the filtering performance of the DPF.

[0004] Currently, for the constructed DPF model to perform DPF overload warning, generally, the driving and parking regeneration are recommended according to the empirical value at a certain mileage, or the carbon loading is predicted according to the carbon loading model. However, the operating conditions of actual vehicle diesel engines are very complex, and the DPF carbon loading obtained by the traditional method based on experimental calibration and constructing the DPF model has a large gap with the actual value, resulting in an inaccurate determination of the DPF regeneration timing and an error in the DPF overload warning reported by the vehicle.

[0005] Therefore, how to optimize the DPF model is an urgent problem to be solved currently. Summary of the Invention

[0006] This application provides a method for constructing a DPF model to improve the accuracy of DPF overload warning.

[0007] In a first aspect, a method for constructing a DPF model is provided, including:

[0008] Obtain a historical vehicle road spectrum data set, and divide the historical vehicle road spectrum data set into a first vehicle road spectrum data subset and a second vehicle road spectrum data subset according to a set ratio; generate a DPF model according to the first vehicle road spectrum data subset; adjust the DPF model according to the second vehicle road spectrum data subset to obtain a target DPF model; perform DPF overload warning prediction on vehicles within N days according to the target DPF model to obtain a prediction result, and determine the vehicle overload accuracy rate of the prediction result; wherein, N is an integer greater than 1; if the vehicle overload accuracy rate of the prediction result meets the set threshold, it is determined that the construction of the target DPF model is completed.

[0009] Optionally, the second vehicle road spectrum data subset includes the intake pressure value and the DPF carrier differential pressure of at least one vehicle; the DPF model includes a set overload time threshold; the adjusting the DPF model according to the second vehicle road spectrum data subset includes:

[0010] Input the intake pressure values and the DPF carrier differential pressures in the second vehicle road spectrum data subset into the DPF model, adjust the set overload time threshold of the DPF model, and determine the target overload time threshold of the DPF model.

[0011] Optionally, the method further includes:

[0012] If the vehicle overload accuracy rate of the prediction result does not meet the set threshold, expand the historical vehicle road spectrum data set, and divide the expanded historical vehicle road spectrum data set into a third vehicle road spectrum data subset and a fourth vehicle road spectrum data subset according to a set ratio; update the DPF model according to the third vehicle road spectrum data subset; adjust the updated DPF model according to the fourth vehicle road spectrum data subset to obtain an updated target DPF model.

[0013] Optionally, the performing DPF overload warning prediction on vehicles within N days according to the target DPF model to obtain a prediction result, and determining the vehicle overload accuracy rate of the prediction result includes:

[0014] Within the N days, count the number of overloaded vehicles each day, calculate the first newly added overloaded vehicle number from the (i - 1)-th day to the i-th day, and obtain the device identifiers of each first newly added overloaded vehicle on the i-th day, where i is an integer greater than 1 and less than or equal to N; according to the target DPF model, predict the second newly added overloaded vehicle number from the (i - 1)-th day to the i-th day, and obtain the device identifiers of each second newly added overloaded vehicle on the i-th day; match the device identifiers of each first newly added overloaded vehicle with the device identifiers of each second newly added overloaded vehicle to determine the target newly added overloaded vehicles with matching device identifiers and the number of target newly added overloaded vehicles, so as to obtain the prediction result on the i-th day; divide the number of target newly added overloaded vehicles by the number of first newly added overloaded vehicles to obtain the vehicle overload accuracy rate of the prediction result on the i-th day.

[0015] Optionally, after determining that the target DPF model is constructed, it further includes:

[0016] According to the target DPF model, determine the predicted value of the DPF carrier differential pressure of the target vehicle under the current intake pressure value; if the actual value of the DPF carrier differential pressure of the target vehicle is greater than the predicted value of the DPF carrier differential pressure and exceeds the target overload time threshold, then output an overload warning message, where the overload warning message is used to indicate that the vehicle is in a DPF overload state.

[0017] In a second aspect, a DPF model construction device is provided, including:

[0018] An acquisition module, configured to acquire a historical vehicle road spectrum data set and divide the historical vehicle road spectrum data set into a first vehicle road spectrum data subset and a second vehicle road spectrum data subset according to a set ratio; a DPF model generation module, configured to generate a DPF model according to the first vehicle road spectrum data subset; a DPF model adjustment module, configured to adjust the DPF model according to the second vehicle road spectrum data subset to obtain a target DPF model; a DPF model verification module, configured to perform DPF overload warning prediction on vehicles within N days according to the target DPF model to obtain a prediction result, and determine the vehicle overload accuracy rate of the prediction result; where N is an integer greater than 1; and, if the vehicle overload accuracy rate of the prediction result meets a set threshold, then determine that the target DPF model is constructed.

[0019] Optionally, the second vehicle road spectrum data subset includes the intake pressure value and the DPF carrier differential pressure of at least one vehicle; the DPF model includes a set overload time threshold; the DPF model adjustment module is specifically configured to:

[0020] Input each intake pressure value and each DPF carrier differential pressure in the second vehicle road spectrum data subset into the DPF model, adjust the overload time threshold set in the DPF model, and determine the target overload time threshold of the DPF model.

[0021] Optionally, the device further includes: a DPF model update module;

[0022] The DPF model update module is configured to, if the vehicle overload accuracy rate of the prediction result does not meet the set threshold, instruct the acquisition module to expand the historical vehicle road spectrum data set, and divide the expanded historical vehicle road spectrum data set into a third vehicle road spectrum data subset and a fourth vehicle road spectrum data subset according to a set ratio; update the DPF model according to the third vehicle road spectrum data subset; and adjust the updated DPF model according to the fourth vehicle road spectrum data subset to obtain an updated target DPF model.

[0023] Optionally, the DPF model verification module is specifically configured to:

[0024] Within the N days, respectively count the number of overloaded vehicles on each day, calculate the first newly added overloaded vehicle number from the i-th day to the (i - 1)-th day, and obtain the device identifier of each first newly added overloaded vehicle on the i-th day, where i is an integer greater than 1 and less than or equal to N; predict the second newly added overloaded vehicle number from the i-th day to the (i - 1)-th day according to the target DPF model, and obtain the device identifier of each second newly added overloaded vehicle on the i-th day; match the device identifiers of the first newly added overloaded vehicles with the device identifiers of the second newly added overloaded vehicles to determine the target newly added overloaded vehicles with matching device identifiers and the number of target newly added overloaded vehicles, and obtain the prediction result on the i-th day; divide the number of target newly added overloaded vehicles by the number of first newly added overloaded vehicles to obtain the vehicle overload accuracy rate of the prediction result on the i-th day.

[0025] Optionally, the device further includes: a DPF overload monitoring module;

[0026] The DPF overload monitoring module is configured to determine the predicted value of the DPF carrier differential pressure of the target vehicle at the current intake pressure value according to the target DPF model; if the actual value of the DPF carrier differential pressure of the target vehicle is greater than the predicted value of the DPF carrier differential pressure and exceeds the target overload time threshold, output an overload warning message, where the overload warning message is used to indicate that the vehicle is in a DPF overload state.

[0027] In a third aspect, there is provided an electronic device, including:

[0028] A memory for storing a computer program; a processor for implementing the method steps described in any one of the first aspects when executing the computer program stored on the memory.

[0029] In a fourth aspect, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps described in any one of the first aspects are implemented.

[0030] In the embodiments of the present application, after obtaining the historical vehicle road spectrum data set, the historical vehicle road spectrum data set is divided into a first vehicle road spectrum data subset and a second vehicle road spectrum data subset according to a set ratio, and then a DPF model is generated according to the obtained first vehicle road spectrum data subset. Therefore, a DPF model is fitted based on a large amount of vehicle road spectrum data (sample data), and this DPF model can cover all working condition points, improving the applicability of the DPF model. Moreover, according to the second vehicle road spectrum data subset, the DPF model is adjusted to obtain a target DPF model, optimizing the DPF model and improving the prediction accuracy of the DPF model. Further, according to the target DPF model, DPF overload warning prediction is performed on vehicles within N days to obtain a prediction result, and the vehicle overload accuracy rate of the prediction result is determined. If the vehicle overload accuracy rate of the prediction result meets the set threshold, it is determined that the construction of the target DPF model is completed. Therefore, through real vehicle verification, the performance of the target DPF model is further evaluated and reverse verified, so that when using the constructed target DPF model, the accuracy rate of DPF overload warning is improved, meeting the user experience.

[0031] For the various aspects in the second to fourth aspects above and the possible technical effects that each aspect may achieve, please refer to the description of the possible technical effects that can be achieved for the first aspect or various possible solutions in the first aspect above, and details will not be repeated here. Description of the Drawings

[0032] Figure 1 It is a flowchart of a method for constructing a DPF model provided by an embodiment of the present application;

[0033] Figure 2 It is a two-dimensional statistical distribution diagram of vehicle road spectrum data provided by an embodiment of the present application;

[0034] Figure 3 It is a logical schematic diagram of DPF model construction provided by an embodiment of the present application;

[0035] Figure 4 It is a structural schematic diagram of a DPF model construction device provided by an embodiment of the present application;

[0036] Figure 5Schematic diagram of another DPF model construction device provided by an embodiment of the present application;

[0037] Figure 6 Schematic diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0038] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings. The specific operation methods in the method embodiments can also be applied to the device embodiments or system embodiments. It should be noted that in the description of the present application, "a plurality of" is understood as "at least two". "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. The connection between A and B can represent: two situations where A is directly connected to B and A is connected to B through C. In addition, in the description of the present application, terms such as "first" and "second" are only used for the purpose of distinguishing descriptions, and cannot be understood as indicating or implying relative importance, nor can they be understood as indicating or implying order.

[0039] To better understand the embodiments of the present application, some terms in the embodiments of the present application will be explained below to facilitate understanding by those skilled in the art.

[0040] (1) Intake pressure sensor: Generally installed in the intake manifold, it senses the vacuum change in the intake manifold with different engine speeds and loads, and then converts the change in the internal resistance of the sensor into a voltage signal.

[0041] (2) DPF differential pressure sensor: Installed at both ends of the DPF to measure the DPF differential pressure value.

[0042] (3) Data fitting, also known as curve fitting, commonly known as drawing a curve, is a representation method that substitutes existing discrete data (fitting data) into a mathematical formula through mathematical methods. A number of discrete data can be obtained through methods such as sampling and experiments. Based on these data, we often hope to obtain a continuous function (that is, a curve) or a more dense discrete equation that fits the known data. This process is called fitting.

[0043] (4) Verification data is the data sample reserved during model training. When we adjust the model hyperparameters, we need to evaluate the model's ability based on it. Usually, during repeated model training, it is used to verify the current model's generalization ability (accuracy, recall rate, etc.) to determine whether to abort the training and continue.

[0044] Currently, when the vehicle reports DPF overload, it does not report DPF overload when the model accumulates statistics to a certain limit, but directly reports the DPF overload fault of the vehicle when the carbon loading calculated by the DPF differential pressure sensor is too high. However, when calibrating the vehicle bench with the model, it is impossible to fully consider abnormal situations such as vehicle driving conditions or vehicle aftertreatment equipment. When the vehicle working conditions are harsh, the carbon deposition speed of the afterprocessor is faster than the model calculation, and the DPF early warning function built into the ECU fails, resulting in the vehicle reaching the overload level earlier and reporting the DPF overload fault, which requires the driver (user) to enter the station for ash cleaning, regeneration and other treatments, affecting the user's work.

[0045] In view of this, to further illustrate the technical solutions provided by the embodiments of the present application, the following will be described in detail in combination with the accompanying drawings and specific implementation manners. Although the embodiments of the present application provide method operation steps as shown in the following embodiments or drawings, based on routine or non-creative labor, more or fewer operation steps may be included in the method. In steps where there is no necessary causal relationship logically, the execution order of these steps is not limited to the execution order provided by the embodiments of the present application. When the method is actually processed or the device executes, it can be executed or executed in parallel according to the method order shown in the embodiments or drawings.

[0046] Figure 1 It is a flowchart of a DPF model construction method provided by an embodiment of the present application, used to optimize the DPF model and improve the accuracy of DPF overload early warning. This process can be executed by a DPF model construction device, which can be implemented in software, hardware, or a combination of software and hardware. As shown in the figure, this process includes the following steps:

[0047] Step 101: Obtain a historical vehicle road spectrum data set, and divide the historical vehicle road spectrum data set into a first vehicle road spectrum data subset and a second vehicle road spectrum data subset according to a set ratio.

[0048] Optionally, the historical vehicle road spectrum data set may include vehicle road spectrum data collected within a certain period of time. For example, the historical vehicle road spectrum data set includes the vehicle road spectrum data for the whole year of 2021.

[0049] For example, after obtaining the vehicle road spectrum data for the whole year of 2021, the historical vehicle road spectrum data set from January to December can be divided into a first vehicle road spectrum data subset and a second vehicle road spectrum data subset according to a set ratio (such as 7:3, or 6:4, etc.).

[0050] This first vehicle road spectrum data subset can be called fitting data, which is convenient for subsequent fitting analysis based on sufficient vehicle road spectrum data in this first vehicle road spectrum data subset to generate a DPF model.

[0051] This second subset of vehicle road spectrum data can be referred to as verification data, which is convenient for subsequently testing, correcting, etc. the DPF model through the vehicle road spectrum data in this second subset of vehicle road spectrum data.

[0052] Optionally, the historical vehicle road spectrum data set may include the intake pressure value and the DPF carrier differential pressure of at least one vehicle, and may also include data such as engine speed and torque. The intake pressure value can specifically be collected by an intake pressure sensor, and the DPF carrier differential pressure can specifically be collected by a DPF differential pressure sensor.

[0053] It should be noted that the types, materials, etc. of the above sensors are not limited in the embodiments of the present application.

[0054] Step 102: Generate a DPF model according to the first subset of vehicle road spectrum data.

[0055] Optionally, the DPF model can be generated in the following manner: perform distribution statistics on the intake pressure value and the DPF carrier differential pressure when the vehicle is in an overloaded state and the intake pressure value and the DPF carrier differential pressure when the vehicle is in a normal state in the first subset of vehicle road spectrum data to obtain a distribution statistical result; determine the DPF model according to the distribution statistical result.

[0056] As Figure 2 shown, it is a two-dimensional statistical distribution diagram of vehicle road spectrum data provided by the embodiments of the present application. The Figure 2 abscissa (X) therein is used to represent the intake pressure value of the vehicle, and the ordinate (Y) is used to represent the DPF carrier differential pressure of the vehicle. Figure 2 A therein is used to represent the distribution of each intake pressure value and each DPF carrier differential pressure when the DPF of the vehicle is in a normal state; Figure 2 B therein is used to represent the distribution of each intake pressure value and each DPF carrier differential pressure when the DPF of the vehicle is in an overloaded state; Figure 2 C therein is used to represent the division area between the normal state and the overloaded state of the DPF of the vehicle. The division area can be analyzed to find a refined division line C, and finally a DPF model is generated. This division line can satisfy the following expression:

[0057] y = F(X)

[0058] wherein, X is the intake pressure value and Y is the DPF carrier differential pressure.

[0059] Optionally, the DPF model may further include an overload time threshold, which is used to represent that when the intake pressure value X is stable, if the predicted value of the DPF carrier differential pressure predicted by the above DPF model is less than or equal to the actual value of the DPF overload differential pressure and exceeds this overload time threshold, the DPF of the vehicle is overloaded.

[0060] Step 103: Adjust the above DPF model according to the above second vehicle road spectrum data subset to obtain a target DPF model.

[0061] The second vehicle road spectrum data subset may include the intake pressure value and the DPF carrier differential pressure of at least one vehicle. Specifically, it may include the intake pressure value and the DPF carrier differential pressure of overloaded vehicles, as well as the intake pressure value and the DPF carrier differential pressure of non-overloaded vehicles.

[0062] Optionally, the above DPF model can be adjusted in the following way: Input the intake pressure values and the DPF carrier differential pressures in the second vehicle road spectrum data subset into the DPF model, adjust the overload time threshold set in the DPF model, and determine the target overload time threshold of the DPF model. For example, input the intake pressure value and the DPF carrier differential pressure of an overloaded vehicle into the DPF model. If the predicted value of the DPF carrier differential pressure predicted by the model is less than or equal to the actual value of the input DPF carrier differential pressure and does not exceed the overload time threshold, then adjust the overload time threshold set in the DPF model to determine the target overload time threshold of the DPF model.

[0063] In some other embodiments, input the intake pressure value and the DPF carrier differential pressure of a non-overloaded vehicle into the DPF model. If the predicted value of the DPF carrier differential pressure predicted by the model is greater than the actual value of the input DPF carrier differential pressure and does not exceed the overload time threshold, then adjust the overload time threshold set in the DPF model to determine the target overload time threshold of the DPF model.

[0064] In the embodiments of the present application, after generating the DPF model according to the first vehicle road spectrum data subset, the DPF model is further corrected based on the second vehicle road spectrum data subset, which further optimizes the DPF model to obtain a target DPF model that meets the accuracy requirements.

[0065] Step 104: According to the above target DPF model, perform DPF overload early warning prediction on vehicles within N days to obtain a prediction result, and determine the vehicle overload accuracy rate of the prediction result. Wherein, N is an integer greater than 1.

[0066] Optionally, a DPF overload warning prediction is performed on vehicles within N days to obtain a prediction result, and the vehicle overload accuracy of the prediction result is determined in the following manner: within N days, the number of overloaded vehicles per day is counted respectively, and the number of the first newly added overloaded vehicles from the i-th day to the i-1th day is calculated, and the equipment identification of each first newly added overloaded vehicle on the i-th day is obtained, where i is an integer greater than 1 and less than or equal to N; according to the target DPF model, the number of the second newly added overloaded vehicles from the i-th day to the i-1th day is predicted, and the equipment identification of each second newly added overloaded vehicle on the i-th day is obtained (for example, the vehicle license plate number or the DPF identification number), the equipment identification of each first newly added overloaded vehicle is matched with the equipment identification of each second newly added overloaded vehicle, and the target newly added overloaded vehicles with matching equipment identifications and the number of target newly added overloaded vehicles are determined to obtain the prediction result for the i-th day; the target newly added overloaded vehicle number is divided by the first newly added overloaded vehicle number to obtain the vehicle overload accuracy of the prediction result. For example, the number of overloaded vehicles from September 1 to 10, 2022 is obtained, and it can also be sorted in descending order, and the number of the first newly added overloaded vehicles on September 2 from September 1 is calculated to be 174, and the equipment identification of each second newly added overloaded vehicle on September 2 is obtained, and so on; then according to the above-mentioned target DPF model, it is predicted that the number of the second newly added overloaded vehicles on September 2 from September 1 is 160, and the equipment identification of each second newly added overloaded vehicle on September 2 is obtained, and so on; the equipment identification of each first newly added overloaded vehicle on September 2 is matched with the equipment identification of each second newly added overloaded vehicle, and the target newly added overloaded vehicle with the same equipment identification as each second newly added overloaded vehicle is found from each first newly added overloaded vehicle, and the number of the target newly added overloaded vehicles (for example, 122) is obtained; finally, 122 / 174 is obtained, and the vehicle overload accuracy of the prediction result on September 2 is 70.11%. As shown in Table 1, an example table of real vehicle verification data provided by an embodiment of the present application is exemplified.

[0067] Table 1: Example of real vehicle verification data

[0068]

[0069] Step 105: Determine whether the vehicle overload accuracy of the above measurement results meets the set threshold. If so, it is determined that the target DPF model is completed. If not, it indicates that the target DPF model does not meet the design requirements, and the target DPF model can be rebuilt until it meets the design requirements.

[0070] Optionally, the target DPF model can be reconstructed in the following way: if the vehicle overload accuracy rate of the prediction result does not meet the set threshold (for example, the set threshold is greater than 75%), the historical vehicle road spectrum data set is expanded (for example, expanded to the vehicle road spectrum data from 2020 to 2021), and the expanded historical vehicle road spectrum data set is divided into a third vehicle road spectrum data subset and a fourth vehicle road spectrum data subset according to a set ratio; the DPF model is updated according to the third vehicle road spectrum data subset; and the updated DPF model is adjusted according to the fourth vehicle road spectrum data subset to obtain the updated target DPF model, thereby further ensuring the applicability of the DPF model.

[0071] In some other embodiments, after it is determined that the construction of the target DPF model is completed, it can be put into use. Specifically, according to the target DPF model, the predicted value of the DPF carrier differential pressure of the target vehicle at the current intake pressure value is determined; if the actual value of the DPF carrier differential pressure of the target vehicle is greater than the predicted value of the DPF carrier differential pressure predicted by the model and exceeds the target overload time threshold, an overload warning message is output, and the overload warning message is used to indicate that the vehicle is in a DPF overload state.

[0072] In some other embodiments, the output form of the overload warning message may specifically include voice prompts and may also include popping up a prompt window on the user interface. The prompt window can be a floating window and is displayed on the top layer. The overload warning message is displayed in the prompt window, and the overload warning message may include that there is an abnormality in the DPF of the target vehicle, the cause of the abnormality (for example, DPF overload), whether to perform a DPF regeneration operation (for the user to select), the location of the nearby maintenance service station, etc. The embodiment of the present application does not limit the output manner of the overload warning message.

[0073] Optionally, the overload warning message can be sent to the maintenance service station (which can be propagated in a broadcast manner), or the overload warning message can be sent to the user terminal device, or the overload warning message can be sent to both the maintenance service station and the user terminal device, so as to remind the user to perform a regeneration operation or remind the service station to actively contact the user to provide a regeneration service, reducing the time delay caused by vehicle overload for the user and even the increase in maintenance costs caused by damage to the post-treatment DPF component due to incorrect operation, thereby improving user satisfaction and reducing maintenance costs.

[0074] In the embodiments of the present application, after obtaining the historical vehicle road spectrum data set, the historical vehicle road spectrum data set is divided into a first vehicle road spectrum data subset and a second vehicle road spectrum data subset according to a set ratio, and then a DPF model is generated based on the obtained first vehicle road spectrum data subset. Therefore, the DPF model is fitted based on a large amount of vehicle road spectrum data (sample data), and the DPF model can cover all working condition points, improving the applicability of the DPF model. Moreover, according to the second vehicle road spectrum data subset, the DPF model is adjusted to obtain the target DPF model, optimizing the DPF model and improving the prediction accuracy of the DPF model. Furthermore, according to the target DPF model, DPF overload warning prediction is performed on vehicles within N days to obtain a prediction result, and the vehicle overload accuracy rate of the prediction result is determined. If the vehicle overload accuracy rate of the prediction result meets the set threshold, it is determined that the construction of the target DPF model is completed. Therefore, through vehicle verification, the performance of the target DPF model is further evaluated and reverse verification is performed, so that when using the constructed target DPF model, the accuracy rate of DPF overload warning is improved, meeting the user experience.

[0075] Based on the above Figure 1 , Figure 3 An exemplary logical schematic diagram of constructing a DPF model provided by the embodiments of the present application is shown. As shown in the figure, first, a historical vehicle road spectrum data set is obtained (for example, including the vehicle road spectrum data for the whole year of 2021), and the obtained vehicle road spectrum data is divided into fitting data (such as Figure 1 the data in the first vehicle road spectrum data subset in Figure 1 ), and verification data (such as

[0076] the data in the second vehicle road spectrum data subset in

[0077] Figure 4 ) according to the ratio of 7:3. The fitting data is statistically analyzed to fit the function F(X) to obtain the DPF model. Then, the DPF model is adjusted through the verification data to obtain the target DPF model that meets the accuracy requirements. Finally, vehicle verification is performed to determine whether the vehicle overload accuracy rate of the prediction result of the target DPF model meets the set threshold. If not, the vehicle road spectrum data of 2020 is expanded into the historical vehicle road spectrum data set. If so, it indicates that the construction of the target DPF is completed, and the construction ends. Figure 4 shown, the device includes: an acquisition module 401, a DPF model generation module 402, a DPF model adjustment module 403, and a DPF model verification module 404.

[0078] An acquisition module 401, configured to acquire a set of historical vehicle road spectrum data, and divide the set of historical vehicle road spectrum data into a first vehicle road spectrum data subset and a second vehicle road spectrum data subset according to a set ratio.

[0079] A DPF model generation module 402, configured to generate a DPF model according to the first vehicle road spectrum data subset.

[0080] A DPF model adjustment module 403, configured to adjust the DPF model according to the second vehicle road spectrum data subset to obtain a target DPF model.

[0081] A DPF model verification module 404, configured to perform DPF overload warning prediction on vehicles within N days according to the target DPF model to obtain a prediction result, and determine the vehicle overload accuracy rate of the prediction result; where N is an integer greater than 1; and, if the vehicle overload accuracy rate of the prediction result meets a set threshold, determine that the construction of the target DPF model is completed.

[0082] Optionally, the second vehicle road spectrum data subset includes the intake pressure value and the DPF carrier differential pressure of at least one vehicle; the DPF model includes a set overload time threshold; the DPF model adjustment module 403 is specifically configured to: input each intake pressure value and each DPF carrier differential pressure in the second vehicle road spectrum data subset into the DPF model, adjust the overload time threshold set in the DPF model, and determine the target overload time threshold of the DPF model.

[0083] Optionally, the DPF model verification module 404 is specifically configured to:

[0084] Within the N days, respectively count the number of overloaded vehicles per day, calculate the first newly added overloaded vehicle number from the i-th day to the (i - 1)-th day, and obtain the device identifier of each first newly added overloaded vehicle on the i-th day, where i is an integer greater than 1 and less than or equal to N; according to the target DPF model, predict the second newly added overloaded vehicle number from the i-th day to the (i - 1)-th day, and obtain the device identifier of each second newly added overloaded vehicle on the i-th day; match the device identifiers of the first newly added overloaded vehicles with the device identifiers of the second newly added overloaded vehicles to determine the target newly added overloaded vehicles with matching device identifiers and the number of target newly added overloaded vehicles, to obtain the prediction result on the i-th day; divide the number of target newly added overloaded vehicles by the number of first newly added overloaded vehicles to obtain the vehicle overload accuracy rate of the prediction result on the i-th day.

[0085] In some other embodiments, the structural schematic diagram of the DPF model construction device is in addition to the above Figure 4In addition to the modules shown, it may further include a DPF model update module and a DPF overload monitoring module. Figure 5 It is a schematic structural diagram of another DPF model construction device provided by an embodiment of the present application. As shown in the figure, the device includes: an acquisition module 401, a DPF model generation module 402, a DPF model adjustment module 403, a DPF model verification module 404, a DPF model update module 501, and a DPF overload monitoring module 502. Among them, the relevant descriptions of the acquisition module 401, the DPF model generation module 402, the DPF model adjustment module 403, and the DPF model verification module 404 refer to the above Figure 4 , and will not be repeated here.

[0086] The DPF model update module 501 is configured to, if the vehicle overload accuracy rate of the prediction result does not meet the set threshold, instruct the acquisition module 401 to expand the historical vehicle road spectrum data set, and divide the expanded historical vehicle road spectrum data set into a third vehicle road spectrum data subset and a fourth vehicle road spectrum data subset according to a set ratio; update the DPF model according to the third vehicle road spectrum data subset; and adjust the updated DPF model according to the fourth vehicle road spectrum data subset to obtain an updated target DPF model.

[0087] The DPF overload monitoring module 502 is configured to determine a predicted value of the DPF carrier differential pressure of the target vehicle at the current intake pressure value according to the target DPF model; if the actual value of the DPF carrier differential pressure of the target vehicle is greater than the predicted value of the DPF carrier differential pressure and exceeds the target overload time threshold, an overload warning message is output, and the overload warning message is used to indicate that the vehicle is in a DPF overload state.

[0088] It should be noted here that the above device provided by the embodiment of the present application can implement all the method steps in the embodiment of the above DPF model construction method and can achieve the same technical effects. The same parts and beneficial effects as those in the method embodiment will not be specifically described in this embodiment.

[0089] Based on the same technical concept, an electronic device is further provided in an embodiment of the present application, and the electronic device can implement the functions of the foregoing DPF model construction device.

[0090] Figure 6 It is a schematic structural diagram of the electronic device provided by the embodiment of the present application.

[0091] At least one processor 601 and a memory 602 connected to the at least one processor 601. In the embodiment of the present application, the specific connection medium between the processor 601 and the memory 602 is not limited. Figure 6Take the connection between the processor 601 and the memory 602 via the bus 600 as an example. The bus 600 is represented by a thick line in Figure 6 . The connection manners between other components are only for illustrative purposes and are not restrictive. The bus 600 can be divided into an address bus, a data bus, a control bus, etc. For the sake of easy representation, Figure 6 it is only represented by a thick line in, but it does not mean that there is only one bus or one type of bus. Alternatively, the processor 601 can also be referred to as a controller, and there is no limitation on the name.

[0092] In the embodiments of the present application, the memory 602 stores instructions executable by at least one processor 601. By executing the instructions stored in the memory 602, at least one processor 601 can execute a DPF model construction method described above. The processor 601 can implement Figure 4 or Figure 5 the functions of each module in the device shown.

[0093] Among them, the processor 601 is the control center of the device. It can connect various parts of the entire control device by using various interfaces and lines. By running or executing the instructions stored in the memory 602 and calling the data stored in the memory 602, various functions of the device and process data, so as to monitor the device as a whole.

[0094] In a possible design, the processor 601 may include one or more processing units. The processor 601 may integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, the driver interface, application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above modem processor may not be integrated into the processor 601. In some embodiments, the processor 601 and the memory 602 can be implemented on the same chip. In some embodiments, they can also be separately implemented on independent chips.

[0095] The processor 601 can be a general-purpose processor, such as a central processing unit (CPU), a digital signal processor, an application-specific integrated circuit, a field programmable gate array, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of a DPF model construction method disclosed in combination with the embodiments of the present application can be directly embodied as being executed by a hardware processor, or executed by a combination of hardware and software modules in the processor.

[0096] The memory 602, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The memory 602 can include at least one type of storage medium, for example, it can include flash memory, hard disk, multimedia card, card-type memory, random access memory (RAM), static random access memory (SRAM), programmable read-only memory (PROM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), magnetic memory, magnetic disk, optical disc, and so on. The memory 602 is any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to this. The memory 602 in the embodiments of the present application can also be a circuit or any other device capable of implementing a storage function, for storing program instructions and / or data.

[0097] By programming the design of the processor 601, the code corresponding to a DPF model construction method introduced in the foregoing embodiments can be solidified into the chip, so that the chip can execute Figure 2 a DPF model construction method of the illustrated embodiment when running. How to program the design of the processor 601 is a well-known technology to those skilled in the art and will not be elaborated here.

[0098] It should be noted here that the above-mentioned communication electronic device provided in the embodiments of the present application can implement all the method steps implemented in the above method embodiments and can achieve the same technical effects. The same parts and beneficial effects as those in the method embodiments in this embodiment will not be specifically elaborated here.

[0099] The embodiments of the present application also provide a computer-readable storage medium storing computer-executable instructions for causing a computer to execute a DPF model construction method in the above embodiments.

[0100] The embodiments of the present application also provide a computer program product, which, when called by a computer, causes the computer to execute a DPF model construction method in the above embodiments.

[0101] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0102] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable DPF model construction devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable DPF model construction devices generate means for realizing the functions specified in Figure 1 one or more of the flows Figure 1 or blocks.

[0103] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable DPF model construction device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that realize the functions specified in Figure 1 one or more of the flows Figure 1 or blocks.

[0104] These computer program instructions can also be loaded onto a computer or other programmable DPF model construction device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for realizing the functions specified in Figure 1 one or more of the flows Figure 1 or blocks.

Claims

1. A method for constructing a DPF model, characterized in that, Including: Obtain a historical vehicle road spectrum data set, and divide the historical vehicle road spectrum data set into a first vehicle road spectrum data subset and a second vehicle road spectrum data subset according to a set ratio; Generate a diesel particulate filter (DPF) model according to the first vehicle road spectrum data subset; Adjust the DPF model according to the second vehicle road spectrum data subset to obtain a target DPF model; Perform DPF overload warning prediction on vehicles within N days according to the target DPF model to obtain a prediction result, and determine the vehicle overload accuracy rate of the prediction result; where N is an integer greater than 1; If the vehicle overload accuracy rate of the prediction result meets a set threshold, determine that the construction of the target DPF model is completed; Among them, performing DPF overload warning prediction on vehicles within N days according to the target DPF model to obtain a prediction result, and determining the vehicle overload accuracy rate of the prediction result includes: Within the N days, respectively count the number of overloaded vehicles every day, calculate the first newly added overloaded vehicle number from the i-th day to the (i - 1)-th day, and obtain the equipment identifiers of each first newly added overloaded vehicle on the i-th day, where i is an integer greater than 1 and less than or equal to N; According to the target DPF model, predict the second newly added overloaded vehicle number from the i-th day to the (i - 1)-th day, and obtain the equipment identifiers of each second newly added overloaded vehicle on the i-th day; Match the equipment identifiers of the first newly added overloaded vehicles with the equipment identifiers of the second newly added overloaded vehicles to determine the target newly added overloaded vehicles with matching equipment identifiers and the number of target newly added overloaded vehicles to obtain the prediction result on the i-th day; Divide the number of target newly added overloaded vehicles by the number of first newly added overloaded vehicles to obtain the vehicle overload accuracy rate of the prediction result on the i-th day.

2. The method according to claim 1, characterized in that The second vehicle road spectrum data subset includes the intake pressure value and the DPF carrier differential pressure of at least one vehicle; the DPF model includes a set overload time threshold; Adjusting the DPF model according to the second vehicle road spectrum data subset includes: Input the intake pressure values and DPF carrier differential pressures in the second vehicle road spectrum data subset into the DPF model, adjust the overload time threshold set in the DPF model, and determine the target overload time threshold of the DPF model.

3. The method according to claim 1, wherein The method further includes: If the vehicle overload accuracy rate of the prediction result does not meet the set threshold, expand the historical vehicle road spectrum data set, and divide the expanded historical vehicle road spectrum data set into a third vehicle road spectrum data subset and a fourth vehicle road spectrum data subset according to a set ratio; Update the DPF model according to the third vehicle road spectrum data subset; Adjust the updated DPF model according to the fourth vehicle road spectrum data subset to obtain an updated target DPF model.

4. The method according to claim 2, wherein After determining that the construction of the target DPF model is completed, it further includes: According to the target DPF model, determine the predicted value of the DPF carrier differential pressure of the target vehicle under the current intake pressure value; If the actual value of the differential pressure of the DPF carrier of the target vehicle is greater than the predicted value of the differential pressure of the DPF carrier and exceeds the target overload time threshold, an overload warning message is output, and the overload warning message is used to indicate that the vehicle is in a DPF overload state.

5. A DPF model construction device, characterized in that, It includes: An acquisition module, configured to acquire a historical vehicle road spectrum data set and divide the historical vehicle road spectrum data set into a first vehicle road spectrum data subset and a second vehicle road spectrum data subset according to a set ratio; A DPF model generation module, configured to generate a diesel particulate filter (DPF) model according to the first vehicle road spectrum data subset; A DPF model adjustment module, configured to adjust the DPF model according to the second vehicle road spectrum data subset to obtain a target DPF model; A DPF model verification module, configured to perform DPF overload warning prediction on vehicles within N days according to the target DPF model to obtain a prediction result, and determine the vehicle overload accuracy rate of the prediction result; where N is an integer greater than 1; and, if the vehicle overload accuracy rate of the prediction result meets a set threshold, it is determined that the construction of the target DPF model is completed; Among them, the DPF model verification module is specifically configured to: Within the N days, respectively count the number of overloaded vehicles per day, calculate the first newly added overloaded vehicle number from the i-th day to the (i - 1)-th day, and obtain the device identifiers of each first newly added overloaded vehicle on the i-th day, where i is an integer greater than 1 and less than or equal to N; According to the target DPF model, predict the second newly added overloaded vehicle number from the i-th day to the (i - 1)-th day, and obtain the device identifiers of each second newly added overloaded vehicle on the i-th day; Match the device identifiers of the first newly added overloaded vehicles with the device identifiers of the second newly added overloaded vehicles to determine the target newly added overloaded vehicles with matching device identifiers and the number of target newly added overloaded vehicles, and obtain the prediction result on the i-th day; Divide the number of target newly added overloaded vehicles by the number of first newly added overloaded vehicles to obtain the vehicle overload accuracy rate of the prediction result on the i-th day.

6. The device according to claim 5, characterized in that The second vehicle road spectrum data subset includes the intake pressure value and the differential pressure of the DPF carrier of at least one vehicle; the DPF model includes a set overload time threshold; The DPF model adjustment module is specifically configured to: Input each intake pressure value and each differential pressure of the DPF carrier in the second vehicle road spectrum data subset into the DPF model, adjust the overload time threshold set in the DPF model, and determine the target overload time threshold of the DPF model.

7. The device according to claim 5, characterized in that The device further includes: a DPF model update module; The DPF model update module is configured to, if the vehicle overload accuracy rate of the prediction result does not meet the set threshold, instruct the acquisition module to expand the historical vehicle road spectrum data set, and divide the expanded historical vehicle road spectrum data set into a third vehicle road spectrum data subset and a fourth vehicle road spectrum data subset according to a set ratio; Update the DPF model according to the third vehicle road spectrum data subset; Adjust the updated DPF model according to the fourth vehicle road spectrum data subset to obtain an updated target DPF model.

8. The device according to claim 6, wherein The device further includes: a DPF overload monitoring module; The DPF overload monitoring module is configured to determine a predicted value of the DPF carrier differential pressure of the target vehicle at the current intake pressure value according to the target DPF model; If the actual value of the DPF carrier differential pressure of the target vehicle is greater than the predicted value of the DPF carrier differential pressure and exceeds the target overload time threshold, an overload warning message is output, and the overload warning message is used to indicate that the vehicle is in a DPF overload state.

9. An electronic device, characterized in that, Comprising: A memory for storing a computer program; A processor, when executing the computer program stored on the memory, implements the method according to any one of claims 1-4.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1-4 is implemented.

Images