Pollutant emission data prediction method, medium, equipment, vehicle and product

Abstract

The invention relates to a pollutant emission data prediction method, a medium, equipment, a vehicle and a product, and the method comprises the steps: inputting the vehicle actual operation data of a to-be-predicted vehicle and the engine steady-state emission data corresponding to the vehicle actual operation data into an emission prediction model corresponding to the vehicle working condition type of the to-be-predicted vehicle, and obtaining pollutant emission data of the to-be-predicted vehicle output by the emission prediction model. According to the method, the vehicle actual operation data of the to-be-predicted vehicle and the engine steady-state emission data corresponding to the vehicle actual operation data are synthesized, and the two types of data are input into the emission prediction model corresponding to the vehicle working condition type of the to-be-predicted vehicle, so that the comprehensive consideration mode provides a rich data basis for the emission prediction model; and moreover, the influence of different vehicle working condition types on pollutant emission is considered, and the prediction accuracy of the pollutant emission data of the to-be-predicted vehicle predicted by the emission prediction model is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicles, and in particular to a pollutant emission data prediction method, medium, equipment, vehicle and product. Background Art

[0002] The rapid growth in the number of vehicles has led to increasingly serious problems with vehicle pollutant emissions. Against the backdrop of increasing importance of environmental protection and increasingly stringent pollutant emission standards, the industry's demand for vehicle pollutant emission data forecasts has become increasingly urgent.

[0003] Therefore, how to predict vehicle pollutant emission data has become a technical problem that needs to be solved urgently in the industry. Summary of the Invention

[0004] The embodiments of the present application provide a pollutant emission data prediction method, which improves the prediction accuracy of pollutant emission data and at least partially solves the above-mentioned technical problems.

[0005] To achieve the above objectives, according to a first aspect of the present application, a method for predicting pollutant emission data is provided, comprising:

[0006] The actual vehicle operation data of the vehicle to be predicted and the engine steady-state emission data corresponding to the actual vehicle operation data are input into the emission prediction model corresponding to the vehicle operating condition type of the vehicle to be predicted, and the pollutant emission data of the vehicle to be predicted output by the emission prediction model is obtained.

[0007] According to a second aspect of the present application, a pollutant emission data prediction device is provided, comprising:

[0008] The prediction module is used to input the actual vehicle operation data of the vehicle to be predicted and the engine steady-state emission data corresponding to the actual vehicle operation data into the emission prediction model corresponding to the vehicle operating condition type of the vehicle to be predicted, and obtain the pollutant emission data of the vehicle to be predicted output by the emission prediction model.

[0009] According to a third aspect of the present application, a computer-readable storage medium is further provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0010] According to a fourth aspect of the present application, an electronic device is also provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0011] According to a fifth aspect of the present application, a vehicle is also provided, comprising the above-mentioned electronic device.

[0012] According to a sixth aspect of the present application, a computer program product is also provided, comprising a computer program or instructions, which implement the steps of the above method when executed by a processor.

[0013] To sum up, in the embodiment of the present application, the actual vehicle operation data of the vehicle to be predicted and the engine steady-state emission data corresponding to the actual vehicle operation data are integrated, and these two types of data are input into the emission prediction model. This comprehensive consideration method provides a rich data basis for the emission prediction model, and improves the prediction accuracy of the emission prediction model in predicting the pollutant emission data of the vehicle to be predicted; by inputting these two types of data into the emission prediction model corresponding to the vehicle operating condition type of the vehicle to be predicted, the impact of different vehicle operating condition types on pollutant emissions is fully considered, and the prediction accuracy of the emission prediction model in predicting the pollutant emission data of the vehicle to be predicted is further improved.

[0014] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] To more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present application. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0016] In order to more completely understand the present application and its beneficial effects, the following description will be given in conjunction with the accompanying drawings, wherein the same drawing numbers represent the same parts in the following description.

[0017] Figure 1 This is one of the flow charts of the pollutant emission data prediction method provided in the exemplary embodiment of the present application;

[0018] Figure 2 This is the second flow chart of the pollutant emission data prediction method provided in the exemplary embodiment of the present application;

[0019] Figure 3 This is the third flow chart of the pollutant emission data prediction method provided in the exemplary embodiment of the present application;

[0020] Figure 4 is a schematic diagram of a process for training an emission prediction model provided in an exemplary embodiment of the present application;

[0021] Figure 5 is a schematic structural diagram of a pollutant emission data prediction device provided in an exemplary embodiment of the present application;

[0022] Figure 6 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0024] The pollutant emission data prediction method provided in the embodiment of the present application is applicable to a terminal, which can be various electronic devices with a display screen and supporting web browsing, including but not limited to servers, smart phones, tablet computers, laptops, and desktop computers.

[0025] Figure 1 This is one of the flow charts of the pollutant emission data prediction method provided in the exemplary embodiment of this application, such as Figure 1 As shown, the pollutant emission data prediction method provided in the embodiment of the present application includes step 110. The steps of the method flow are only a possible implementation of the present application.

[0026] Step 110: Input the actual vehicle operation data of the vehicle to be predicted and the engine steady-state emission data corresponding to the actual vehicle operation data into the emission prediction model corresponding to the vehicle operating condition type of the vehicle to be predicted, and obtain the pollutant emission data of the vehicle to be predicted output by the emission prediction model.

[0027] Specifically, the execution subject of the pollutant emission data prediction method provided in the embodiment of the present application is a pollutant emission data prediction device, which can be a hardware device independently set in the terminal or a software program running in the terminal.

[0028] Vehicles to be predicted: refers to vehicles whose pollutant emissions need to be predicted.

[0029] Actual vehicle operation data: data that reflects the actual performance of various parameters of the vehicle during actual driving, including vehicle speed, engine speed and torque.

[0030] Steady-state engine emissions data: This data is measured when the engine is in a stable operating state and contains various exhaust pollutants (such as carbon monoxide (CO), hydrocarbons (HC), nitrogen oxides (NOx), and carbon dioxide (CO2)). This data serves as a reference for the emission prediction model when it is used to predict pollutant emissions.

[0031] Vehicle operating condition type: It is divided into different categories based on the actual vehicle operating data, which can include cold engine and catalyst heating conditions, hot start conditions, high load conditions, abnormal front and rear oxygen control conditions and normal conditions, etc.

[0032] Emission prediction models are used to predict vehicle pollutant emissions based on input vehicle operating data and engine steady-state emissions data corresponding to actual vehicle operating data. Emission prediction models can be constructed using convolutional neural network models, fully connected neural network models, recurrent neural network models, and long-short-term memory neural network models. Each vehicle operating condition has its own corresponding emission prediction model.

[0033] Pollutant emission data: This data represents the specific values or concentrations of various pollutants emitted from vehicle exhaust. The pollutant emission data output by the emission prediction model represents the actual pollutant emissions predicted by the vehicle being predicted.

[0034] During the actual operation of the vehicle to be predicted, actual operating data such as vehicle speed, engine speed, and torque are collected, and steady-state engine emissions data are obtained based on this actual operating data. Based on this actual operating data, the current operating condition of the vehicle to be predicted is determined. A matching emission prediction model is selected from multiple emission prediction models. The actual operating data and the corresponding steady-state engine emissions data are then concatenated and input into the emission prediction model corresponding to the current operating condition of the vehicle to be predicted. The emission prediction model then extracts features from the received data, performs computations, and outputs pollutant emissions data for the vehicle to be predicted.

[0035] The pollutant emission data prediction method provided in the embodiment of the present application integrates the actual vehicle operation data of the vehicle to be predicted and the engine steady-state emission data corresponding to the actual vehicle operation data, and inputs these two types of data into the emission prediction model. This comprehensive consideration method provides a rich data basis for the emission prediction model, thereby improving the prediction accuracy of the emission prediction model in predicting the pollutant emission data of the vehicle to be predicted; by inputting these two types of data into the emission prediction model corresponding to the vehicle operating condition type of the vehicle to be predicted, the impact of different vehicle operating condition types on pollutant emissions is fully considered, thereby further improving the prediction accuracy of the emission prediction model in predicting the pollutant emission data of the vehicle to be predicted.

[0036] It should be noted that each implementation method of the present application can be freely combined, the order can be changed, or it can be executed separately, and does not need to rely on or depend on a fixed execution order.

[0037] In some embodiments, the pollutant emission data prediction method provided in this embodiment includes: obtaining the engine steady-state emission data corresponding to the actual vehicle operation data from a pre-stored emission data set.

[0038] Specifically, the emissions data set includes engine operating condition data and the engine steady-state emissions data corresponding to each set of operating condition data. The operating condition data may include engine speed, engine torque, water temperature, air-fuel ratio (lambda), ignition angle, and variable valve timing (VVT).

[0039] Before using the emission prediction model, the target engine can be tested through an engine bench sweep test to obtain an emission data set.

[0040] For example, the target engine can be mounted on a test bench and connected to the relevant sensors and measuring equipment. Based on the target engine's operating range, a test combination of speed, torque, water temperature, lambda value, ignition angle, and VVT is set. Steady-state engine emissions data for each test combination is recorded. At each test point, the target engine's speed, torque, water temperature, lambda value, ignition angle, VVT, and corresponding CO, HC, and NOx emissions are recorded. This data is then organized to create an emissions data set.

[0041] The actual vehicle operation data includes the driving data of the vehicle to be predicted and the first operating condition data of the engine of the vehicle to be predicted. The operating condition data in the emission data set is called the second operating condition data. The first operating condition data in the actual vehicle operation data can be matched with the second operating condition data in the emission data set to obtain the steady-state emission data of the engine corresponding to the actual vehicle operation data.

[0042] For example, data obtained from an engine bench sweep test can be plotted as a steady-state emissions characteristic diagram to obtain an emissions data set. When querying the steady-state engine emissions data corresponding to the vehicle's actual operating data, if the first operating condition data for the vehicle's actual operating data happens to be a test-measured data point, that is, if there is second operating condition data in the emissions data set that matches the first operating condition data, the engine steady-state emissions data corresponding to the second operating condition data can be directly read to obtain the engine steady-state emissions data corresponding to the vehicle's actual operating data. If the first operating condition data does not correspond to the test-measured data point, it is necessary to use surrounding known data points through interpolation to calculate the emissions data for the first operating condition data.

[0043] Interpolation processing can be performed on the data in the emission data set during the use of the emission prediction model; it can also be performed on the data in the emission data set during the training process of the emission prediction model; it can also be performed on the data obtained from the engine bench sweep test when the emission data set is constructed to obtain the emission data set. After the data in the emission data set is interpolated, the emission data set can be updated based on the processing results.

[0044] The target engine may be of the same type, operating principle and / or pollutant emission as the engine of the vehicle to be predicted. The target engine may also be the same engine as the engine of the vehicle to be predicted.

[0045] In some embodiments, the actual vehicle operation data includes driving data of the vehicle to be predicted and first operating condition data of an engine of the vehicle to be predicted; Figure 2 This is the second flow chart of the pollutant emission data prediction method provided in the exemplary embodiment of the present application; Figure 2 As shown, the obtaining of the engine steady-state emission data corresponding to the actual vehicle operation data from the pre-stored emission data set includes:

[0046] Step 210 , matching the first operating condition data in the actual vehicle operation data with the second operating condition data recorded in the emission data set;

[0047] Step 220: Obtain the engine steady-state emission data corresponding to the actual vehicle operation data based on the matching result.

[0048] Wherein, when the matching result is a successful match, the engine steady-state emission data corresponding to the second operating condition data matching the first operating condition data is used as the engine steady-state emission data corresponding to the actual vehicle operation data.

[0049] When the matching result is a matching failure, interpolation processing is performed on the data in the emission data set, and the engine steady-state emission data corresponding to the actual vehicle operation data is obtained based on the interpolation processing result.

[0050] Specifically, driving data is information reflecting the driving status of a vehicle, such as vehicle speed and throttle depth.

[0051] Operating condition data are engine operation parameters, including speed, torque, water temperature, lambda, ignition angle and VVT, etc.

[0052] The first operating condition data is the operating condition data of the engine of the vehicle to be predicted when the vehicle to be predicted is actually running. The second operating condition data is the operating condition data of the target engine recorded in the emission data set.

[0053] The actual vehicle operation data includes the driving data of the vehicle to be predicted and the first operating condition data of the engine of the vehicle to be predicted.

[0054] For example, the actual vehicle operation data of the vehicle to be predicted includes driving data such as the current speed and throttle depth of the vehicle to be predicted, and also includes the current engine speed, torque, water temperature, lambda, ignition angle and VVT of the vehicle to be predicted.

[0055] The first operating condition data is matched with the second operating condition data recorded in the emission data set. If the match is successful, that is, the emission data set also records the second operating condition data that is identical to the first operating condition data, then the engine steady-state emission data corresponding to the second operating condition data is used as the engine steady-state emission data corresponding to the actual vehicle operation data.

[0056] If the matching fails, that is, if the emission data set does not contain the second operating condition data that is identical to the first operating condition data, then the data in the emission data set may be interpolated. For example, the data in the emission data set may be processed using interpolation methods such as linear interpolation, Lagrange interpolation, and polynomial interpolation to obtain the engine steady-state emissions data corresponding to the actual vehicle operating data.

[0057] The pollutant emission data prediction method provided in the embodiment of the present application can quickly and accurately obtain the engine steady-state emission data corresponding to the actual vehicle operation data, thereby improving the data acquisition efficiency of the engine steady-state emission data.

[0058] In some embodiments, step 110 includes:

[0059] Normalizing the actual vehicle operation data and the engine steady-state emission data corresponding to the actual vehicle operation data;

[0060] The normalized actual vehicle operation data and the engine steady-state emission data are spliced and sent to the emission prediction model corresponding to the vehicle operating condition type of the vehicle to be predicted.

[0061] Specifically, the actual vehicle operation data and engine steady-state emission data contain multiple parameters, such as vehicle speed and engine speed, etc. These data are normalized to eliminate the dimensional differences and numerical range differences between different parameters.

[0062] For example, the actual vehicle operation data and engine steady-state emission data are normalized to [0,1], and the data a t_ori For example, define the upper limit a max and lower limit a min , the original data a t_ori Scale to

[0063] The normalized actual vehicle operating data and the corresponding engine steady-state emission data are spliced according to the established correspondence to obtain a feature vector or feature matrix, and the feature vector or feature matrix is sent to the emission prediction model corresponding to the vehicle operating condition type of the vehicle to be predicted.

[0064] The pollutant emission data prediction method provided in the embodiment of the present application can enable the emission prediction model to effectively identify the data by preprocessing the actual vehicle operation data and the engine steady-state emission data, thereby improving the prediction efficiency of the pollutant emission data.

[0065] Figure 3 This is the third flow chart of the pollutant emission data prediction method provided in the exemplary embodiment of this application, such as Figure 3 As shown, step 110 includes:

[0066] Step 310: determining the vehicle operating condition type of the vehicle to be predicted based on the actual vehicle operating data;

[0067] Step 320: Obtain an emission prediction model corresponding to the vehicle operating condition type;

[0068] Step 330 : Inputting the actual vehicle operation data and the engine steady-state emission data corresponding to the actual vehicle operation data into the emission prediction model.

[0069] Specifically, a model library containing emission prediction models corresponding to various vehicle operating condition types can be constructed.

[0070] According to the data requirement range of each vehicle operating condition type for the vehicle's actual operating data and the vehicle's actual operating data, the vehicle operating condition type to which the vehicle to be predicted currently belongs is determined, and the emission prediction model corresponding to the vehicle operating condition type is obtained from the model library.

[0071] The actual vehicle operation data and the engine steady-state emission data corresponding to the actual vehicle operation data are input into an emission prediction model corresponding to the vehicle operating condition type to which the vehicle to be predicted currently belongs.

[0072] The pollutant emission data prediction method provided in the embodiment of the present application determines the vehicle operating condition type of the vehicle to be predicted through the actual vehicle operation data, and then obtains the corresponding emission prediction model, thereby improving the prediction accuracy of the pollutant emission data prediction.

[0073] In some embodiments, the vehicle operating condition type includes at least one of a cold engine and catalyst heating condition, a hot start condition, a high load condition, an abnormal front and rear oxygen control condition, and a normal condition.

[0074] The determining the vehicle operating condition type of the vehicle to be predicted based on the actual vehicle operating data includes:

[0075] The vehicle operating condition type of the vehicle to be predicted is determined based on at least one of the engine water temperature, the catalyst flag position, the engine speed, the engine torque and the oxygen content of the catalyst exhaust gas in the actual vehicle operation data.

[0076] The determining of the vehicle operating condition type of the vehicle to be predicted based on at least one of the engine water temperature, the catalyst flag, the engine speed, the engine torque, and the oxygen content of the catalyst exhaust gas in the actual vehicle operating data includes:

[0077] When the engine water temperature is less than a first water temperature threshold and the catalyst flag indicates that the catalyst of the exhaust system of the predicted vehicle is in a heated state, determining that the vehicle operating condition type is the cold engine and catalyst heated operating condition;

[0078] When the engine water temperature is greater than a second water temperature threshold and the engine speed is within a preset speed range, determining that the vehicle operating condition type is the hot start operating condition;

[0079] When the engine speed is greater than a speed threshold and the engine torque is greater than a torque threshold, determining that the vehicle operating condition type is the heavy load operating condition;

[0080] determining that the vehicle operating condition type is the front and rear oxygen control abnormal operating condition when the correlation between the oxygen content in the exhaust gas entering the catalyst and the oxygen content in the exhaust gas after being processed by the catalyst is less than a correlation threshold;

[0081] When the actual operating data of the vehicle does not meet the data requirement range of the cold engine and catalyst heating condition, the hot start condition, the high load condition and the front and rear oxygen control abnormal condition, the vehicle operating condition type is determined to be the normal condition.

[0082] Specifically, the vehicle operating condition type of the vehicle to be predicted can be determined based on the engine water temperature, catalyst flag, engine speed, engine torque, and oxygen content of catalyst exhaust gas in the actual vehicle operating data. The determination can be made in the following manner:

[0083] The engine water temperature, the first water temperature threshold, and the catalyst flag can be used to determine whether the vehicle's operating condition is a cold engine with a heated catalyst. The first water temperature threshold is the lower limit of the engine water temperature. The various thresholds and data ranges in the embodiments of this application can be set based on actual conditions.

[0084] When the engine water temperature is lower than the first water temperature threshold, the engine is considered to be in a cold state.

[0085] The status of the catalyst flag can be identified by a binary signal (e.g., 0 for unheated, 1 for heated) provided by the control system or aftertreatment system of the vehicle to be predicted. The status of the catalyst flag is checked. If the catalyst flag indicates that the catalyst is heating and the engine water temperature is less than a first water temperature threshold, the vehicle operating condition is determined to be a cold engine with catalyst heating.

[0086] Whether the vehicle's operating condition is a hot start condition can be determined using the engine water temperature, the second water temperature threshold, the engine speed, and a preset speed range. The second water temperature threshold is the upper limit of the engine water temperature. The preset speed range is the engine speed range for a hot start condition.

[0087] When the engine water temperature is greater than the second water temperature threshold, the engine may be in a running state after a hot start.

[0088] Generally, after a hot start, the engine speed may remain low for a short period of time before gradually rising to a normal speed range. Therefore, when the engine water temperature is greater than the second water temperature threshold and the engine speed is within the preset speed range, the vehicle operating condition is determined to be a hot start condition.

[0089] Whether the vehicle operating condition of the vehicle to be predicted is a heavy load condition can be determined by the engine speed, speed threshold, engine torque, and torque threshold. The speed threshold is the lower limit of the engine speed under heavy load conditions.

[0090] In a heavy load operating condition, the engine torque output by the engine is generally large. Therefore, when the engine speed is greater than the speed threshold and the engine torque is greater than the torque threshold, the vehicle operating condition type is determined to be a heavy load operating condition.

[0091] It is possible to determine whether the vehicle operating condition type of the vehicle to be predicted is an abnormal front and rear oxygen control operating condition based on the oxygen content in the exhaust gas of the catalyst and a correlation threshold.

[0092] Analyze the data from the front oxygen sensor and rear oxygen sensor of the vehicle to be predicted. The front oxygen sensor is mainly used to monitor the oxygen content of the exhaust gas entering the catalyst, while the rear oxygen sensor is used to monitor the oxygen content of the exhaust gas after being processed by the catalyst.

[0093] The correlation between the oxygen content of the exhaust gas entering the catalyst and the oxygen content of the exhaust gas after being treated by the catalyst is calculated. Under normal circumstances, the data from the front oxygen sensor and the rear oxygen sensor have a certain correlation. For example, when the catalyst is functioning properly, the reading of the rear oxygen sensor should fluctuate within a certain range of the reading of the front oxygen sensor.

[0094] If the correlation between the data of the front oxygen sensor and the rear oxygen sensor is less than the correlation threshold, there may be a situation of abnormal front and rear oxygen control. Therefore, when the correlation between the oxygen content in the exhaust gas entering the catalyst and the oxygen content in the exhaust gas after being treated by the catalyst is less than the correlation threshold, it is determined that the vehicle operating condition type is an abnormal front and rear oxygen control operating condition.

[0095] When the actual operating data of the vehicle does not meet the data requirement range of the cold engine and catalyst heating operating condition, the hot start operating condition, the high load operating condition and the front and rear oxygen control abnormal operating condition, the vehicle operating condition type is determined to be a normal operating condition.

[0096] The pollutant emission data prediction method provided in the embodiment of the present application judges the vehicle operating condition type through the actual vehicle operation data, so that the relevant data can be input into the emission prediction model corresponding to the vehicle operating condition type of the vehicle to be predicted, thereby improving the prediction accuracy of the pollutant emission data prediction.

[0097] In some embodiments, different vehicle operating condition types correspond to different training sample subsets of emission prediction models.

[0098] Dividing the training sample set based on the data requirement range of the vehicle actual operation data of the vehicle operating condition type to obtain a training sample subset for each vehicle operating condition type;

[0099] An initial emission prediction model corresponding to each vehicle operating condition type is trained based on the training sample subset of each vehicle operating condition type to obtain an emission prediction model corresponding to each vehicle operating condition type.

[0100] Specifically, Figure 4 is a flow chart of the training emission prediction model provided in the exemplary embodiment of the present application, such as Figure 4 As shown, the second operating condition data of the engine and the engine steady-state emission data corresponding to the second operating condition data can be collected through the engine bench test, and these data can be stored in the form of a mapping diagram or map; the actual vehicle operation data and the pollutant emission data corresponding to the actual vehicle operation data can be collected through the real driving emissions (RDE) test of the whole vehicle.

[0101] The pollutant emission data is preprocessed, such as data cleaning, smoothing and normalization, and features are constructed using the engine steady-state emission data and the preprocessed pollutant emission data to obtain a training sample set.

[0102] The training sample set is divided into multiple training sample subsets based on the data requirements of the vehicle operating condition type for actual vehicle operation data. Each vehicle operating condition type has its own corresponding training sample subset. The corresponding emission prediction model is trained using the training sample subsets for each vehicle operating condition type, thereby improving the prediction accuracy of the emission prediction model.

[0103] In some embodiments, each training sample in the training sample subset includes an actual operating data sample measured when a first test is performed on the target engine and a pollutant emission data label corresponding to the actual operating data sample, as well as an engine steady-state emission data sample corresponding to a second operating condition data sample that matches the actual operating data sample when a second test is performed on the target engine.

[0104] The first test includes testing a vehicle using the target engine using a portable emission measurement system, and / or the second test includes testing the target engine by installing it on a test bench.

[0105] Specifically, a portable emissions measurement system (PEMS) can be used to collect vehicle RDE operating condition information, i.e., conduct a first test. The RDE operating condition information includes vehicle speed, throttle depth, engine speed, engine torque, water temperature, lambda, ignition angle, VVT, and pollutant emission data. This data is processed and used as actual operating data samples and pollutant emission data labels corresponding to the actual operating data samples. The engine in the vehicle can be the target engine, or it can be an engine with the same type, operating principle, and / or pollutant emission conditions as the target engine.

[0106] A sweep test, i.e., a second test, can be performed on the target engine on an engine test bench to collect test data under steady-state conditions. This test data includes second operating condition data and steady-state emissions data corresponding to the second operating condition data. This data is processed to generate second operating condition data samples and engine steady-state emissions data samples corresponding to the second operating condition data samples.

[0107] The second operating condition data sample and the engine steady-state emission data sample corresponding to the second operating condition data sample can be stored as an engine steady-state emission six-dimensional lookup table, and the steady-state emission data can be queried through the engine speed, torque, water temperature, lambda, ignition angle and VVT.

[0108] The data collected by PEMS equipment may have problems such as missing data, data anomalies, uneven data sampling frequencies, and large differences in data values. Therefore, the collected data needs to undergo preprocessing operations such as data cleaning, smoothing, and normalization.

[0109] For example, for missing data, interpolation filling methods can be used to fill in the gaps; for problems such as data fluctuations and outliers, filtering can be used to smooth the data; and data signals with different sampling intervals can be processed into data sequences with a sampling interval of 1s.

[0110] When constructing each training sample, it is necessary to splice the actual operation data sample, the second operating condition data sample of the pollutant emission data label corresponding to the actual operation data sample, and the engine steady-state emission data sample corresponding to the second operating condition data sample.

[0111] The steady-state emission data sample under the first operating condition data sample can be obtained by interpolating the first operating condition data sample on the engine steady-state emission characteristic map according to the first operating condition data sample in the actual operation data sample.

[0112] For example, the speed, torque, water temperature, lambda, ignition angle and VVT of the first operating condition data sample can be interpolated on the engine steady-state emission characteristic map to obtain the steady-state emission data sample under the first operating condition data, that is, the engine steady-state emission data sample under the first operating condition can be interpolated on the engine steady-state emission characteristic map according to the engine signal to obtain the map = map{speed, torque, water temperature, lambda, ignition angle, VVT}.

[0113] After obtaining the steady-state emission data sample under the first operating condition data sample, the first operating condition data sample, the steady-state emission data sample corresponding to the first operating condition data sample, and the steady-state emission data sample corresponding to the second operating condition data sample that is identical to the first operating condition data sample can be concatenated and used as input to the initial emission prediction model. The initial emission prediction model is an emission prediction model for which training has not yet begun or completed.

[0114] The pollutant emission data labels corresponding to the actual operation data samples can also be obtained based on the actual operation data samples. The pollutant emission data labels can be used as comparison values for the pollutant emission data output by the initial emission prediction model.

[0115] Each training sample consists of x and y, where x is the input to the initial emissions prediction model and y is the comparison value of the pollutant emissions data output by the initial emissions prediction model. x includes any actual operating data sample, and the engine steady-state emissions data sample corresponding to the second operating condition data sample matched by this actual operating data sample, where x = [engine steady-state emissions data sample, vehicle speed, throttle depth, engine speed, torque, water temperature, lambda, ignition angle, VVT, etc.]; y includes the pollutant emission data label corresponding to this actual operating data sample, where y = [CO, HC, NOx, etc.].

[0116] Based on the vehicle operating condition type's required data range for actual vehicle operation, training samples are divided into five groups: normal operating conditions, cold engine with catalyst heating conditions, hot start conditions, high load conditions, and abnormal front and rear oxygen control conditions. Cold engine with catalyst heating conditions are filtered by engine water temperature and catalyst flag; hot start conditions are filtered by engine water temperature and engine speed; and high load conditions are filtered by engine speed and engine torque. Training samples that do not fall under cold engine with catalyst heating conditions, hot start conditions, high load conditions, or abnormal front and rear oxygen control conditions are labeled as normal operating conditions.

[0117] The initial emission prediction model for each vehicle operating condition is trained using a subset of training samples for each vehicle operating condition. A Support Vector Machine (SVM) model can be selected as the initial emission prediction model, with the emission feature vector x as the model input and the emission result y as the true label for training the initial emission prediction model. This training yields an emission prediction model for each vehicle operating condition.

[0118] The pollutant emission data prediction method provided in the embodiment of the present application comprehensively considers the engine steady-state emission data and the vehicle's actual operating condition RDE test data to train the emission prediction model corresponding to the vehicle operating condition type, and can achieve accurate prediction of pollutant emission data under the vehicle's actual operating conditions with fewer actual vehicle test collection times; it divides the engine operating conditions by physical rules, trains the emission prediction model corresponding to each vehicle operating condition type, and improves the prediction accuracy of pollutant emission data.

[0119] The pollutant emission data prediction device provided in an embodiment of the present application is described below. The pollutant emission data prediction device described below and the pollutant emission data prediction method described above can be referenced to each other.

[0120] Figure 5 is a schematic diagram of the structure of the pollutant emission data prediction device provided in the embodiment of the present application, such as Figure 5 As shown, the apparatus includes a prediction module 510 .

[0121] The prediction module 510 is used to input the actual vehicle operation data of the vehicle to be predicted and the engine steady-state emission data corresponding to the actual vehicle operation data into the emission prediction model corresponding to the vehicle operating condition type of the vehicle to be predicted, and obtain the pollutant emission data of the vehicle to be predicted output by the emission prediction model.

[0122] Among them, the prediction module 510 can be used to execute step 110 in the embodiment corresponding to the above-mentioned pollutant emission data prediction method. For the specific implementation methods of these modules and more details, please refer to the corresponding method part, which will not be repeated here.

[0123] It should be noted here that the pollutant emission data prediction device provided in the embodiment of the present application can implement all the method steps implemented in the above-mentioned pollutant emission data prediction method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0124] Figure 6 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application, such as Figure 6 As shown, the electronic device may include: a processor (Processor) 610, a communication interface (Communication Interface) 620, a memory (Memory) 630 and a communication bus 640, wherein the processor 610, the communication interface 620, and the memory 630 communicate with each other via the communication bus 640. The processor 610 may call a computer program in the memory 630 to execute the above method, for example, including:

[0125] The actual vehicle operation data of the vehicle to be predicted and the engine steady-state emission data corresponding to the actual vehicle operation data are input into the emission prediction model corresponding to the vehicle operating condition type of the vehicle to be predicted, and the pollutant emission data of the vehicle to be predicted output by the emission prediction model is obtained.

[0126] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of a software function module and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0127] An embodiment of the present application further provides a computer-readable storage medium having instructions stored thereon. When the instructions are executed by a processor, the processor is configured to execute the above-mentioned mobile charging scheduling method.

[0128] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0129] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0130] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0131] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0132] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0133] Memory may include non-permanent memory in a computer-readable storage medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable storage medium.

[0134] Computer-readable storage media includes permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules, 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, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, 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. As defined herein, computer-readable storage media does not include transitory media such as modulated communication signals and carrier waves.

[0135] The present application also provides a vehicle including the aforementioned electronic device. In this embodiment, the vehicle may be a fuel-powered vehicle, a plug-in hybrid vehicle, or a new energy vehicle, etc., which is not specifically limited in this application.

[0136] An embodiment of the present application further provides a computer program product, comprising a computer program or instructions, which implement the steps of the above method when executed by a processor.

[0137] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more features. In the description of this application, "plurality" means two or more, unless otherwise specifically defined.

[0138] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0139] The embodiments, implementation methods and related technical features of the present application can be combined and replaced with each other without conflict.

[0140] The above are merely preferred embodiments of the present application and do not constitute any form of limitation to the present application. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present application without departing from the content of the technical solution of the present application are still within the scope of the technical solution of the present application.

Claims

1. A method for predicting pollutant emission data, characterized in that: include: The actual vehicle operation data of the vehicle to be predicted and the engine steady-state emission data corresponding to the actual vehicle operation data are input into the emission prediction model corresponding to the vehicle operating condition type of the vehicle to be predicted, and the pollutant emission data of the vehicle to be predicted output by the emission prediction model is obtained.

2. The method according to claim 1, characterized in that Also includes: The engine steady-state emission data corresponding to the actual vehicle operation data is obtained from a pre-stored emission data set.

3. The method according to claim 2, characterized in that The actual vehicle operation data includes the driving data of the vehicle to be predicted and the first operating condition data of the engine of the vehicle to be predicted; The obtaining the engine steady-state emission data corresponding to the actual vehicle operation data from a pre-stored emission data set includes: matching the first operating condition data in the actual vehicle operation data with the second operating condition data recorded in the emission data set; The engine steady-state emission data corresponding to the actual vehicle operation data is obtained based on the matching result.

4. The method according to claim 3, characterized in that The obtaining, based on the matching result, the engine steady-state emission data corresponding to the actual vehicle operation data includes: When the matching result is successful, the engine steady-state emission data corresponding to the second operating condition data that matches the first operating condition data is used as the engine steady-state emission data corresponding to the actual vehicle operation data.

5. The method according to claim 3, characterized in that The obtaining, based on the matching result, the engine steady-state emission data corresponding to the actual vehicle operation data includes: When the matching result is a matching failure, interpolation processing is performed on the data in the emission data set, and the engine steady-state emission data corresponding to the actual vehicle operation data is obtained based on the interpolation processing result.

6. The method according to claim 1, characterized in that The step of inputting the actual vehicle operation data of the vehicle to be predicted and the engine steady-state emission data corresponding to the actual vehicle operation data into an emission prediction model corresponding to the vehicle operating condition type of the vehicle to be predicted comprises: Normalizing the actual vehicle operation data and the engine steady-state emission data corresponding to the actual vehicle operation data; The normalized actual vehicle operation data and the engine steady-state emission data are spliced and sent to the emission prediction model corresponding to the vehicle operating condition type of the vehicle to be predicted.

7. The method according to any one of claims 1 to 6, characterized in that The step of inputting the actual vehicle operation data of the vehicle to be predicted and the engine steady-state emission data corresponding to the actual vehicle operation data into an emission prediction model corresponding to the vehicle operating condition type of the vehicle to be predicted comprises: determining the vehicle operating condition type of the vehicle to be predicted based on the actual vehicle operating data; Obtaining an emission prediction model corresponding to the vehicle operating condition type; The actual vehicle operation data and the engine steady-state emission data corresponding to the actual vehicle operation data are input into the emission prediction model.

8. The method according to claim 7, characterized in that The vehicle operating condition type includes at least one of a cold engine and catalyst heating operating condition, a hot start operating condition, a high load operating condition, an abnormal front and rear oxygen control operating condition, and a normal operating condition.

9. The method according to claim 8, characterized in that The determining the vehicle operating condition type of the vehicle to be predicted based on the actual vehicle operating data includes: The vehicle operating condition type of the vehicle to be predicted is determined based on at least one of the engine water temperature, the catalyst flag position, the engine speed, the engine torque and the oxygen content of the catalyst exhaust gas in the actual vehicle operation data.

10. The method according to claim 8, characterized in that The determining the vehicle operating condition type of the vehicle to be predicted based on at least one of an engine water temperature, a catalyst flag position, an engine speed, an engine torque, and an oxygen content of catalyst exhaust gas in the actual vehicle operating data includes: When the engine water temperature is less than a first water temperature threshold and the catalyst flag indicates that the catalyst of the exhaust system of the predicted vehicle is in a heated state, determining that the vehicle operating condition type is the cold engine and catalyst heated operating condition; When the engine water temperature is greater than a second water temperature threshold and the engine speed is within a preset speed range, determining that the vehicle operating condition type is the hot start operating condition; When the engine speed is greater than a speed threshold and the engine torque is greater than a torque threshold, determining that the vehicle operating condition type is the heavy load operating condition; determining that the vehicle operating condition type is the front and rear oxygen control abnormal operating condition when the correlation between the oxygen content in the exhaust gas entering the catalyst and the oxygen content in the exhaust gas after being processed by the catalyst is less than a correlation threshold; When the actual operating data of the vehicle does not meet the data requirement range of the cold engine and catalyst heating condition, the hot start condition, the high load condition and the front and rear oxygen control abnormal condition, the vehicle operating condition type is determined to be the normal condition.

11. The method according to any one of claims 1 to 6, characterized in that: Different vehicle operating conditions correspond to different subsets of training samples for emission prediction models.

12. The method according to any one of claims 1 to 6, characterized in that Also includes: Dividing the training sample set based on the data requirement range of the vehicle actual operation data of the vehicle operating condition type to obtain a training sample subset for each vehicle operating condition type; An initial emission prediction model corresponding to each vehicle operating condition type is trained based on the training sample subset of each vehicle operating condition type to obtain an emission prediction model corresponding to each vehicle operating condition type.

13. The method according to claim 11, characterized in that Each training sample in the training sample subset includes an actual operating data sample measured when a first test is performed on the target engine and a pollutant emission data label corresponding to the actual operating data sample, as well as an engine steady-state emission data sample corresponding to a second operating condition data sample that matches the actual operating data sample when a second test is performed on the target engine.

14. The method according to claim 13, characterized in that The first test includes testing a vehicle using the target engine using a portable emission measurement system, and / or the second test includes testing the target engine by installing it on a test bench.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 14 are implemented.

16. An electronic device having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 14 are implemented.

17. A vehicle, characterized in that: The electronic device comprising claim 16.

18. A computer program product, characterized in that The method comprises a computer program or instructions, which implement the steps of the method according to any one of claims 1 to 14 when executed by a processor.

Images