Method and device for calculating urea injection quantity

Abstract

The application discloses a urea injection amount calculation method and device, and relates to the technical field of diesel engine exhaust aftertreatment, which comprises the following steps: sequentially inputting the operation data of a diesel engine into a preset nitrogen oxide emission prediction model according to time sequence to predict the nitrogen oxide emission of the diesel engine; determining the target stoichiometric ratio corresponding to the nitrogen oxide emission, multiplying the target stoichiometric ratio by the predicted nitrogen oxide emission to obtain the theoretical pre-control amount of urea; calculating the first actual pre-control amount of urea according to the theoretical pre-control amount, and determining the second actual pre-control amount of urea when the diesel engine is in a special working condition; and determining the urea injection amount based on the first actual pre-control amount and the second actual pre-control amount. By applying the technical scheme of the application, the problems of high cost and slow response speed of the NOx sensor, which are not conducive to realizing precise urea injection, can be solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of diesel engine exhaust aftertreatment, in particular to a urea injection amount calculation method and device. BACKGROUND

[0002] To meet the stringent requirements of national VI regulations on nitrogen oxide (NOx) emissions, many diesel engines for road use equipped with feedforward control systems choose selective catalytic reduction (SCR) systems. Since NOx is the most important parameter for calculating feedforward reductant, it is crucial to obtain the original machine NOx emissions.

[0003] Currently, a physical NOx sensor is usually installed on the SCR catalyst to obtain the NOx emissions through the NOx sensor. However, this approach increases hardware costs, and since the low-temperature response time of the NOx sensor is relatively long, the sensor value loses real-time performance after being obtained through sampling in the control process, which is not conducive to precise urea injection and thus cannot meet the emission requirements. SUMMARY

[0004] The present application provides a urea injection amount calculation method and device, which mainly solves the problems of high cost and slow response of the NOx sensor, which is not conducive to precise urea injection.

[0005] According to a first aspect of an embodiment of the present application, a urea injection amount calculation method is provided, comprising:

[0006] obtaining operation data of a diesel engine;

[0007] performing dimensionality reduction processing on the operation data using a preset principal component analysis algorithm to obtain reduced dimension operation data;

[0008] inputting the reduced dimension operation data into a preset nitrogen oxide emission prediction model in time sequence to predict the nitrogen oxide emission, to obtain the nitrogen oxide emission of the diesel engine, wherein the preset nitrogen oxide emission prediction model represents the mapping relationship between the reduced dimension operation data and the nitrogen oxide emission;

[0009] determining a target stoichiometric ratio corresponding to the nitrogen oxide emission, and multiplying the target stoichiometric ratio by the predicted nitrogen oxide emission to obtain a theoretical pre-control amount of urea;

[0010] According to the theoretical pre-control amount, a first actual pre-control amount of urea is calculated, and a second actual pre-control amount of urea when the diesel engine is in a special working condition is determined;

[0011] Based on the first actual pre-control amount and the second actual pre-control amount, the urea injection amount is determined.

[0012] According to a second aspect of the embodiments of the present application, there is provided a urea injection amount calculation device, comprising:

[0013] an acquisition unit configured to acquire operation data of a diesel engine;

[0014] a dimension reduction unit configured to perform dimension reduction processing on the operation data using a preset principal component analysis algorithm to obtain reduced dimension operation data;

[0015] a prediction unit configured to sequentially input the reduced dimension operation data into a preset nitrogen oxide emission amount prediction model in time sequence to predict nitrogen oxide emission amount, to obtain nitrogen oxide emission amount of the diesel engine, wherein the preset nitrogen oxide emission amount prediction model represents a mapping relationship between the reduced dimension operation data and the nitrogen oxide emission amount;

[0016] a determination unit configured to determine a target stoichiometric ratio corresponding to the nitrogen oxide emission amount, and multiply the target stoichiometric ratio by the predicted nitrogen oxide emission amount to obtain a theoretical pre-control amount of urea;

[0017] a calculation unit configured to calculate a first actual pre-control amount of urea according to the theoretical pre-control amount, and determine a second actual pre-control amount of urea when the diesel engine is in a special working condition;

[0018] The determination unit is further configured to determine a urea injection amount based on the first actual pre-control amount and the second actual pre-control amount.

[0019] According to a third aspect of the embodiments of the present application, there is provided a computer readable storage medium having a computer program stored thereon, the program being executed by a processor to implement the following steps:

[0020] acquiring operation data of a diesel engine;

[0021] performing dimension reduction processing on the operation data using a preset principal component analysis algorithm to obtain reduced dimension operation data;

[0022] sequentially inputting the reduced dimension operation data into a preset nitrogen oxide emission amount prediction model in time sequence to predict nitrogen oxide emission amount, to obtain nitrogen oxide emission amount of the diesel engine, wherein the preset nitrogen oxide emission amount prediction model represents a mapping relationship between the reduced dimension operation data and the nitrogen oxide emission amount;

[0023] determining a target stoichiometric ratio corresponding to the nitrogen oxide emission amount, and multiplying the target stoichiometric ratio by the predicted nitrogen oxide emission amount to obtain a theoretical pre-control amount of urea;

[0024] According to the theoretical pre-control amount, a first actual pre-control amount of the urea is calculated, and a second actual pre-control amount of the urea when the diesel engine is in a special working condition is determined;

[0025] Based on the first actual pre-control amount and the second actual pre-control amount, a urea injection amount is determined.

[0026] According to a fourth aspect of the embodiments of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the program:

[0027] Obtaining operation data of a diesel engine;

[0028] Performing dimension reduction processing on the operation data by using a preset principal component analysis algorithm to obtain reduced dimension operation data;

[0029] Inputting the reduced dimension operation data into a preset nitrogen oxide emission amount prediction model in time sequence to predict the nitrogen oxide emission amount, to obtain the nitrogen oxide emission amount of the diesel engine, wherein the preset nitrogen oxide emission amount prediction model represents a mapping relationship between the reduced dimension operation data and the nitrogen oxide emission amount;

[0030] Determining a target stoichiometric ratio corresponding to the nitrogen oxide emission amount, and multiplying the target stoichiometric ratio by the predicted nitrogen oxide emission amount to obtain a theoretical pre-control amount of urea;

[0031] According to the theoretical pre-control amount, a first actual pre-control amount of the urea is calculated, and a second actual pre-control amount of the urea when the diesel engine is in a special working condition is determined;

[0032] Based on the first actual pre-control amount and the second actual pre-control amount, a urea injection amount is determined.

[0033] The innovation points of the embodiments of the present application include:

[0034] 1. Following the idea of software replacing hardware, a virtual sensor is used to replace a traditional SCR upstream NOx sensor, thereby saving hardware cost and making up for the limitations of the NOx sensor, which is one of the innovation points of the embodiments of the present application.

[0035] 2. The principal component analysis algorithm is used to perform dimension reduction processing on the operation data of the diesel engine, thereby reducing the calculation amount, which is one of the innovation points of the embodiments of the present application.

[0036] 3. The first actual pre-control amount and the second actual pre-control amount are calculated respectively, to realize precise urea injection under different working conditions of the diesel engine, which is one of the innovation points of the embodiments of the present application.

[0037] The urea injection amount calculation method and device provided by the application can obtain the operation data of the diesel engine, and utilize a preset principal component analysis algorithm to perform dimension reduction processing on the operation data to obtain reduced operation data, while the reduced operation data is sequentially input into a preset nitrogen oxide emission prediction model in time sequence to predict the nitrogen oxide emission, so as to obtain the nitrogen oxide emission of the diesel engine, then the target stoichiometric ratio corresponding to the nitrogen oxide emission is determined, and the target stoichiometric ratio is multiplied by the predicted nitrogen oxide emission to obtain the theoretical pre-control amount of urea, then the first actual pre-control amount of urea is calculated according to the theoretical pre-control amount, and the second actual pre-control amount of urea is determined when the diesel engine is in a special working condition, and finally the urea injection amount is determined based on the first actual pre-control amount and the second actual pre-control amount. It can be seen that the application follows the idea of software replacing hardware, and uses a virtual sensor to replace the traditional SCR upstream NOx sensor, which makes up for the limitations of the NOx sensor, has fast response time, low cost, and is conducive to realizing accurate injection of urea. In addition, the application uses the principal component analysis algorithm to perform dimension reduction processing on the operation data of the diesel engine, which can reduce the calculation amount and improve the calculation efficiency of the nitrogen oxide emission. Further, the application can realize accurate injection of urea under different working conditions of the diesel engine by calculating the first actual pre-control amount and the second actual pre-control amount.

[0038] The above description is only a summary of the technical solutions of the application. In order to more clearly understand the technical means of the application, the application can be implemented according to the content of the specification, and in order to make the above and other purposes, features and advantages of the application more obvious and easy to understand, the following specific embodiments of the application are described. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description are only some embodiments of the application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0040] Figure 1 A urea injection amount calculation method flowchart provided by an embodiment of the application is shown;

[0041] Figure 2 Another urea injection amount calculation method flowchart provided by an embodiment of the application is shown;

[0042] Figure 3A structure schematic diagram of a urea injection amount calculation device provided by an embodiment of the present application is shown.

[0043] Figure 4 A structure schematic diagram of another urea injection amount calculation device provided by an embodiment of the present application is shown.

[0044] Figure 5 A physical structure schematic diagram of an electronic device provided by an embodiment of the present application is shown. DETAILED DESCRIPTION

[0045] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by those skilled in the art without creative effort belong to the protection scope of the present application.

[0046] It should be noted that the terms "comprising" and "having" and any variations thereof in the embodiments of the present application and the drawings are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed or optionally further includes other steps or units inherent to the process, method, product or device.

[0047] The way of installing a physical NOx sensor on an SCR catalyst increases hardware cost, and since the low-temperature response time of the NOx sensor is relatively long, the value of the sensor loses real-time performance after being obtained by sampling in the control process, thus being not conducive to realizing precise injection of urea, and thus failing to meet emission requirements.

[0048] In order to overcome the above defects, an embodiment of the present application provides a urea injection amount calculation method, as shown in the figure, the method comprises the following steps. Figure 1

[0049] Step 101: Obtain running data of a diesel engine.

[0050] The running data of the diesel engine includes engine speed, torque, injection amount, intake flow, intake pressure, intake temperature, oxygen concentration, oil pressure, oil temperature, cooling water temperature, EGR opening, atmospheric pressure, atmospheric temperature, rail pressure and main injection advance angle. It should be noted that the running data of the diesel engine in the embodiments of the present application is not limited to the above data, but can also be other data.

[0051] ​The embodiment of the present application is mainly applicable to the scene of predicting nitrogen oxide emission amount by using a model and calculating urea injection amount based on the predicted nitrogen oxide emission amount. The execution subject of the embodiment of the present application is a device or equipment capable of predicting nitrogen oxide emission amount and calculating urea injection amount.

[0052] In order to predict nitrogen oxide emission amount of a diesel engine by using a software algorithm, the embodiment of the present application collects running data such as engine speed, torque, injection amount, intake flow, intake pressure, intake temperature, oxygen concentration, oil pressure, oil temperature, cooling water temperature, EGR opening, atmospheric pressure, atmospheric temperature, rail pressure and main injection advance angle of the engine at every preset time interval by using various types of sensors. The running data is sent to an ECU after A / D conversion, and the ECU can predict nitrogen oxide emission amount of the diesel engine based on the running data. The preset time interval can be set according to actual business requirements, such as data collection every 10 ms.

[0053] Step 102, dimension reduction processing is performed on the running data by using a preset principal component analysis algorithm to obtain dimension-reduced running data.

[0054] In order to reduce the calculation amount in the process of predicting nitrogen oxide emission amount, the embodiment of the present application performs dimension reduction processing on the running data by using a preset principal component analysis algorithm. For this process, the method comprises the following steps: determining a parameter matrix composed of the running data; calculating a covariance matrix corresponding to the parameter matrix; calculating each eigenvalue corresponding to the covariance matrix and an eigenvector corresponding to each eigenvalue; calculating a contribution rate corresponding to each eigenvector according to each eigenvalue, and sorting each eigenvector according to the contribution rate to obtain a sorting result; selecting a target eigenvector ranked within a preset range from each eigenvector according to the sorting result; adding the contribution rates corresponding to the target eigenvectors to obtain a cumulative contribution rate of the target eigenvectors; if the cumulative contribution rate is greater than a preset contribution rate, then the target eigenvectors are used to form a conversion matrix, and the parameter matrix is multiplied by the conversion matrix to obtain dimension-reduced running data.

[0055] For example, the original 15-dimensional running data is reduced in dimension to obtain a 3-dimensional principal component loading matrix. When performing principal component analysis, the ECU first forms the received diesel engine running data into a p*n-dimensional parameter matrix X, where p is the dimension and n is the number of samples, then calculates the p-order covariance matrix cov(X) of the parameter matrix X, where cov(X) is a p-order square matrix, then calculates the eigenvalues and eigenvectors of the covariance matrix cov(X), further calculates the contribution rate corresponding to each eigenvector, for the contribution rate corresponding to any eigenvector, the eigenvalues corresponding to all eigenvectors are added to obtain the total eigenvalue, and the eigenvalue corresponding to any eigenvector is divided by the total eigenvalue to obtain the contribution rate corresponding to any eigenvector. In this way, the contribution rates corresponding to all eigenvectors can be obtained in the above manner.

[0056] Further, the eigenvectors are sorted in descending order of their corresponding contribution rates, and the top-ranked eigenvectors are selected as target eigenvectors. Then, the contribution rates corresponding to the target eigenvectors are added to obtain the cumulative contribution rate. If the cumulative contribution rate is greater than a predetermined contribution rate, such as 80%, the target eigenvectors are combined into a conversion matrix. Then, the parameter matrix is multiplied by the conversion matrix to obtain a principal component loading matrix, which is the reduced running data.

[0057] Step 103, sequentially inputting the reduced running data into a preset nitrogen oxide emission prediction model according to time sequence to predict the nitrogen oxide emission, to obtain the nitrogen oxide emission of the diesel engine.

[0058] The preset nitrogen oxide emission prediction model represents the mapping relationship between the reduced running data and the nitrogen oxide emission. The preset nitrogen oxide emission prediction model is a preset long short-term memory model LSTM, and the reduced running data is a running data sequence.

[0059] For the embodiment of the application, in order to predict the nitrogen oxide emission of the diesel engine, step 103 specifically includes: inputting the running data sequence into the preset long short-term memory model to predict the nitrogen oxide emission, to obtain the nitrogen oxide emission of the diesel engine.

[0060] The preset long short-term memory model LSTM includes a forgetting gate, an input gate and an output gate. The forgetting gate determines how much information of the previous state is retained to the current time, and its calculation formula is:

[0061] f t =σ(W f *[h t-1 ,x t ]+bf )

[0062] Further, the input gate includes two parts, one is a sigmoid layer to determine which information needs to be updated, and the other is a tanh layer to generate a vector, that is, the alternative content (Ct) for updating, and the calculation formula is:

[0063] i t = σ(W i *[h t-1 , x t ]+b i )

[0064]

[0065]

[0066] Further, the output gate includes two parts, one is a sigmoid layer to determine the output part of the cell state, and the other is a tanh to process the cell state and multiply it with the output of the sigmoid gate, and the calculation formula is:

[0067]

[0068] h t = o t *tanh(C t )

[0069] Wherein, W f , b f , W i , b i , W o , b o are the weight matrix of the forgetting gate, the bias term of the forgetting gate, the weight matrix of the input gate, the bias term of the input gate, the weight matrix of the output gate, and the bias term of the output gate, respectively. t-1 , x t are the output value of the long short-term memory neural network at the previous moment and the input vector at the current moment, respectively. σ(·) is a sigmoid activation function, and the calculation formula is tanh is a hyperbolic tangent activation function, and the calculation formula is

[0070] Therefore, by presetting the long short-term memory model LSTM, the NOx emission amount can be accurately predicted based on the engine running parameters at the previous moment and the current engine running parameters, so that the NOx value in volume fraction and mass flow can be obtained respectively, and the function of a virtual sensor is played.

[0071] Further, before predicting the NOx original engine emission value by using the preset long short-term memory model LSTM, the preset long short-term memory model LSTM needs to be trained. Specifically, the particle swarm algorithm can be used to optimize different parameter combinations of the time window size, the number of hidden layers, the number of neurons in each layer, and the learning rate of the LSTM algorithm through iteration. After 50 iterations, the optimal parameter combination is obtained, and thus the final LSTM prediction model is obtained. Then, the optimized prediction model is burned into the ECU.

[0072] Step 104: determining a target stoichiometric ratio corresponding to the nitrogen oxide emission amount, and multiplying the target stoichiometric ratio by the predicted nitrogen oxide emission amount to obtain a theoretical pre-control amount of urea.

[0073] For the embodiment of the present application, after obtaining the NOx emission amount measured by the virtual sensor, the theoretical pre-control amount of urea can be calculated based on the NOx emission amount to realize accurate injection of urea. Specifically, first, the target stoichiometric ratio is determined according to the average temperature of the SCR catalyst and the preset stoichiometric ratio table MAP, and then the target stoichiometric ratio is multiplied by the predicted NOx emission amount to obtain the amount of urea required for complete elimination of NOx. Thus, the theoretical pre-control amount of urea can be obtained, so as to determine the actual injection amount of urea according to the theoretical pre-control amount.

[0074] Step 105: calculating a first actual pre-control amount of the urea according to the theoretical pre-control amount, and determining a second actual pre-control amount of the urea when the diesel engine is in a special working condition.

[0075] For the embodiment of the present application, after obtaining the theoretical pre-control amount of urea, two actual pre-control amounts of urea, including the first actual pre-control amount and the second actual pre-control amount, need to be calculated. The first actual pre-control amount is the actual pre-control amount determined according to the SCR model, and the second actual pre-control amount is the pre-control amount calculated independently of the SCR model by considering the special working condition of the engine and the system efficiency.

[0076] Step 106: determining the urea injection amount based on the first actual pre-control amount and the second actual pre-control amount.

[0077] For the embodiment of the present application, the enabling switch can be set to switch between the first actual pre-control amount and the second actual pre-control amount. Normally, the first actual pre-control amount is the urea injection amount, but if the ambient temperature, the ambient pressure, the HC state, the average temperature of the SCR catalyst, and the engine operating state all meet the corresponding conditions, it can be considered that the diesel engine is in a special working condition. At this time, the state machine will issue an active adaptation instruction, and the pre-control amount will be switched from the first actual pre-control amount to the second actual pre-control amount, that is, the second actual pre-control amount is selected as the urea injection amount. If the state machine issues an instruction to no longer actively adapt, the first actual pre-control amount will continue to be used as the urea injection amount.

[0078] The embodiment of the present application provides a urea injection amount calculation method, which adopts the idea of replacing hardware with software, replaces the traditional SCR upstream NOx sensor with a virtual sensor, makes up for the limitations of the NOx sensor, has fast response time and low cost, is beneficial to realizing accurate urea injection, and further has the advantages that the embodiment of the present application adopts a principal component analysis algorithm to perform dimension reduction processing on the operating data of the diesel engine, can reduce the calculation amount, and improve the calculation efficiency of the nitrogen oxide emission amount.

[0079] Further, as a refinement and expansion of the above-mentioned embodiment, the embodiment of the present application provides another urea injection amount calculation method, as shown in Figure 2 The method comprises the following steps:

[0080] Step 201: acquiring operating data of a diesel engine.

[0081] For the embodiment of the present application, various types of sensors can be used to collect engine speed, torque, injection amount, intake flow, intake pressure, intake temperature, oxygen concentration, oil pressure, oil temperature, cooling water temperature, EGR opening, atmospheric pressure, atmospheric temperature, rail pressure, and main injection advance angle at preset time intervals.

[0082] Step 202: performing dimension reduction processing on the operating data by using a preset principal component analysis algorithm to obtain dimension-reduced operating data.

[0083] For the embodiment of the present application, in order to reduce the calculation amount in the nitrogen oxide emission amount prediction process, a preset principal component analysis algorithm is used to perform dimension reduction processing on the operating data. The process is completely the same as step 102, and will not be repeated here.

[0084] Step 203: sequentially inputting the dimension-reduced operating data into a preset nitrogen oxide emission amount prediction model in time sequence to predict the nitrogen oxide emission amount, and obtaining the nitrogen oxide emission amount of the diesel engine.

[0085] The preset nitrogen oxide emission prediction model represents a mapping relationship between the reduced operation data and the nitrogen oxide emission. The preset nitrogen oxide emission prediction model is a preset long short-term memory (LSTM) model, and the reduced operation data is an operation data sequence.

[0086] Specifically, the operation data sequence is input into the preset long short-term memory model for nitrogen oxide emission prediction, so as to obtain the nitrogen oxide emission of the diesel engine.

[0087] It should be noted that the prediction model in the embodiment of the present application is not limited to the long short-term memory model (LSTM), but can also be other models.

[0088] In step 204, the target stoichiometric ratio corresponding to the nitrogen oxide emission is determined, and the target stoichiometric ratio is multiplied by the predicted nitrogen oxide emission to obtain the theoretical pre-control amount of urea.

[0089] For the embodiment of the present application, after the NOx emission is predicted, the theoretical pre-control amount of urea can be calculated according to the NOx emission and the target stoichiometric ratio. For the determination process of the target stoichiometric ratio, as an optional implementation manner, the method comprises: obtaining discrete stoichiometric ratios at different SCR catalyst average temperatures from a preset stoichiometric ratio table; determining an SCR catalyst aging factor, correcting the discrete stoichiometric ratios at the different SCR catalyst average temperatures based on the SCR catalyst aging factor to obtain a plurality of corrected discrete stoichiometric ratios; performing interpolation processing on the plurality of corrected discrete stoichiometric ratios to obtain a stoichiometric ratio curve; obtaining an SCR catalyst upstream temperature and an SCR catalyst downstream temperature, and calculating an SCR catalyst average temperature according to the SCR catalyst upstream temperature and the SCR catalyst downstream temperature; and determining a target stoichiometric ratio corresponding to the SCR catalyst average temperature according to the stoichiometric ratio curve.

[0090] Specifically, some discrete stoichiometric ratios can be extracted from a preset stoichiometric ratio table (MAP), and the discrete stoichiometric ratios are corrected according to an SCR catalyst aging factor. Then, by performing interpolation processing on the corrected discrete stoichiometric ratios, a curve of the stoichiometric ratio with respect to the SCR catalyst average temperature can be obtained, and the Newton interpolation method or the Lagrange interpolation method can be used for interpolation processing.

[0091] Further, according to the temperature upstream of the SCR catalyst and the temperature downstream of the SCR catalyst, the average temperature of the SCR catalyst is calculated, and then according to the calculated average temperature of the SCR catalyst, the stoichiometric ratio curve is looked up to determine the target stoichiometric ratio corresponding to the average temperature of the SCR catalyst. Then the determined target stoichiometric ratio is multiplied by the predicted nitrogen oxide emission amount to obtain the theoretical pre-control amount of urea.

[0092] Step 205, according to the theoretical pre-control amount, the first actual pre-control amount of urea is calculated, and the second actual pre-control amount of urea when the diesel engine is in a special working condition is determined.

[0093] For the embodiment of the present application, after the theoretical pre-control amount of urea is determined, the first actual pre-control amount of urea can be calculated based on the theoretical pre-control amount. For this process, the method comprises: obtaining the total mileage of the vehicle, the aging factor of the SCR catalyst, the ratio of NO to NO2, the original exhaust temperature and the average temperature of the SCR catalyst; according to the total mileage of the vehicle, the aging factor of the SCR catalyst, the ratio of NO to NO2, the original exhaust temperature and the average temperature of the SCR catalyst, a preset SCR catalyst conversion efficiency chart is looked up to determine the target conversion efficiency; the theoretical pre-control amount is multiplied by the target conversion efficiency to obtain the first actual pre-control amount of urea.

[0094] In addition, the second actual pre-control amount of urea can also be calculated independently of the SCR model. For this process, the method comprises: obtaining the temperature upstream of the SCR catalyst, the upstream nitrogen oxide mass flow, the exhaust gas mass flow, the aging factor of the SCR catalyst and the HC pollution condition of the SCR catalyst; according to the temperature upstream of the SCR catalyst and the upstream nitrogen oxide mass flow, a preset basic pre-control amount chart is looked up to determine the corresponding basic pre-control amount; according to the exhaust gas mass flow, the aging factor of the SCR catalyst and the HC pollution condition of the SCR catalyst, a preset pre-control amount correction chart is looked up to determine the corresponding pre-control amount correction coefficient; the basic pre-control amount is multiplied by the pre-control amount correction coefficient to obtain the second actual pre-control amount of urea.

[0095] In this way, the first actual pre-control amount and the second actual pre-control amount of urea can be calculated in the above-mentioned manner, so as to determine the injection amount of urea according to the first actual pre-control amount and the second actual pre-control amount.

[0096] Step 206, if the diesel engine is in a special working condition, the second actual pre-control amount is determined as the urea injection amount.

[0097] For the embodiment of the present application, if the ambient temperature, the ambient pressure, the HC state, the SCR average temperature and the engine operating state all meet the corresponding conditions, it is determined that the engine is in a special working condition, at this time the state machine issues an active adaptation instruction, and the pre-control amount is switched from the first actual pre-control amount to the second actual pre-control amount, that is, the second actual pre-control amount is selected as the urea injection amount.

[0098] Step 207, if the diesel engine is in a normal working condition, the first actual pre-control amount is determined as the urea injection amount.

[0099] For the embodiment of the present application, when the diesel engine is in a normal working condition, the first actual pre-control amount is usually selected as the urea injection amount.

[0100] Another urea injection amount calculation method provided by the embodiment of the present application adopts the idea of replacing software with hardware, and replaces the traditional SCR upstream NOx sensor with a virtual sensor, which makes up for the limitations of the NOx sensor, has a fast response time and low cost, is conducive to realizing precise urea injection, and in addition, the embodiment of the present application adopts a principal component analysis algorithm to perform dimensionality reduction processing on the operating data of the diesel engine, which can reduce the calculation amount and improve the calculation efficiency of the nitrogen oxide emission amount, and further, the embodiment of the present application can realize precise urea injection under different working conditions of the diesel engine by calculating the first actual pre-control amount and the second actual pre-control amount.

[0101] Further, as a specific implementation of Figure 1 , the embodiment of the present application provides a urea injection amount calculation device, as shown in Figure 3 , the device comprises an acquisition unit 31, a dimensionality reduction unit 32, a prediction unit 33, a determination unit 34 and a calculation unit 35.

[0102] The acquisition unit 31 can be used to acquire the operating data of the diesel engine.

[0103] The dimensionality reduction unit 32 can be used to perform dimensionality reduction processing on the operating data by using a preset principal component analysis algorithm to obtain dimensionally reduced operating data.

[0104] The prediction unit 33 can be used to input the dimensionally reduced operating data into a preset nitrogen oxide emission amount prediction model in time sequence to predict the nitrogen oxide emission amount, thereby obtaining the nitrogen oxide emission amount of the diesel engine, wherein the preset nitrogen oxide emission amount prediction model represents the mapping relationship between the dimensionally reduced operating data and the nitrogen oxide emission amount.

[0105] The determining unit 34 can be configured to determine a target stoichiometric ratio corresponding to the nitrogen oxide emission amount, and multiply the target stoichiometric ratio by the predicted nitrogen oxide emission amount to obtain a theoretical pre-control amount of urea.

[0106] The calculating unit 35 can be configured to calculate a first actual pre-control amount of urea according to the theoretical pre-control amount, and determine a second actual pre-control amount of urea when the diesel engine is in a special working condition.

[0107] The determining unit 34 can also be configured to determine a urea injection amount based on the first actual pre-control amount and the second actual pre-control amount.

[0108] In a specific application scenario, the dimension reduction unit 32 can include a first determining module 321, a first calculating module 322 and a sorting module 323, as shown in the figure. Figure 4

[0109] The first determining module 321 can be configured to determine a parameter matrix composed of the running data.

[0110] The first calculating module 322 can be configured to calculate a covariance matrix corresponding to the parameter matrix.

[0111] The first calculating module 322 can also be configured to calculate each eigenvalue corresponding to the covariance matrix, and an eigenvector corresponding to each eigenvalue.

[0112] The sorting module 323 can be configured to calculate a contribution rate corresponding to each eigenvector according to each eigenvalue, sort each eigenvector according to the contribution rate, and obtain a sorting result.

[0113] The first determining module 321 can also be configured to select a target eigenvector ranked within a preset range from each eigenvector according to the sorting result.

[0114] The first calculating module 322 can also be configured to add the contribution rates corresponding to the target eigenvectors to obtain a cumulative contribution rate of the target eigenvectors.

[0115] The first calculating module 322 can also be configured to, if the cumulative contribution rate is greater than a preset contribution rate, compose a conversion matrix with the target eigenvectors, and multiply the parameter matrix by the conversion matrix to obtain the running data after dimension reduction.

[0116] ​In a specific application scenario, the preset nitrogen oxide emission prediction model is a preset long short-term memory model, the reduced dimension operation data is an operation data sequence, and the prediction unit 33 can be specifically configured to input the operation data sequence into the preset long short-term memory model to predict the nitrogen oxide emission, thereby obtaining the nitrogen oxide emission of the diesel engine.

[0117] In a specific application scenario, the determination unit 34 includes a first acquisition module 341, a second determination module 342, an interpolation module 343, and a second calculation module 344.

[0118] The first acquisition module 341 can be configured to acquire discrete stoichiometric ratios at different SCR catalyst average temperatures from a preset stoichiometric ratio table.

[0119] The second determination module 342 can be configured to determine an SCR catalyst aging factor, correct the discrete stoichiometric ratios at the different SCR catalyst average temperatures based on the SCR catalyst aging factor, and obtain a plurality of corrected discrete stoichiometric ratios.

[0120] The interpolation module 343 can be configured to perform interpolation processing on the plurality of corrected discrete stoichiometric ratios to obtain a stoichiometric ratio curve.

[0121] The second calculation module 344 can be configured to acquire an SCR catalyst upstream temperature and an SCR catalyst downstream temperature, and calculate an SCR catalyst average temperature according to the SCR catalyst upstream temperature and the SCR catalyst downstream temperature.

[0122] The second determination module 342 can also be configured to determine a target stoichiometric ratio corresponding to the SCR catalyst average temperature according to the stoichiometric ratio curve.

[0123] In a specific application scenario, the calculation unit 35 includes a second acquisition module 351, a third determination module 352, and a third calculation module 353.

[0124] The second acquisition module 351 can be configured to acquire a total vehicle mileage, an SCR catalyst aging factor, a ratio of NO to NO2, an original exhaust temperature, and an SCR catalyst average temperature.

[0125] The third determination module 352 can be configured to query a preset SCR catalyst conversion efficiency table according to the total vehicle mileage, the SCR catalyst aging factor, the ratio of NO to NO2, the original exhaust temperature, and the SCR catalyst average temperature, and determine a target conversion efficiency.

[0126] The third calculation module 353 can be configured to multiply the theoretical pre-control amount by the target conversion efficiency to obtain a first actual pre-control amount of the urea.

[0127] Further, the second acquisition module 351 can be further configured to acquire an upstream temperature of the SCR catalyst, an upstream nitrogen oxide mass flow, an exhaust gas mass flow, an aging factor of the SCR catalyst, and an HC pollution condition of the SCR catalyst.

[0128] The third determination module 352 can be further configured to query a preset basic pre-control amount chart according to the upstream temperature of the SCR catalyst and the upstream nitrogen oxide mass flow to determine a corresponding basic pre-control amount.

[0129] The third determination module 352 can be further configured to query a preset pre-control amount correction chart according to the exhaust gas mass flow, the aging factor of the SCR catalyst and the HC pollution condition of the SCR catalyst to determine a corresponding pre-control amount correction coefficient.

[0130] The third calculation module 353 can be further configured to multiply the basic pre-control amount by the pre-control amount correction coefficient to obtain a second actual pre-control amount of the urea.

[0131] In a specific application scenario, the determination unit 34 can be specifically configured to determine the second actual pre-control amount as the urea injection amount if the diesel engine is in a special working condition, and determine the first actual pre-control amount as the urea injection amount if the diesel engine is in a normal working condition.

[0132] It should be noted that other corresponding descriptions of the various functional modules involved in the urea injection amount calculation device provided by the embodiments of the present application can be referred to the corresponding descriptions of the method shown in Figure 1 The method shown in the figure, and will not be repeated here.

[0133] Based on the above as Figure 1According to the method, the embodiment of the present application also provides a computer readable storage medium, which has a computer program stored thereon, and the program is executed by a processor to realize the following steps: obtaining operation data of a diesel engine; performing dimension reduction processing on the operation data by using a preset principal component analysis algorithm to obtain reduced dimension operation data; inputting the reduced dimension operation data into a preset nitrogen oxide emission amount prediction model in time sequence to predict nitrogen oxide emission amount, so as to obtain the nitrogen oxide emission amount of the diesel engine, wherein the preset nitrogen oxide emission amount prediction model represents a mapping relationship between the reduced dimension operation data and the nitrogen oxide emission amount; determining a target stoichiometric ratio corresponding to the nitrogen oxide emission amount, and multiplying the target stoichiometric ratio by the predicted nitrogen oxide emission amount to obtain a theoretical pre-control amount of urea; calculating a first actual pre-control amount of urea according to the theoretical pre-control amount, and determining a second actual pre-control amount of urea when the diesel engine is in a special working condition; and determining a urea injection amount based on the first actual pre-control amount and the second actual pre-control amount.

[0134] According to the method and the device, the embodiment of the present application also provides an entity structure diagram of an electronic device, as shown in the figure, the electronic device comprises a processor 41, a memory 42, and a computer program stored in the memory 42 and executable on the processor, wherein the memory 42 and the processor 41 are arranged on a bus 43, and the processor 41 realizes the following steps when executing the program: obtaining operation data of a diesel engine; performing dimension reduction processing on the operation data by using a preset principal component analysis algorithm to obtain reduced dimension operation data; inputting the reduced dimension operation data into a preset nitrogen oxide emission amount prediction model in time sequence to predict nitrogen oxide emission amount, so as to obtain the nitrogen oxide emission amount of the diesel engine, wherein the preset nitrogen oxide emission amount prediction model represents a mapping relationship between the reduced dimension operation data and the nitrogen oxide emission amount; determining a target stoichiometric ratio corresponding to the nitrogen oxide emission amount, and multiplying the target stoichiometric ratio by the predicted nitrogen oxide emission amount to obtain a theoretical pre-control amount of urea; calculating a first actual pre-control amount of urea according to the theoretical pre-control amount, and determining a second actual pre-control amount of urea when the diesel engine is in a special working condition; and determining a urea injection amount based on the first actual pre-control amount and the second actual pre-control amount. Figure 1 Figure 3 According to the method and the device, the embodiment of the present application also provides an entity structure diagram of an electronic device, as shown in the figure, the electronic device comprises a processor 41, a memory 42, and a computer program stored in the memory 42 and executable on the processor, wherein the memory 42 and the processor 41 are arranged on a bus 43, and the processor 41 realizes the following steps when executing the program: obtaining operation data of a diesel engine; performing dimension reduction processing on the operation data by using a preset principal component analysis algorithm to obtain reduced dimension operation data; inputting the reduced dimension operation data into a preset nitrogen oxide emission amount prediction model in time sequence to predict nitrogen oxide emission amount, so as to obtain the nitrogen oxide emission amount of the diesel engine, wherein the preset nitrogen oxide emission amount prediction model represents a mapping relationship between the reduced dimension operation data and the nitrogen oxide emission amount; determining a target stoichiometric ratio corresponding to the nitrogen oxide emission amount, and multiplying the target stoichiometric ratio by the predicted nitrogen oxide emission amount to obtain a theoretical pre-control amount of urea; calculating a first actual pre-control amount of urea according to the theoretical pre-control amount, and determining a second actual pre-control amount of urea when the diesel engine is in a special working condition; and determining a urea injection amount based on the first actual pre-control amount and the second actual pre-control amount. Figure 5

[0135] ​​The embodiment of the present application adopts the idea of replacing hardware with software, replaces the traditional SCR upstream NOx sensor with a virtual sensor, makes up for the limitations of the NOx sensor, has fast response time, low cost, and is conducive to realizing precise injection of urea, in addition, the embodiment of the present application adopts a principal component analysis algorithm to perform dimension reduction processing on the operation data of the diesel engine, can reduce the amount of calculation, improve the calculation efficiency of the nitrogen oxide emission, and further, the embodiment of the present application can realize precise injection of urea under different operating conditions of the diesel engine by calculating the first actual pre-control amount and the second actual pre-control amount.

[0136] Those skilled in the art can understand that the drawings are only schematic diagrams of an embodiment, and the modules or flows in the drawings are not necessarily necessary for implementing the present application.

[0137] Those skilled in the art can understand that the modules in the device in the embodiment can be distributed in the device in the embodiment according to the description of the embodiment, or can be changed and located in one or more devices different from the embodiment. The modules in the above embodiment can be combined into one module, or can be further split into multiple sub-modules.

[0138] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for calculating urea injection volume, characterized in that, include: Acquire the operating data of the diesel engine; the operating data of the diesel engine includes engine speed, torque, fuel injection quantity, intake air flow, intake air pressure, intake air temperature, oxygen concentration, oil pressure, oil temperature, coolant temperature, EGR opening, atmospheric pressure, atmospheric temperature, rail pressure, and main injection advance angle. The running data is dimensionality reduced by using a preset principal component analysis algorithm to obtain dimensionality-reduced running data. The reduced operating data is sequentially input into a preset nitrogen oxide emission prediction model in chronological order to predict nitrogen oxide emissions, thereby obtaining the nitrogen oxide emissions of the diesel engine. The preset nitrogen oxide emission prediction model represents the mapping relationship between the reduced operating data and nitrogen oxide emissions. Determine the target stoichiometric ratio corresponding to the nitrogen oxide emissions, and multiply the target stoichiometric ratio by the predicted nitrogen oxide emissions to obtain the theoretical pre-controlled amount of urea; Based on the theoretical pre-control quantity, calculate the first actual pre-control quantity of urea, and determine the second actual pre-control quantity of urea when the diesel engine is under special operating conditions; if the ambient temperature, ambient pressure, HC state, SCR catalyst average temperature, and engine operating state all meet the corresponding conditions, then the diesel engine is considered to be under special operating conditions; wherein, the calculation of the first actual pre-control quantity of urea based on the theoretical pre-control quantity includes: obtaining the total vehicle mileage, SCR catalyst aging factor, NO to NO2 ratio, original exhaust temperature, and SCR catalyst average temperature; based on the total vehicle mileage, the SCR catalyst aging factor, the NO to NO2 ratio, the original exhaust temperature, and the SCR catalyst average temperature, query a preset SCR catalyst conversion efficiency chart to determine the target conversion efficiency; The theoretical pre-controlled quantity is multiplied by the target conversion efficiency to obtain the first actual pre-controlled quantity of urea; wherein, determining the second actual pre-controlled quantity of urea when the diesel engine is under special operating conditions includes: obtaining the upstream temperature of the SCR catalyst, the upstream nitrogen oxide mass flow rate, the exhaust gas mass flow rate, the SCR catalyst aging factor, and the HC pollution status of the SCR catalyst; based on the upstream temperature of the SCR catalyst and the upstream nitrogen oxide mass flow rate, querying a preset basic pre-controlled quantity chart to determine the corresponding basic pre-controlled quantity; based on the exhaust gas mass flow rate, the SCR catalyst aging factor, and the HC pollution status of the SCR catalyst, querying a preset pre-controlled quantity correction chart to determine the corresponding pre-controlled quantity correction coefficient; multiplying the basic pre-controlled quantity by the pre-controlled quantity correction coefficient to obtain the second actual pre-controlled quantity of urea; Based on the first actual pre-controlled quantity and the second actual pre-controlled quantity, the urea injection quantity is determined; specifically, if the diesel engine is under special operating conditions, the second actual pre-controlled quantity is determined as the urea injection quantity; if the diesel engine is under normal operating conditions, the first actual pre-controlled quantity is determined as the urea injection quantity.

2. The method according to claim 1, characterized in that, The step of using a preset principal component analysis algorithm to perform dimensionality reduction processing on the running data to obtain dimensionality-reduced running data includes: Determine the parameter matrix composed of the running data; Calculate the covariance matrix corresponding to the parameter matrix; Calculate the eigenvalues ​​corresponding to the covariance matrix and the eigenvectors corresponding to the eigenvalues; Based on each feature value, the contribution rate corresponding to each feature vector is calculated, and the feature vectors are sorted according to the contribution rate to obtain the sorting result; Based on the sorting results, target feature vectors ranked within a preset range are selected from each feature vector. The cumulative contribution rate of the target feature vector is obtained by summing the contribution rates corresponding to the target feature vectors. If the cumulative contribution rate is greater than the preset contribution rate, the target feature vectors are used to form a transformation matrix, and the parameter matrix is ​​multiplied by the transformation matrix to obtain the dimensionality-reduced running data.

3. The method according to claim 1, characterized in that, The preset nitrogen oxide emission prediction model is a preset long short-term memory model, and the dimensionality-reduced operating data is an operating data sequence. The step of sequentially inputting the dimensionality-reduced operating data into the preset nitrogen oxide emission prediction model in chronological order to predict nitrogen oxide emissions and obtain the nitrogen oxide emissions of the diesel engine includes: The operating data sequence is input into the preset long short-term memory model to predict nitrogen oxide emissions, thereby obtaining the nitrogen oxide emissions of the diesel engine.

4. The method according to claim 1, characterized in that, Determining the target stoichiometric ratio corresponding to the nitrogen oxide emissions includes: Obtain the discrete stoichiometry at the average temperature of different SCR catalysts from a preset stoichiometric ratio chart; The SCR catalyst aging factor is determined, and the discrete stoichiometry of the SCR catalyst at the average temperature of different SCR catalysts is corrected based on the SCR catalyst aging factor to obtain multiple corrected discrete stoichiometry. Interpolation processing is performed on the multiple corrected discrete stoichiometric ratios to obtain stoichiometric ratio curves; The upstream temperature and downstream temperature of the SCR catalyst are obtained, and the average temperature of the SCR catalyst is calculated based on the upstream temperature and downstream temperature of the SCR catalyst. Based on the stoichiometric curve, the target stoichiometric ratio corresponding to the average temperature of the SCR catalyst is determined.

5. A urea injection quantity calculation device, characterized in that, include: The acquisition unit is used to acquire the operating data of the diesel engine; the operating data of the diesel engine includes engine speed, torque, fuel injection quantity, intake air flow, intake air pressure, intake air temperature, oxygen concentration, oil pressure, oil temperature, coolant temperature, EGR opening, atmospheric pressure, atmospheric temperature, rail pressure, and main injection advance angle. The dimensionality reduction unit is used to perform dimensionality reduction processing on the running data using a preset principal component analysis algorithm to obtain the dimensionality-reduced running data. The prediction unit is used to input the dimensionality-reduced operating data into a preset nitrogen oxide emission prediction model in chronological order to predict nitrogen oxide emissions and obtain the nitrogen oxide emissions of the diesel engine. The preset nitrogen oxide emission prediction model represents the mapping relationship between the dimensionality-reduced operating data and nitrogen oxide emissions. The determining unit is used to determine the target stoichiometric ratio corresponding to the nitrogen oxide emission amount, and multiply the target stoichiometric ratio by the predicted nitrogen oxide emission amount to obtain the theoretical pre-controlled amount of urea; The calculation unit is used to calculate the first actual pre-controlled amount of urea based on the theoretical pre-controlled amount, and to determine the second actual pre-controlled amount of urea when the diesel engine is under special operating conditions. If the ambient temperature, ambient pressure, HC state, average temperature of the SCR catalyst, and engine operating conditions all meet the corresponding conditions, the diesel engine is considered to be under special operating conditions. Specifically, the calculation unit is used to: obtain the total vehicle mileage, SCR catalyst aging factor, NO to NO2 ratio, original exhaust temperature, and average temperature of the SCR catalyst; and, based on the total vehicle mileage, the SCR catalyst aging factor, the NO to NO2 ratio, the original exhaust temperature, and the average temperature of the SCR catalyst, query a preset SCR catalyst conversion efficiency chart to determine the target conversion efficiency. The calculation unit is further used to: obtain the upstream temperature of the SCR catalyst, the upstream nitrogen oxide mass flow rate, the exhaust gas mass flow rate, the SCR catalyst aging factor, and the HC pollution status of the SCR catalyst; based on the upstream temperature of the SCR catalyst and the upstream nitrogen oxide mass flow rate, query a preset basic control quantity chart to determine the corresponding basic control quantity; based on the exhaust gas mass flow rate, the SCR catalyst aging factor, and the HC pollution status of the SCR catalyst, query a preset control quantity correction chart to determine the corresponding control quantity correction coefficient; and multiply the basic control quantity by the control quantity correction coefficient to obtain the second actual control quantity of the urea. The determining unit is further configured to determine the urea injection quantity based on the first actual pre-controlled quantity and the second actual pre-controlled quantity; specifically, the determining unit is configured to: if the diesel engine is under special operating conditions, determine the second actual pre-controlled quantity as the urea injection quantity; if the diesel engine is under normal operating conditions, determine the first actual pre-controlled quantity as the urea injection quantity.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images