Method and device for monitoring ammonia leakage

Abstract

The application discloses an ammonia leakage monitoring method and device, and relates to the technical field of diesel engine exhaust aftertreatment, which comprises the following steps: obtaining current working condition parameters of a diesel engine; determining whether ammonia leakage exists in an SCR system according to the urea concentration, urea pump pressure and nitrogen oxide concentration downstream of the SCR system in the working condition parameters; if ammonia leakage exists in the SCR system, inputting the working condition parameters into a preset ammonia leakage amount prediction model to predict the ammonia leakage amount, wherein the preset ammonia leakage amount prediction model represents the mapping relationship between different working condition parameters of the diesel engine and different ammonia leakage amounts; and determining the actual urea injection amount of the diesel engine according to the predicted ammonia leakage amount. By applying the technical scheme of the application, the problems of difficult installation and high cost of hardware monitoring equipment can be solved, and the ammonia leakage amount can be effectively calculated.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of diesel engine exhaust aftertreatment technology, in particular to an ammonia leakage monitoring method and device. BACKGROUND

[0002] SCR system is one of the diesel engine exhaust aftertreatment technologies, which can effectively remove nitrogen oxides in exhaust gas by injecting urea solution. The closed-loop control strategy based on NOx sensor is the main control strategy of SCR system, but due to the cross-sensitivity of nitrogen oxide sensor to ammonia and NOx, ammonia leakage may cause continuous increase of urea injection amount, resulting in more ammonia leakage, which is harmful to the engine, so ammonia needs to be monitored.

[0003] At present, exhaust gas analyzers, ammonia sensors and other equipment are usually used to monitor ammonia in exhaust gas. However, this method not only has difficulty in installation and high cost, but also cannot effectively determine the amount of ammonia leakage. SUMMARY

[0004] The present application provides an ammonia leakage monitoring method and device, which can solve the problems of difficult installation and high cost of hardware monitoring equipment, and can also effectively calculate the amount of ammonia leakage, provide guidance for urea injection control strategy, and realize accurate injection.

[0005] According to a first aspect of the embodiment of the present application, an ammonia leakage monitoring method is provided, comprising:

[0006] obtaining current working condition parameters of a diesel engine;

[0007] determining whether there is ammonia leakage in the SCR system according to the urea concentration, urea pump pressure and nitrogen oxide concentration downstream of the SCR system in the working condition parameters;

[0008] if there is ammonia leakage in the SCR system, inputting the working condition parameters into a preset ammonia leakage amount prediction model to predict the ammonia leakage amount, and obtaining the ammonia leakage amount of the SCR system, wherein the preset ammonia leakage amount prediction model represents the mapping relationship between different working condition parameters of the diesel engine and different ammonia leakage amounts;

[0009] determining the actual urea injection amount of the diesel engine according to the predicted ammonia leakage amount.

[0010] According to a second aspect of the embodiment of the present application, an ammonia leakage monitoring device is provided, comprising:

[0011] an acquisition unit for acquiring current working condition parameters of a diesel engine;

[0012] determining whether the SCR system has ammonia leakage according to urea concentration, urea pump pressure and nitrogen oxide concentration downstream of the SCR system in the working condition parameters;

[0013] predicting ammonia leakage amount of the SCR system by inputting the working condition parameters into a preset ammonia leakage amount prediction model if the SCR system has ammonia leakage, wherein the preset ammonia leakage amount prediction model represents a mapping relationship between different working condition parameters of the diesel engine and different ammonia leakage amounts.

[0014] determining actual urea injection amount of the diesel engine according to the predicted ammonia leakage amount.

[0015] According to a third aspect of the embodiment of the present application, a computer readable storage medium is provided, which stores a computer program, and the program is executed by a processor to implement the following steps:

[0016] obtaining current working condition parameters of a diesel engine;

[0017] determining whether the SCR system has ammonia leakage according to urea concentration, urea pump pressure and nitrogen oxide concentration downstream of the SCR system in the working condition parameters;

[0018] predicting ammonia leakage amount of the SCR system by inputting the working condition parameters into a preset ammonia leakage amount prediction model if the SCR system has ammonia leakage, wherein the preset ammonia leakage amount prediction model represents a mapping relationship between different working condition parameters of the diesel engine and different ammonia leakage amounts.

[0019] determining actual urea injection amount of the diesel engine according to the predicted ammonia leakage amount.

[0020] According to a fourth aspect of the embodiment of the present application, an electronic device is provided, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the following steps when executing the program:

[0021] obtaining current working condition parameters of a diesel engine;

[0022] determining whether the SCR system has ammonia leakage according to urea concentration, urea pump pressure and nitrogen oxide concentration downstream of the SCR system in the working condition parameters;

[0023] If the ammonia leakage exists in the SCR system, the working condition parameters are input into a preset ammonia leakage amount prediction model to predict the ammonia leakage amount, so as to obtain the ammonia leakage amount of the SCR system, wherein the preset ammonia leakage amount prediction model represents the mapping relationship between different working condition parameters of the diesel engine and different ammonia leakage amounts.

[0024] According to the predicted ammonia leakage amount, the actual urea injection amount of the diesel engine is determined.

[0025] The innovation points of the embodiments of the present application include:

[0026] 1. According to the working condition data of the diesel engine, it is determined whether the ammonia leakage exists in the SCR system, so as to solve the problems of difficult installation and high cost of hardware monitoring equipment, which is one of the innovation points of the embodiments of the present application.

[0027] 2. The ammonia leakage amount is monitored in real time and accurately, which provides guidance for the urea injection control strategy, and realizes accurate injection, which is one of the innovation points of the embodiments of the present application.

[0028] The ammonia leakage monitoring method and device provided by the present application can obtain the current working condition parameters of the diesel engine, and determine whether the ammonia leakage exists in the SCR system according to the urea concentration, the urea pump pressure and the nitrogen oxide concentration downstream of the SCR system in the working condition parameters. If the ammonia leakage exists in the SCR system, the working condition parameters are input into a preset ammonia leakage amount prediction model to predict the ammonia leakage amount, so as to obtain the ammonia leakage amount of the SCR system, wherein the preset ammonia leakage amount prediction model represents the mapping relationship between different working condition parameters of the diesel engine and different ammonia leakage amounts. Finally, according to the predicted ammonia leakage amount, the actual urea injection amount of the diesel engine is determined. Therefore, according to the working condition data of the diesel engine, it is determined whether the ammonia leakage exists in the SCR system, and in the case of ammonia leakage, the ammonia leakage amount of the SCR system is determined by using the preset ammonia leakage amount prediction model. Not only can the problems of high cost and difficult installation of hardware monitoring equipment be solved, but also the ammonia leakage amount can be monitored in real time and accurately, which provides guidance for the urea injection control strategy, so as to realize accurate injection.

[0029] The above description is only a summary of the technical solutions of the present application. In order to more clearly understand the technical means of the present application, the specific embodiments of the present application can be implemented according to the content of the description, and in order to make the above and other purposes, characteristics and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0030] In order to make the technical solutions in the embodiments of the present application or the prior art clearer, the accompanying drawings needed in the embodiments or prior art description will be briefly introduced. Obviously, the accompanying drawings in the following description only aim to some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative effort based on these drawings.

[0031] Figure 1 A flowchart of an ammonia leakage monitoring method provided by an embodiment of the present application is shown.

[0032] Figure 2 A flowchart of another ammonia leakage monitoring method provided by an embodiment of the present application is shown.

[0033] Figure 3 A structural diagram of an ammonia leakage monitoring device provided by an embodiment of the present application is shown.

[0034] Figure 4 A structural diagram of another ammonia leakage monitoring device provided by an embodiment of the present application is shown.

[0035] Figure 5 A physical structure diagram of an electronic device provided by an embodiment of the present application is shown. DETAILED DESCRIPTION

[0036] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort belong to the protection scope of the present application.

[0037] It should be noted that the terms "include" and "have" and any variations thereof in the embodiments of the present application and the accompanying 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.

[0038] The prior art is not only difficult to install and high in cost, but also cannot effectively determine the ammonia leakage amount.

[0039] In order to overcome the above-mentioned defects, an ammonia leakage monitoring method is provided by an embodiment of the present application, as shown in the figure, which comprises the following steps. Figure 1

[0040] Step 101: Obtain the current working condition parameters of the diesel engine.​

[0041] The working condition parameters of the diesel engine include SCR upstream nitrogen oxide concentration, SCR downstream nitrogen oxide concentration, crank angle, ambient temperature, cooling water temperature, urea concentration, urea pump pressure, intake air pressure, SCR upstream exhaust gas temperature and catalyst temperature.

[0042] The embodiment of the present application is mainly applicable to the scene of monitoring whether the SCR system exists ammonia leakage and calculating the ammonia leakage amount. The execution subject of the embodiment of the present application is a device or equipment capable of monitoring whether the SCR system exists ammonia leakage and calculating the ammonia leakage amount.

[0043] The monitoring system of the embodiment of the present application comprises a data acquisition module, a communication module, a data processing module and a data storage module. The data acquisition module is used to acquire the working condition parameters of the diesel engine. The sensor unit, DCU, ECU and other control units in the communication module are all configured with communication interfaces, and data transmission is performed through the can bus. The sensor unit transmits the acquired physical signals to the DCU through the can bus, and the DCU, ECU and other control units also share data through the can bus. The data processing module is used to determine whether the SCR system exists ammonia leakage, and calculate the ammonia leakage amount in the case of ammonia leakage. The data storage module is used to record the engine working condition parameters and the corresponding ammonia leakage amount in real time when ammonia leakage occurs, and save the data in the ECU, thereby providing data basis for improving the urea injection strategy and reducing ammonia leakage.

[0044] Specifically, different types of sensors can be used to acquire the SCR upstream nitrogen oxide concentration, SCR downstream nitrogen oxide concentration, crank angle, ambient temperature, cooling water temperature, urea concentration, urea pump pressure, intake air pressure, SCR upstream exhaust gas temperature and catalyst temperature, and then the acquired sensor voltage signals, current signals and resistance signals are converted into digital signals through A / D conversion, so as to facilitate subsequent data processing.

[0045] Step 102, according to the urea concentration, urea pump pressure and nitrogen oxide concentration downstream of the SCR system in the working condition parameters, it is determined whether the SCR system exists ammonia leakage.

[0046] For the embodiment of the present application, in order to determine whether the SCR system has ammonia leakage, step 102 specifically comprises: determining whether the urea concentration in the working condition parameters is greater than or equal to a preset urea concentration and whether the urea pump pressure is greater than or equal to a preset pressure; if the urea concentration is less than the preset urea concentration or the urea pump pressure is less than the preset pressure, the diesel engine is subjected to fault detection; if the urea concentration is greater than or equal to the preset urea concentration and the urea pump pressure is greater than or equal to the preset pressure, it is determined whether the nitrogen oxide concentration downstream of the SCR system in the working condition parameters is greater than a preset nitrogen oxide concentration; if the nitrogen oxide concentration is less than or equal to the preset nitrogen oxide concentration, it is determined that the SCR system does not have ammonia leakage; if the nitrogen oxide concentration is greater than the preset nitrogen oxide concentration, it is determined that the SCR system has ammonia leakage. The preset urea concentration, the preset pressure and the preset nitrogen oxide concentration can be set according to actual business needs.

[0047] Specifically, it can be determined whether the urea concentration collected by the urea quality sensor and the urea pump pressure collected by the urea pump pressure sensor are not lower than normal values. If they are lower than the normal values, it means that the engine is likely to have a fault, and at this time, fault monitoring is needed. If they are not lower than the normal values, it is further determined whether the downstream nitrogen oxide concentration is greater than a preset nitrogen oxide concentration. If it is greater than the preset nitrogen oxide concentration, it means that the SCR system has ammonia leakage. Otherwise, it means that the SCR system does not have ammonia leakage. In this way, it can be detected whether the SCR system has ammonia leakage in the above manner.

[0048] Step 103, if the SCR system has ammonia leakage, the working condition parameters are input into a preset ammonia leakage amount prediction model for ammonia leakage amount prediction, to obtain the ammonia leakage amount of the SCR system.

[0049] The preset ammonia leakage amount prediction model represents the mapping relationship between different working condition parameters of the diesel engine and different ammonia leakage amounts. The preset ammonia leakage amount prediction model can be a three-layer BP neural network model, which includes an input layer, a hidden layer and an output layer, and the input layer, the hidden layer and the output layer all contain multiple neurons.

[0050] For the embodiment of the present application, in the case that it is determined that ammonia leakage exists in the SCR system, a preset ammonia leakage amount prediction model needs to be used to calculate the ammonia leakage amount. For this process, step 103 specifically includes: the working condition parameters are transmitted from the neurons of the input layer to the neurons of the hidden layer, the neurons of the hidden layer process the working condition parameters and then transmit the processing results to the neurons of the output layer for further processing, and finally the ammonia leakage amount output by the output layer is obtained. In the three-layer network, the number n2 of the neurons of the hidden layer and the number n1 of the neurons of the input layer satisfy the following relationship:

[0051] n2=2×n1+1

[0052] Further, the three-layer BP neural network model is as follows:

[0053]

[0054] wherein X is the working condition parameter, is the predicted ammonia leakage amount, the weight from the input layer to the hidden layer is W, the bias term is b1, the activation function is g1, the weight from the hidden layer to the output layer is V, the bias term is b2, and the activation function is g2. Thus, the ammonia leakage amount of the SCR system can be predicted through the above BP neural network model. The activation function can specifically be a Sigmoid function, and the formula is as follows:

[0055]

[0056] Further, before the ammonia leakage amount is predicted, the collected working condition parameter data needs to be normalized. The normalization can be specifically realized by using a mapminmax function, and the mapminmax function is as follows:

[0057]

[0058] wherein x is any parameter element in the working condition parameters, y * is the parameter element after normalization, y max =1, and y min =-1. Thus, according to the above formula, the working condition parameter data can be mapped to the interval of -1 to 1.

[0059] Further, before calculating the ammonia leakage amount by using the model, a preset ammonia leakage amount prediction model (BP neural network model) needs to be constructed. For the model construction process, the method comprises: collecting historical working condition parameters and historical ammonia leakage amounts of the diesel engine in the case that the SCR system exists ammonia leakage; determining initial weights and initial biases between neurons by using a preset genetic algorithm, and determining an initial BP neural network model according to the initial weights and the initial biases; inputting the historical working condition parameters into the initial BP neural network model for ammonia leakage amount prediction to obtain predicted ammonia leakage amounts; constructing a loss function according to the predicted ammonia leakage amounts and the historical ammonia leakage amounts; calculating error terms of neurons in a hidden layer and error terms of neurons in an output layer according to the loss function; updating the initial weights and the initial biases according to the error terms of the neurons in the hidden layer and the error terms of the neurons in the output layer; repeating the iterative updating process of the weights and the biases until the loss function is less than a preset threshold or the number of iterations reaches a preset number, and outputting the final updated weights and biases; and constructing the preset ammonia leakage amount prediction model according to the final updated weights and biases.

[0060] Specifically, historical working condition parameters and historical ammonia leakage amounts of the diesel engine are first collected, and are corresponded and arranged to form an augmented matrix as follows,

[0061]

[0062] wherein X is the historical working condition parameters, Y is the historical ammonia leakage amounts, n is the number of samples, and p is the parameter dimension in the engine related operation data, and n > p. Further, the collected parameter data is normalized by using a mapminmax function, and the data is mapped to an interval of [-1, 1] to obtain a sample data set, and then 80% of the parameter data is randomly extracted as training samples, and the remaining 20% of the parameter data is taken as test samples.

[0063] In the specific model training, the initial weight and initial bias of the BP neural network can be obtained by the global optimization ability of the genetic algorithm, so as to avoid falling into a local minimum value in the training process. The improved BP neural network weight of the genetic algorithm is not randomly generated, but is obtained by the genetic algorithm optimization module. The initial weight and initial bias in the BP algorithm are used as the gene value of the genetic algorithm individual, the individual length is the number of weights and biases in the BP neural network, each gene represents a weight or bias, and the value on the gene is the real value of the connection weight or bias in the BP neural network, so as to form a chromosome in the genetic algorithm. A certain number of chromosomes are used as the initial population of the genetic algorithm training, and after the selection operation, the crossover operation and the mutation operation of the genetic algorithm, an optimal individual is obtained, and then the optimal individual is used as the initial parameter of the BP network for training.

[0064] Further, after the BP neural network model is trained, the historical working condition parameters in the test sample can be input into the trained BP neural network model to predict the ammonia leakage amount, and the model accuracy is evaluated according to the prediction result, and after meeting the requirements, it is used as the final preset ammonia leakage prediction model.

[0065] Step 104, determining the actual urea injection amount of the diesel engine according to the predicted ammonia leakage amount.

[0066] For the embodiment of the application, after the ammonia leakage amount of the SCR system is obtained by using the BP neural network model, the actual injection amount of urea can be adjusted according to the ammonia leakage amount, so as to realize accurate injection of urea.

[0067] The ammonia leakage monitoring method provided by the embodiment of the application not only solves the problems of high cost and difficult installation of hardware monitoring equipment, but also realizes real-time and accurate monitoring of the ammonia leakage amount, provides guidance for the urea injection control strategy, and realizes accurate injection.

[0068] Further, as a refinement and expansion of the above-mentioned embodiment, the embodiment of the application provides another ammonia leakage monitoring method, as shown in Figure 2 The method comprises:

[0069] Step 201, obtaining the current working condition parameters of the diesel engine.

[0070] The working condition parameters of the diesel engine include SCR upstream nitrogen oxide concentration, SCR downstream nitrogen oxide concentration, crank angle, ambient temperature, cooling water temperature, urea concentration, urea pump pressure, intake pressure, SCR upstream exhaust gas temperature and catalyst temperature.

[0071] For the embodiment of the present application, the process of acquiring the diesel engine working condition parameters is completely the same as step 101, and will not be repeated here.

[0072] Step 202, according to the urea concentration, urea pump pressure and nitrogen oxide concentration downstream of the SCR system in the working condition parameters, it is determined whether the SCR system exists ammonia gas leakage.

[0073] For the embodiment of the present application, not only can the way described in embodiment one be used to determine whether the SCR system exists ammonia gas leakage, but also the nitrogen oxide concentration changing with time curve can be determined according to the nitrogen oxide concentration collected by the nitrogen oxide sensor downstream of the SCR, if the concentration of the nitrogen oxide in the curve presents an overall upward trend and is about to exceed the theoretical maximum, it is determined that the SCR system exists ammonia gas leakage; on the contrary, if the nitrogen oxide concentration in the curve has no obvious upward trend and is always within a reasonable range, it is determined that the SCR system does not exist ammonia gas leakage.

[0074] Step 203, if the SCR system exists ammonia gas leakage, the working condition parameters are input into the preset ammonia gas leakage amount prediction model for ammonia gas leakage amount prediction, and the ammonia gas leakage amount of the SCR system is obtained.

[0075] Among them, the preset ammonia gas leakage amount prediction model represents the mapping relationship between different working condition parameters of the diesel engine and different ammonia gas leakage amounts.

[0076] For the embodiment of the present application, not only can the ammonia gas leakage amount be calculated through the working condition parameters of the diesel engine and the preset ammonia gas leakage amount prediction model, but also the ammonia gas leakage amount can be determined by theoretical calculation, and for the theoretical calculation process, the method comprises: calculating the ammonia gas amount injected into the SCR catalyst, the ammonia gas amount released from the wall surface of the SCR catalyst, the ammonia gas amount actually reacted with the nitrogen oxide and the ammonia gas amount adsorbed on the wall surface of the SCR catalyst after reaction; according to the ammonia gas amount injected into the SCR catalyst, the ammonia gas amount released from the wall surface of the SCR catalyst, the ammonia gas amount actually reacted with the nitrogen oxide and the ammonia gas amount adsorbed on the wall surface of the SCR catalyst after reaction, the theoretical ammonia gas leakage amount is calculated.

[0077] Because a series of chemical reactions such as urea pyrolysis, urea hydrolysis and ammonia gas adsorption and desorption will occur when urea enters the SCR catalyst, therefore when calculating the effective ammonia gas amount of the SCR catalyst, factors such as the average temperature of the SCR catalyst, the injected ammonia gas amount, the ammonia gas proportion coefficient deposited in the wall of the SCR catalyst and the ammonia gas proportion coefficient released from the wall have influence on chemical reactions and ammonia gas amount.

[0078] Specifically, for the ammonia amount injected into the SCR catalyst, the corresponding urea decomposition rate can be found in the urea decomposition rate MAP according to the current SCR catalyst temperature and the exhaust mass flow, and the ammonia mass flow injected into the SCR catalyst can be obtained by multiplying the injected urea amount by the urea decomposition rate.

[0079] For the ammonia amount actually reacting with nitrogen oxides, it is mainly affected by the average temperature in the SCR catalyst, the proportion of NO2 and NO in the exhaust gas, and the aging coefficient of the SCR catalyst. Specifically, the aging coefficient of the SCR catalyst and the ammonia oxidation correction coefficient of the catalyst can be obtained according to the SCR catalyst aging coefficient MAP, the catalyst ammonia oxidation coefficient MAP, and the proportion of NO2 and NO in the exhaust gas, and then the final ammonia correction coefficient can be obtained. After that, the ammonia amount actually used to convert NOx in the exhaust gas can be obtained by multiplying the theoretical ammonia mass flow used to convert NOx in the exhaust gas by the final ammonia correction coefficient.

[0080] Further, according to the SCR catalyst wall temperature and the exhaust mass flow, as well as the ammonia proportion coefficient MAP deposited in the SCR catalyst pipe wall and the pipe wall ammonia release ratio coefficient MAP, the corresponding ammonia proportion coefficient deposited in the SCR catalyst pipe wall and the pipe wall ammonia release ratio coefficient can be obtained. After that, the ammonia mass flow adsorbed on the SCR catalyst wall can be obtained by multiplying the ammonia mass flow injected into the SCR catalyst by the deposition coefficient, and then the ammonia mass flow released by the SCR catalyst wall can be obtained by multiplying the amount of ammonia currently stored on the exhaust pipe upstream of the SCR by the pipe wall ammonia release ratio coefficient.

[0081] Finally, the theoretical ammonia leakage amount = ammonia amount injected into the SCR catalyst + ammonia amount released by the SCR catalyst wall - ammonia amount actually reacting with nitrogen oxides - ammonia amount adsorbed on the SCR catalyst wall after reaction. Thus, the theoretical ammonia leakage amount can be accurately calculated in the above manner.

[0082] In specific application scenarios, in order to ensure the prediction accuracy of the ammonia leakage amount, the prediction result of the model can be evaluated according to the theoretical ammonia leakage amount obtained above. Specifically, if the predicted ammonia leakage amount deviates too far from the theoretical ammonia leakage amount, it means that the prediction result of the model this time is not very reliable; on the contrary, if the predicted ammonia leakage amount does not deviate too far from the theoretical ammonia leakage amount, it means that the prediction result of the model this time is relatively reliable.

[0083] Meanwhile, the effect of the prediction model can also be evaluated according to the multiple ammonia leakage amounts predicted within a test cycle and the corresponding actual ammonia leakage amounts. Based on this, the method comprises: obtaining multiple ammonia leakage amounts predicted within a test cycle of the diesel engine; calculating the mean square error of the multiple predicted ammonia leakage amounts and the corresponding actual ammonia leakage amounts; and if the mean square error is within a preset range, determining that the prediction effect of the preset ammonia leakage amount prediction model meets the standard. The specific calculation formula of the mean square error is as follows,

[0084]

[0085] wherein MES is the mean square error of the ammonia leakage amount predicted by the model and the actual ammonia leakage amount, n is the number of samples, w i is the weight corresponding to each sample, y i is the predicted ammonia leakage amount, is the actual ammonia leakage amount. Further, after calculating the mean square error of the ammonia leakage amount predicted by the model and the actual ammonia leakage amount according to the above formula, if the calculated mean square error is within a reasonable range, it indicates that the prediction effect of the model meets the standard; on the contrary, if the calculated mean square error is not within a reasonable range, it indicates that the prediction effect of the model does not meet the standard, and the parameters in the model need to be updated at this time.

[0086] Step 204: obtaining a theoretical urea injection amount and determining the urea injection amount corresponding to the ammonia leakage amount.

[0087] For the embodiment of the present application, after determining the ammonia leakage amount, the corresponding urea injection amount can be calculated according to the determined ammonia leakage amount. At the same time, the ECU unit calculates a theoretical urea injection amount.

[0088] Step 205: subtracting the theoretical urea injection amount from the urea injection amount corresponding to the ammonia leakage amount to obtain the actual urea injection amount.

[0089] The other ammonia leakage monitoring method provided by the embodiment of the present application not only can solve the problems of high cost and difficult installation of hardware monitoring devices, but also can accurately monitor the ammonia leakage amount in real time, provide guidance for the urea injection control strategy, and thus realize accurate injection.

[0090] Further, as a specific implementation of Figure 1 , the embodiment of the present application provides an ammonia leakage monitoring device, as shown in Figure 3 , the device comprises an obtaining unit 31, a determining unit 32, a prediction unit 33 and a determining unit 34.

[0091] The obtaining unit 31 can be used to obtain the current working condition parameters of the diesel engine.

[0092] The determining unit 32 can be configured to determine whether the SCR system has ammonia leakage according to the urea concentration, the urea pump pressure, and the nitrogen oxide concentration downstream of the SCR system in the working condition parameters.

[0093] The predicting unit 33 can be configured to input the working condition parameters into a preset ammonia leakage amount prediction model to predict the ammonia leakage amount of the SCR system if the SCR system has ammonia leakage, wherein the preset ammonia leakage amount prediction model represents a mapping relationship between different working condition parameters of the diesel engine and different ammonia leakage amounts.

[0094] The determining unit 34 can be configured to determine the actual urea injection amount of the diesel engine according to the predicted ammonia leakage amount.

[0095] In a specific application scenario, the determining unit 32 includes a determining module 321, a detecting module 322, and a first determining module 323.

[0096] The determining module 321 can be configured to determine whether the urea concentration in the working condition parameters is greater than or equal to a preset urea concentration and whether the urea pump pressure is greater than or equal to a preset pressure.

[0097] The detecting module 322 can be configured to perform fault detection on the diesel engine if the urea concentration is less than the preset urea concentration or the urea pump pressure is less than the preset pressure.

[0098] The determining module 321 can also be configured to determine whether the nitrogen oxide concentration downstream of the SCR system in the working condition parameters is greater than a preset nitrogen oxide concentration if the urea concentration is greater than or equal to the preset urea concentration and the urea pump pressure is greater than or equal to the preset pressure.

[0099] The first determining module 323 can be configured to determine that the SCR system does not have ammonia leakage if the nitrogen oxide concentration is less than or equal to a preset nitrogen oxide concentration.

[0100] The first determining module 323 can also be configured to determine that the SCR system has ammonia leakage if the nitrogen oxide concentration is greater than a preset nitrogen oxide concentration.

[0101] In a specific application scenario, the preset ammonia leakage amount prediction model is a three-layer BP neural network model, the BP neural network model comprises an input layer, a hidden layer and an output layer, the input layer, the hidden layer and the output layer each comprise a plurality of neurons, the prediction unit 33 can be specifically used for transmitting the working condition parameters from the neurons of the input layer to the neurons of the hidden layer, the neurons of the hidden layer process the working condition parameters and transmit the processing results to the neurons of the output layer for further processing, and finally the ammonia leakage amount output by the output layer is obtained.

[0102] In a specific application scenario, the device further comprises a construction unit 35.

[0103] The construction unit 35 can be specifically used for collecting historical working condition parameters and historical ammonia leakage amounts of the diesel engine in the case that the SCR system exists ammonia leakage; determining initial weights and initial biases between neurons by using a preset genetic algorithm, and determining an initial BP neural network model according to the initial weights and the initial biases; inputting the historical working condition parameters into the initial BP neural network model for ammonia leakage amount prediction to obtain predicted ammonia leakage amounts; constructing a loss function according to the predicted ammonia leakage amounts and the historical ammonia leakage amounts; calculating error terms of neurons in the hidden layer and error terms of neurons in the output layer according to the loss function; updating the initial weights and the initial biases according to the error terms of the neurons in the hidden layer and the error terms of the neurons in the output layer; repeating the iterative updating process of the weights and the biases until the loss function is less than a preset threshold or the number of iterations reaches a preset number, and outputting the final updated weights and biases; and constructing the preset ammonia leakage amount prediction model according to the final updated weights and biases.

[0104] In a specific application scenario, the determination unit 34 comprises an acquisition module 341, a second determination module 342 and a subtraction module 343.

[0105] The acquisition module 341 can be used for acquiring a theoretical urea injection amount.

[0106] The second determination module 342 can be used for determining a urea injection amount corresponding to the ammonia leakage amount.

[0107] The subtraction module 343 can be used for subtracting the urea injection amount corresponding to the ammonia leakage amount from the theoretical urea injection amount to obtain the actual urea injection amount.

[0108] In a specific application scenario, the device further comprises a calculation unit 36.

[0109] The calculation unit 36 can be configured to calculate the amount of ammonia available in the SCR catalyst and the amount of ammonia used for converting nitrogen oxides in the exhaust gas respectively, subtract the amount of ammonia available in the SCR catalyst from the amount of ammonia used for converting nitrogen oxides in the exhaust gas, and obtain the theoretical ammonia leakage amount.

[0110] In a specific application scenario, the acquisition unit 31 can be further configured to acquire a plurality of predicted ammonia leakage amounts in one test cycle of the diesel engine.

[0111] The calculation unit 36 can be further configured to calculate the mean square error of the plurality of predicted ammonia leakage amounts and the corresponding actual ammonia leakage amounts.

[0112] The determination unit 34 can be further configured to determine that the prediction effect of the preset ammonia leakage amount prediction model meets the standard if the mean square error is within a preset range.

[0113] It should be noted that other corresponding descriptions of the various functional modules involved in the ammonia leakage monitoring device provided by the embodiments of the present application can be referred to the corresponding descriptions of the method shown in Figure 1 , which will not be described here in detail.

[0114] Based on the method shown in Figure 1 , correspondingly, the embodiments of the present application also provide a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the following steps: acquiring current working condition parameters of a diesel engine; determining whether ammonia leakage exists in an SCR system according to the urea concentration, the urea pump pressure and the nitrogen oxide concentration downstream of the SCR system in the working condition parameters; if ammonia leakage exists in the SCR system, inputting the working condition parameters into a preset ammonia leakage amount prediction model to predict the ammonia leakage amount, and obtaining the ammonia leakage amount of the SCR system, wherein the preset ammonia leakage amount prediction model represents the mapping relationship between different working condition parameters of the diesel engine and different ammonia leakage amounts; and determining the actual urea injection amount of the diesel engine according to the predicted ammonia leakage amount.

[0115] Based on the method shown in Figure 1 and the device shown in Figure 3 , the embodiments of the present application also provide a physical structure diagram of an electronic device, as shown in Figure 5As shown, the electronic device comprises a processor 41, a memory 42, and a computer program stored on the memory 42 and executable on the processor, wherein the memory 42 and the processor 41 are both arranged on a bus 43, and the processor 41 implements the following steps when executing the program: obtaining current operating condition parameters of a diesel engine; determining whether there is ammonia leakage in the SCR system according to the urea concentration, the urea pump pressure and the nitrogen oxide concentration downstream of the SCR system in the operating condition parameters; if there is ammonia leakage in the SCR system, inputting the operating condition parameters into a preset ammonia leakage amount prediction model to predict the ammonia leakage amount, to obtain the ammonia leakage amount of the SCR system, wherein the preset ammonia leakage amount prediction model represents the mapping relationship between different operating condition parameters of the diesel engine and different ammonia leakage amounts; and determining the actual urea injection amount of the diesel engine according to the predicted ammonia leakage amount.

[0116] By the technical scheme of the embodiment of the present application, not only the problems of high cost and difficult installation of the hardware monitoring device can be solved, but also the ammonia leakage amount can be monitored in real time and accurately, and guidance can be provided for the urea injection control strategy, so as to realize accurate injection.

[0117] 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.

[0118] 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.

[0119] 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 they 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 detecting ammonia leakage, characterized in that, include: Obtain the current operating parameters of the diesel engine; Based on the urea concentration, urea pump pressure, and nitrogen oxide concentration downstream of the SCR system in the operating parameters, determine whether there is ammonia leakage in the SCR system. If the SCR system has an ammonia leak, the operating parameters are input into a preset ammonia leak prediction model to predict the ammonia leak amount, thereby obtaining the ammonia leak amount of the SCR system. The preset ammonia leak prediction model represents the mapping relationship between different operating parameters of the diesel engine and different ammonia leak amounts. Based on the predicted ammonia leakage, the actual urea injection quantity of the diesel engine is determined; The step of determining whether there is ammonia leakage in the SCR system based on the urea concentration, urea pump pressure, and nitrogen oxide concentration downstream of the SCR system in the operating parameters includes: Determine whether the urea concentration in the operating parameters is greater than or equal to the preset urea concentration, and whether the urea pump pressure is greater than or equal to the preset pressure; If the urea concentration is less than the preset urea concentration, or the urea pump pressure is less than the preset pressure, then the diesel engine is subjected to fault detection. If the urea concentration is greater than or equal to the preset urea concentration, and the urea pump pressure is greater than or equal to the preset pressure, then it is determined whether the nitrogen oxide concentration downstream of the SCR system in the operating condition parameters is greater than the preset nitrogen oxide concentration. If the nitrogen oxide concentration is less than or equal to the preset nitrogen oxide concentration, then it is determined that there is no ammonia leakage in the SCR system; If the concentration of nitrogen oxides is greater than the preset concentration of nitrogen oxides, then it is determined that there is an ammonia leak in the SCR system; The preset ammonia leakage prediction model is a three-layer BP neural network model, which includes an input layer, a hidden layer, and an output layer. Each of the input, hidden, and output layers contains multiple neurons. The step of inputting the operating parameters into the preset ammonia leakage prediction model to predict the ammonia leakage and obtain the ammonia leakage of the SCR system includes: The operating parameters are transmitted from the neurons in the input layer to the neurons in the hidden layer. After processing the operating parameters, the neurons in the hidden layer transmit the processing results to the neurons in the output layer for further processing, and finally obtain the ammonia leakage amount output by the output layer.

2. The method according to claim 1, characterized in that, The method further includes: In the event of an ammonia leak in the SCR system, historical operating parameters and historical ammonia leak amounts of the diesel engine are collected. The initial weights and initial biases between each neuron are determined using a preset genetic algorithm, and the initial BP neural network model is determined based on the initial weights and initial biases. The historical operating condition parameters are input into the initial BP neural network model to predict the ammonia leakage amount, and the predicted ammonia leakage amount is obtained. A loss function is constructed based on the predicted ammonia leakage amount and the historical ammonia leakage amount; Based on the loss function, calculate the error terms of neurons in the hidden layer and neurons in the output layer respectively; The initial weights and the initial bias are updated based on the error terms of the neurons in the hidden layer and the error terms of the neurons in the output layer. Repeat the iterative update process of weights and biases until the loss function is less than a preset threshold or the number of iterations reaches a preset number, and then output the final updated weights and biases. Based on the final updated weights and biases, the preset ammonia leakage prediction model is constructed.

3. The method according to claim 1, characterized in that, Determining the actual urea injection quantity of the diesel engine based on the predicted ammonia leakage includes: Obtain the theoretical urea injection volume; Determine the urea injection amount corresponding to the ammonia leakage amount; The actual urea injection amount is obtained by subtracting the theoretical urea injection amount from the urea injection amount corresponding to the ammonia leakage amount.

4. The method according to any one of claims 1-3, further comprising: Calculate the amount of ammonia injected into the SCR catalyst, the amount of ammonia released from the SCR catalyst wall, the actual amount of ammonia reacting with nitrogen oxides, and the amount of ammonia adsorbed on the SCR catalyst wall after the reaction. The theoretical ammonia leakage is calculated based on the amount of ammonia injected into the SCR catalyst, the amount of ammonia released from the SCR catalyst wall, the actual amount of ammonia reacting with nitrogen oxides, and the amount of ammonia adsorbed on the SCR catalyst wall after the reaction.

5. The method according to claim 4, further comprising: Obtain multiple predicted ammonia leakage rates within one test cycle of the diesel engine; Calculate the mean square error between the predicted ammonia leakage amounts and the corresponding actual ammonia leakage amounts; If the mean square error is within the preset range, then the prediction effect of the preset ammonia leakage prediction model is determined to be satisfactory.

6. An ammonia leak monitoring device, characterized in that, include: The acquisition unit is used to acquire the current operating parameters of the diesel engine; The determination unit is used to determine whether there is ammonia leakage in the SCR system based on the urea concentration, urea pump pressure and nitrogen oxide concentration downstream of the SCR system in the operating parameters. The prediction unit is used to input the operating parameters into a preset ammonia leakage prediction model to predict the ammonia leakage if there is ammonia leakage in the SCR system, so as to obtain the ammonia leakage of the SCR system. The preset ammonia leakage prediction model represents the mapping relationship between different operating parameters of the diesel engine and different ammonia leakage. A determining unit is used to determine the actual urea injection quantity of the diesel engine based on the predicted ammonia leakage amount; Specifically, the determination unit is used for: Determine whether the urea concentration in the operating parameters is greater than or equal to the preset urea concentration, and whether the urea pump pressure is greater than or equal to the preset pressure; If the urea concentration is less than the preset urea concentration, or the urea pump pressure is less than the preset pressure, then the diesel engine is subjected to fault detection. If the urea concentration is greater than or equal to the preset urea concentration, and the urea pump pressure is greater than or equal to the preset pressure, then it is determined whether the nitrogen oxide concentration downstream of the SCR system in the operating condition parameters is greater than the preset nitrogen oxide concentration. If the nitrogen oxide concentration is less than or equal to the preset nitrogen oxide concentration, then it is determined that there is no ammonia leakage in the SCR system; If the concentration of nitrogen oxides is greater than the preset concentration of nitrogen oxides, then it is determined that there is an ammonia leak in the SCR system; The preset ammonia leakage prediction model is a three-layer BP neural network model, which includes an input layer, a hidden layer, and an output layer. Each of the input layer, hidden layer, and output layer contains multiple neurons. The prediction unit is specifically used for: The operating parameters are transmitted from the neurons in the input layer to the neurons in the hidden layer. After processing the operating parameters, the neurons in the hidden layer transmit the processing results to the neurons in the output layer for further processing, and finally obtain the ammonia leakage amount output by the output layer.

7. 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 5.

8. 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 5.

Images