A Soft Measurement Method for Exhaust Gas Flow Rate of an Ammonia Engine

Abstract

The present invention relates to a soft measurement method for the exhaust gas flow rate of an ammonia engine, belonging to the technical field of soft measurement of marine engines, and comprising the following steps: acquiring data; selecting auxiliary variables; preprocessing data; analyzing parameter sensitivity; establishing a soft measurement model for the intake gas flow rate of the ammonia engine; training and testing the model; validating the trained soft measurement model for the intake gas flow rate of the ammonia engine using independent test data; and applying the model. The present invention can indirectly obtain the exhaust gas flow rate of the ammonia engine by using the data of other sensor measuring points in the case where a physical flowmeter cannot be used and the carbon balance method cannot be used to calculate the exhaust gas flow rate. By applying the correlation algorithm and the long short-term memory network (LSTM) intelligent algorithm, the present invention analyzes the mapping relationship between the characteristic parameters of the ammonia engine and the intake gas flow rate, establishes a prediction model for the intake gas flow rate of the ammonia engine, and then realizes the indirect monitoring of the exhaust gas flow rate of the ammonia engine that is difficult to directly measure by collecting the fuel consumption in real time.

Description

Technical Field

[0001] The present invention belongs to the technical field of marine engine soft measurement, and in particular relates to a soft measurement method for the exhaust gas flow of an ammonia engine. Background Art

[0002] There are mainly two methods for measuring the exhaust gas flow of an engine: the direct measurement method and the carbon balance method. The direct measurement method directly measures the exhaust gas flow through a flow meter, or calculates the exhaust gas flow by measuring the intake air flow and the fuel flow. The principle of this method is that by controlling and monitoring the intake air volume and fuel volume, the exhaust gas flow can be indirectly calculated through material balance. The carbon balance method calculates the exhaust gas flow by analyzing key parameters such as the concentration of carbon-containing components in the exhaust gas. This method usually requires measuring the concentration of carbon dioxide (CO2) in the exhaust gas, and then deriving the exhaust gas flow based on the carbon source consumption during the combustion process.

[0003] In the application of marine engines, especially low-speed engines, due to the large size of their intake and exhaust pipes and usually limited installation space for flow meters, the direct measurement method is difficult to operate in practice. To overcome these challenges, marine engines generally use the carbon balance method to calculate the exhaust gas flow. By measuring the CO2 concentration and other key emission components in the exhaust gas, the carbon balance method can accurately estimate the exhaust gas flow.

[0004] However, the situation is different for ammonia engines. As a carbon-free fuel, the main components of the exhaust gas of ammonia include nitrogen, water vapor, nitrogen oxides (NOx), and possibly escaping ammonia. This is significantly different from the exhaust gas components of traditional carbon-based fuel (such as diesel, gasoline) engines. Therefore, the carbon balance method cannot be used to calculate the exhaust gas flow of ammonia engines. Because ammonia fuel does not contain carbon elements, the exhaust gas flow cannot be calculated by measuring carbon. This particularity makes the traditional carbon balance method inapplicable to ammonia engines, and there is an urgent need to develop a new exhaust gas flow measurement method suitable for ammonia fuel engines.

[0005] Developing an exhaust gas flow measurement technology suitable for ammonia engines is of great significance for promoting the wide application of ammonia as an alternative fuel. As an environmentally friendly fuel, ammonia has broad application prospects in ships and other fields, but its unique emission characteristics require innovation in the exhaust gas flow measurement method. In the future, how to design a simple, operable and economical exhaust gas flow measurement method for ammonia engines while ensuring measurement accuracy will be a key technical problem in the research of ammonia fuel engines. Summary of the Invention

[0006] The object of the present invention is to provide a soft measurement method for the exhaust gas flow of an ammonia engine for engines that cannot measure the exhaust gas flow of a marine ammonia fuel engine using the direct measurement method and the carbon balance method, so as to measure the exhaust gas flow.

[0007] To achieve the above object, the technical solution of the present invention provides a soft measurement method for the exhaust gas flow of an ammonia engine, which includes the following steps:

[0008] Obtain data: Obtain the emission data, fuel consumption data, and conventional measurement point data of the ammonia engine in diesel mode, and calculate the exhaust gas flow and intake air flow.

[0009] Select auxiliary variables: Select multiple variables that can be measured or extracted as the pre-input variables of the intake air flow prediction model of the ammonia engine.

[0010] Preprocess the data: Eliminate abnormal data, and ensure the consistency of the data scales between different parameters according to the method of numerical interpolation.

[0011] Analyze parameter sensitivity: Analyze the contribution of the auxiliary variables to the predicted value of the intake air flow, and screen several auxiliary variables with the greatest influence as the final model inputs.

[0012] Establish a soft measurement model for the intake air flow of the ammonia engine: Establish a soft measurement model for the intake air flow of the ammonia engine based on the long short-term memory network.

[0013] Train and test the model: Train and test the soft measurement model for the intake air flow of the ammonia engine. Train the model based on the selected auxiliary variables and the intake air flow data of the ammonia engine in diesel mode, and perform parameter tuning; Use independent test data to verify the trained soft measurement model for the intake air flow of the ammonia engine.

[0014] Apply the model: After completing the training and testing of the intake air flow soft measurement model in the diesel mode of the ammonia engine, this soft measurement model can be directly used for predicting the intake air flow in the ammonia mode of the ammonia engine; By collecting the fuel consumption data in real time, adding the predicted intake air flow to the collected fuel consumption is the predicted exhaust gas flow in the ammonia mode.

[0015] Preferably, in the step of obtaining data, the control system of the ammonia engine can be used to collect the data of each measurement point of the engine, or an online monitoring system can be used to obtain the data by communicating with the control system of the ammonia engine and the emission analyzer.

[0016] Preferably, in the step of selecting auxiliary variables, engine characteristic parameters with a high degree of correlation with the intake air flow can be selected as auxiliary variables, including engine speed, torque, supercharger speed, and supercharger outlet temperature.

[0017] Preferably, in the step of preprocessing data, an interpolation function is used to adjust the data obtained at different sampling rates so that they have the same time scale; the formula is as follows:

[0018]

[0019] where interpolate is the interpolation function that estimates the values of new data points between or outside the original data points; x is the original data, which can be time series data; new_rate is the target sampling rate, representing the new time interval to which the original data is resampled.

[0020] Preferably, in the step of analyzing parameter sensitivity, a global sensitivity analysis method is used to evaluate the influence degree of each input parameter on the output result; the formula is as follows:

[0021]

[0022] where Si is the sensitivity index, is the output variance caused by the i-th parameter, is the total output variance.

[0023] Preferably, in the step of establishing a soft measurement model for the intake air flow of an ammonia engine, the long short-term memory network introduces forget gates, input gates, and output gates to control the flow of information. The long short-term memory network includes an input layer, an LSTM layer, and a fully connected output layer; the input layer receives data with a shape of (time step, number of features), where the time step and the number of features are determined by the shape of the normalized training data; the LSTM layer contains 128 units and uses the SELU activation function, and only returns the last output of the sequence; a fully connected layer maps the output of the LSTM layer to a space with the same dimension as the target data to generate a prediction result.

[0024] Preferably, in the step of establishing a soft measurement model for the intake air flow of an ammonia engine, the model uses the mean squared error as the loss function and adopts the Adam optimizer for training; the LSTM unit formula is as follows:

[0025]

[0026] where are the activation vectors of the forget gate, input gate, and output gate respectively, is the cell state, is the candidate cell state, is the input at the current time step, is the hidden state, is the activation function, and are the weight and bias respectively. The subscript t - 1 represents the previous time step, and the subscript t represents the current time step.

[0027] Preferably, in the steps of training and testing the model, the mean square error between the predicted value of the intake air flow calculated by the soft sensor model and the measured value of the intake air flow is used to evaluate the prediction accuracy of the soft sensor model; the formula is as follows:

[0028]

[0029] Wherein, is the actual value, is the predicted value, is the total number of samples.

[0030] Preferably, in the step of applying the model, when the ammonia engine is tested on the bench, the soft sensor model of the intake air flow is built based on the diesel mode; the soft sensor model algorithm is deployed in the engine control system or the online monitoring system. When the ammonia engine switches to the ammonia mode, the three variables with the greatest influence are collected in real time as the input of the soft sensor model to obtain the real-time predicted intake air flow in the ammonia mode; the mean absolute percentage error is used to calculate the error between the predicted value and the true value of the intake air flow; the calculation formula of the mean absolute percentage error is:

[0031]

[0032] Wherein, is the actual value, is the predicted value, is the total number of samples.

[0033] In summary, the present invention includes the following beneficial technical effects:

[0034] The present invention can indirectly obtain the exhaust gas flow of the ammonia engine by using the data of other sensor measuring points when the physical flowmeter cannot be used and the carbon balance method cannot be used to calculate the exhaust gas flow. By applying the correlation algorithm and the long short-term memory network (LSTM) intelligent algorithm, the present invention analyzes the mapping relationship between the characteristic parameters of the ammonia engine and the intake air flow, establishes a prediction model for the intake air flow of the ammonia engine, and then realizes the indirect monitoring of the exhaust gas flow of the ammonia engine that is difficult to directly measure by collecting the fuel consumption in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 is a schematic diagram of the implementation steps of the soft sensor method for the exhaust gas flow of the ammonia engine;

[0036] Figure 2 is a schematic diagram of the principle of the LSTM network;

[0037] Figure 3 is a schematic diagram of the sensitivity analysis result of the parameters affecting the exhaust gas flow of the ammonia engine;

[0038] Figure 4 This is a schematic diagram of the model training error curve;

[0039] Figure 5 Schematic diagram of the exhaust flow prediction results of an ammonia engine. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] The embodiment of the present invention discloses an ammonia engine exhaust flow monitoring method based on soft measurement technology. The method can indirectly obtain the exhaust flow of the ammonia engine by using data from other sensor measurement points when a physical flow meter cannot be used and the carbon balance method cannot be used to calculate the exhaust flow. By using the association algorithm and the long short-term memory network (LSTM) intelligent algorithm, the mapping relationship between the characteristic parameters of the ammonia engine and the intake flow is analyzed, and an ammonia engine intake flow prediction model is established. Then, by collecting fuel consumption in real time, indirect monitoring of the exhaust flow of the ammonia engine that is difficult to measure directly can be achieved. Its characteristic is that the method determines the mapping relationship between the characteristic parameters of the ammonia engine and the intake flow through the following steps:

[0042] 1) Data acquisition: The emission data, fuel consumption data and conventional measurement point data of the ammonia engine in diesel mode are obtained by bench testing, and the exhaust flow rate of the ammonia engine in diesel mode is calculated by the carbon balance method; the intake flow rate of the ammonia engine is equal to the exhaust flow rate minus the fuel consumption.

[0043] 2) Auxiliary variable selection: Select appropriate variables as pre-input variables for the ammonia engine intake flow prediction model. The auxiliary variables must be measurable or extractable, and the auxiliary variables should be as independent as possible to reduce redundancy.

[0044] 3) Data preprocessing: Data preprocessing mainly includes two aspects: one is to eliminate abnormal data, and the other is to ensure the consistency of data scales between different parameters based on numerical interpolation methods.

[0045] 4) Parameter sensitivity analysis: Global sensitivity analysis is used to calculate the contribution of each auxiliary variable to the intake flow prediction value, and the three variables with the greatest influence are selected as the final model input.

[0046] 5) Soft measurement model of ammonia engine intake flow: A soft measurement model of ammonia engine intake flow is established based on long short-term memory network (LSTM).

[0047] 6) Model training and testing: Train and test the soft sensor model for the intake air flow of the ammonia engine. Train the model based on the selected parameters and the intake air flow data in the diesel mode of the ammonia engine, and optimize the parameters. Use independent test data to verify the prediction effect of the trained soft sensor model for the intake air flow of the ammonia engine, specifically including using the mean square error to evaluate the prediction accuracy and reliability.

[0048] 7) Application of the model: After completing the training and testing of the soft sensor model for the intake air flow in the diesel mode of the ammonia engine, this soft sensor model can be directly used for predicting the intake air flow in the ammonia mode of the ammonia engine. By collecting the fuel consumption (diesel, ammonia) data in real time, adding the predicted intake air flow to the collected fuel consumption gives the predicted exhaust gas flow in the ammonia mode.

[0049] The following elaborates on each step in detail:

[0050] 1) Data acquisition: In bench testing, the engine control system of the ammonia engine can be used to collect data at each measurement point of the engine; or an online monitoring system can be used to obtain data by communicating with the engine control system and the emission analyzer of the ammonia engine.

[0051] 2) Selection of auxiliary variables: Engine characteristic parameters with a relatively high correlation with the intake air flow can be selected as auxiliary variables, such as engine speed, torque, turbocharger speed, turbocharger outlet temperature, etc.

[0052] 3) Data preprocessing: Use an interpolation function to adjust the data with different sampling rates obtained to have the same time scale. The formula is as follows:

[0053]

[0054] where interpolate is the interpolation function, which is used to estimate the values of new data points between or outside the original data points. x is the original data, which can be time series data, such as sensor readings, and it is collected at a certain time interval (the original sampling rate). new_rate is the target sampling rate, indicating the new time interval to which the original data is resampled.

[0055] 4) Parameter sensitivity analysis: Adopt a global sensitivity analysis method to evaluate the influence degree of each input parameter on the output result. The formula is as follows:

[0056]

[0057] where Si is the sensitivity index, is the output variance caused by the i-th parameter, is the total output variance.

[0058] 5) Soft sensor model for ammonia engine intake air flow: A soft sensor model for ammonia engine intake air flow is established based on the Long Short-Term Memory network (LSTM). LSTM is a special type of Recurrent Neural Network (RNN) used to process and predict long-term dependencies in time series data. Different from traditional RNNs, LSTM introduces three gating mechanisms (forget gate, input gate, and output gate) to control the flow of information. The main working principle of LSTM is as Figure 2 shown, consisting of an input layer, an LSTM layer, and a fully connected output layer. The input layer accepts data with a shape of (time steps, number of features), where the time steps and the number of features are determined by the shape of the normalized training data. The LSTM layer contains 128 units and uses the SELU activation function, which only returns the last output of the sequence. Finally, a fully connected layer maps the output of the LSTM layer to a space with the same dimension as the target data to generate the prediction result. The model uses the Mean Squared Error (MSE) as the loss function and is trained using the Adam optimizer.

[0059] The LSTM cell formula is as follows:

[0060]

[0061] where are the activation vectors of the forget gate, input gate, and output gate respectively, is the cell state, is the candidate cell state, is the input at the current time step, is the hidden state, is the activation function, and are the weights and biases respectively. The subscript t - 1 represents the previous time step, and the subscript t represents the current time step.

[0062] 6) Model training and testing: The Mean Squared Error (MSE) between the predicted intake air flow value calculated using the soft sensor model and the intake air flow test value (the calculated exhaust flow value based on the carbon balance method) is used to evaluate the prediction accuracy of the soft sensor model. The formula is as follows:

[0063]

[0064] where, is the actual value, is the predicted value, is the total number of samples.

[0065] 7) Application of the model: When the ammonia engine is under bench test, a soft sensor model for intake air flow is built based on the diesel mode. The soft sensor model algorithm is deployed in the engine control system or the online monitoring system. When the ammonia engine switches to the ammonia mode, by collecting the three variables with the greatest impact in real time as the input of the soft sensor model, the real-time predicted intake air flow under the ammonia mode can be obtained. By collecting the data of fuel consumption (diesel, ammonia) in real time, adding the predicted intake air flow and the collected fuel consumption gives the predicted exhaust gas flow under the ammonia mode. The mean absolute percentage error (MAPE) is used to calculate the error between the predicted value and the true value of the intake air flow. The calculation formula for the mean absolute percentage error is:

[0066]

[0067] where is the actual value, is the predicted value, is the total number of samples.

[0068] Application example:

[0069] To verify the soft sensor effect of the correlation algorithm and the long short-term memory network on the engine exhaust gas flow, due to the lack of ammonia engine test data and the general applicability of the present invention to the prediction of engine exhaust gas flow, the test data collected by the control system of a spark-ignition compressed natural gas high-speed engine is used as the research object, and some auxiliary variables are selected, such as: speed (SPEED), torque (TORQUE), turbine inlet temperature (T_TRB_I), turbine outlet temperature (T_TRB_O), turbine inlet pressure (P_TRB-I), intercooler inlet pressure (P_IC_I), intercooler outlet pressure (P_IC_O), intercooler inlet temperature (T_IC_I), intercooler outlet temperature (T_IC_O), etc. to predict the engine exhaust gas flow.

[0070] During the same sampling time for the auxiliary variables, due to different sampling frequencies, the number of data points for different auxiliary variables is not consistent. Therefore, the data resampling method is used to make the number of data points consistent. For example, taking the number of data points 25520 of the intercooler inlet pressure within the same sampling time as the benchmark, the remaining parameters are resampled so that the number of data points of other parameters remains 25520.

[0071] The sensitivity of the exhaust gas flow to different auxiliary variables is analyzed, and the analysis results are as follows:

[0072] The three parameters that have the greatest impact on the exhaust gas flow rate are: the inlet pressure of the intercooler (P_IC_I), the inlet pressure of the turbine (P_TRB-I), and the outlet pressure of the intercooler (P_IC_O). The sensitivity indices are 0.79, 0.12, and 0.09 respectively (the sensitivity index ranges from 0 to 1, and the closer it is to 1, the greater the impact of the parameter). The results are as Figure 3 shown.

[0073] After the parameter sensitivity analysis is completed, the three auxiliary variables with the greatest impact (P_IC_I, P_TRB-I, P_IC_O) are used as the input parameters of the LSTM model. The acquired test data is divided into a training set and a test set, with a ratio of 6:4. The number of data points in the training set is 15312, and the number of data points in the test set is 10208. The loss function curve of the LTSM model training is as Figure 4 shown, and the order of magnitude of the training error reaches , and it has converged, indicating that the model has reached stability.

[0074] The model loss curve has converged. The trained LTSM model is used for exhaust gas flow rate prediction. The prediction results are as Figure 5 shown. The trend of the true value and the prediction value is the same, and the mean absolute percentage error is 2.79%. Figure 5 It shows that using the LTSM model to predict the engine exhaust gas flow rate has a good effect.

[0075] This application relates to the exhaust gas flow rate measurement technology of marine ammonia fuel engines, belonging to the field of soft measurement technology for marine engines. The present invention provides a method for measuring the exhaust gas flow rate of an engine based on soft measurement technology. By applying the correlation algorithm and the long short-term memory network (LSTM) intelligent algorithm, the mapping relationship between the engine characteristic parameters and the exhaust gas flow rate is analyzed, and an engine exhaust gas flow rate prediction model is established to realize the indirect monitoring of the exhaust gas flow rate of the ammonia engine that is difficult to directly measure.

[0076] To verify the implementation effect of this method, based on the test data of a natural gas high-speed engine ignited by a spark plug obtained, the engine characteristic parameters are dimensionally reduced through simulation means, the structure of the exhaust gas flow rate prediction model is optimized, and the accuracy, real-time performance, and generalization ability of the prediction model are improved. Comparing the model prediction value with the test value, the exhaust gas flow rate prediction effect is good, and the mean absolute percentage error of the exhaust gas flow rate prediction ≤ 3%. The verification results show that the method provided by the present invention is applicable to the prediction of the engine exhaust gas flow rate. The present invention has general applicability to various types of engines. Especially when the engine uses carbon-free fuels such as ammonia and hydrogen, the present invention can be used to predict the intake air flow rate through the soft measurement method, and then by real-time collecting the fuel consumption, the exhaust gas flow rate can be obtained. The present invention provides a solution for the exhaust gas flow rate measurement of zero-carbon engines.

[0077] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A soft measurement method for exhaust flow of an ammonia engine, characterized in that: The following steps are involved: Data acquisition: Acquire emission data, fuel consumption data and conventional measurement point data of the ammonia engine in diesel mode, and calculate exhaust flow and intake flow; Select auxiliary variables: select multiple variables that can be measured or extracted as pre-input variables of the ammonia engine intake flow prediction model, and the selected variables are a parameter combination of engine speed, torque, supercharger speed, turbine inlet temperature, turbine outlet temperature, turbine inlet pressure, intercooler inlet pressure, intercooler outlet pressure, intercooler inlet temperature, and intercooler outlet temperature; Preprocess data: remove abnormal data and use numerical interpolation to ensure that the data scales between different parameters are consistent; Analyze parameter sensitivity: Use global sensitivity to analyze the contribution of auxiliary variables to the intake flow prediction value, and select several auxiliary variables with the greatest impact as the final model input; Establish a soft-sensing model for the intake air flow of an ammonia engine: Establish a soft-sensing model for the intake air flow of an ammonia engine based on a long short-term memory network; Training and testing models: Train and test the soft measurement model of intake air flow of ammonia engines. The model is trained based on the screened auxiliary variables and intake air flow data of ammonia engines in diesel mode, and parameters are tuned. Use independent test data to validate the trained ammonia engine intake air flow soft-sensing model; Application model: After completing the training and testing of the intake flow soft measurement model in the diesel mode of an ammonia engine, the soft measurement model can be directly used to predict the intake flow in the ammonia mode of an ammonia engine; By collecting fuel consumption data in real time, the predicted intake flow rate and the collected fuel consumption are added to obtain the predicted exhaust flow rate under the ammonia mode.

2. The soft measurement method of exhaust flow of an ammonia engine according to claim 1 is characterized in that: In the data acquisition step, the ammonia engine control system is used to collect data from various measuring points of the engine, or an online monitoring system is used to acquire data by communicating with the ammonia engine control system and the emission analyzer.

3. The soft measurement method of exhaust flow of an ammonia engine according to claim 1, characterized in that: In the data preprocessing step, the interpolation function is used to adjust the data obtained at different sampling rates to have the same time scale; the formula is as follows: Where interpolate is an interpolation function that estimates the value of new data points between or outside the original data points; x is the original data, which can be time series data; new_rate is the target sampling rate, which represents the new time interval to which the original data is resampled.

4. The soft measurement method of exhaust flow of an ammonia engine according to claim 1, characterized in that: In the step of analyzing parameter sensitivity, a global sensitivity analysis method is used to evaluate the influence of each input parameter on the output result; the formula is as follows: Where Si is the sensitivity index, is the output variance caused by the i-th parameter, is the total output variance.

5. The soft measurement method of exhaust flow of an ammonia engine according to claim 1, characterized in that: In the steps of establishing the soft-sensing model of the intake flow of an ammonia engine, the long short-term memory network introduces a forget gate, an input gate, and an output gate to control the flow of information. The long short-term memory network includes an input layer, an LSTM layer, and a fully connected output layer; the input layer accepts a shape of a specified time step and number of features, where the time step and number of features are determined by the shape of the normalized training data; the LSTM layer contains 128 units and uses the SELU activation function, returning only the last output of the sequence; a fully connected layer maps the output of the LSTM layer to a space of the same dimension as the target data to produce a prediction result.

6. The soft measurement method of exhaust flow of an ammonia engine according to claim 5, characterized in that: In the step of establishing the soft-sensing model of the intake flow of the ammonia engine, the model uses the mean square error as the loss function and uses the Adam optimizer for training; the LSTM unit formula is as follows: in are the activation vectors of the forget gate, input gate, and output gate, respectively. is the cell state, is the candidate cell state, is the input of the current time step, is the hidden state, is the activation function, and are weight and bias respectively, the subscript t-1 represents the previous time step, and the subscript t represents the current time step.

7. The soft measurement method of exhaust flow of an ammonia engine according to claim 1, characterized in that: In the training and testing model steps, the mean square error between the intake flow prediction value calculated by the soft measurement model and the intake flow test value is used to evaluate the accuracy of the soft measurement model prediction; the formula is as follows: in, is the actual value, is the predicted value, is the total number of samples.

8. The soft measurement method of exhaust flow of an ammonia engine according to claim 1, characterized in that: In the application model step, when the ammonia engine is tested on the bench, the intake flow soft measurement model is built based on the diesel mode; the soft measurement model algorithm is deployed in the engine control system or online monitoring system. When the ammonia engine is switched to the ammonia mode, the three variables with the greatest influence are collected in real time as the input of the soft measurement model to obtain the real-time predicted intake flow under the ammonia mode; the error between the predicted value and the actual value of the intake flow is calculated using the mean absolute percentage error; The mean absolute percentage error is calculated as: in, is the actual value, is the predicted value, is the total number of samples.

Images