Diesel engine gas path system parameter prediction method, device and equipment and storage medium

Abstract

The application discloses a diesel engine gas path system parameter prediction method and device, equipment and a storage medium, and relates to the technical field of diesel engine gas path system modeling research. The diesel engine gas path system parameter prediction method comprises the following steps: acquiring a diesel engine speed, a diesel engine charging efficiency, a cylinder cycle fuel injection amount, a cylinder average exhaust temperature and a compressor outlet air mass flow; establishing a compressor parameter prediction model according to the diesel engine speed, the cylinder average exhaust temperature, the cylinder cycle fuel injection amount and the compressor outlet air mass flow; establishing a intercooler parameter prediction model according to the diesel engine speed, the compressor outlet air mass flow and the compressor parameter prediction model; establishing a cylinder parameter prediction model according to the diesel engine speed, the diesel engine charging efficiency and the intercooler parameter prediction model; and connecting the compressor parameter prediction model, the intercooler parameter prediction model and the cylinder parameter prediction model to obtain a diesel engine gas path system parameter prediction model, so that comprehensive prediction of parameters is realized.

Description

Technical Field

[0001] This application relates to the technical field of diesel engine air circuit system modeling research, specifically to a method, device, equipment and storage medium for predicting parameters of a diesel engine air circuit system. Background Technology

[0002] The combustion state of a diesel engine cylinder is mainly affected by two factors: fuel injection and air intake. Therefore, monitoring and evaluating key parameters of the air intake system is essential. However, most engine models lack sensors for monitoring air intake performance parameters such as temperature and pressure at the turbocharger and intercooler outlets, making timely assessment of the system's condition difficult. This results in early detection of pressure and temperature anomalies in the air intake system. Prolonged abnormalities in temperature and pressure can lead to changes in intake volume, potentially worsening combustion and even causing significant fluctuations in engine speed. The development of computer simulation technology has made it possible to monitor the diesel engine air intake system by establishing parameter prediction models. The emergence of data-driven algorithms such as neural networks will also reduce the difficulty of detailed mechanism modeling and avoid the common problem of missing parameters for certain components in mechanism modeling.

[0003] Patent CN116976026A describes a digital twin method for aero-engine exhaust temperature. It designs a prediction method for aero-engine exhaust temperature, combining correlation analysis between aero-engine characteristic parameters and target parameters, and adaptively corrects the exhaust temperature model using time-series and periodic data. This allows for tracking exhaust temperature based on the current state of the aero-engine, reflecting performance changes. However, the method and process described in this patent are not applicable to the modeling of diesel engine gas path systems. Furthermore, previous data on diesel engine intercooler modeling almost exclusively rely on mechanistic modeling methods or model the intercooler in commercial software. Therefore, existing parametric modeling methods suffer from incomplete modeling data and inaccurate parameter predictions. Summary of the Invention

[0004] Purpose of the invention: The embodiments of this application provide a method for predicting parameters of a diesel engine air circuit system, aiming to overcome the technical problems of incomplete modeling and inaccurate prediction of parameters in the prior art for diesel engine air circuit systems; another purpose of the embodiments of this application is to provide a device for predicting parameters of a diesel engine air circuit system; a third purpose of this application is to provide an electronic device; and a fourth purpose of this application is to provide a computer-readable storage medium.

[0005] Technical Solution: This application describes a method for predicting parameters of a diesel engine air circuit system. This method is applied to a diesel engine air circuit system, which includes at least a diesel engine, a compressor, an intercooler, and a cylinder. The method includes:

[0006] The system obtains diesel engine speed, diesel engine charging efficiency, cylinder cycle fuel injection quantity, cylinder average exhaust temperature, and compressor outlet air mass flow rate.

[0007] A compressor parameter prediction model is established based on the diesel engine speed, the average cylinder exhaust temperature, the cylinder cycle fuel injection quantity, and the compressor outlet air mass flow rate.

[0008] An intercooler parameter prediction model is established based on the diesel engine speed, the compressor outlet air mass flow rate, and the compressor parameter prediction model.

[0009] A cylinder parameter prediction model is established based on the diesel engine speed, the diesel engine charging efficiency, and the intercooler parameter prediction model.

[0010] According to the preset connection relationship of the diesel engine air circuit system, the compressor parameter prediction model, the intercooler parameter prediction model and the cylinder parameter prediction model are connected to obtain the diesel engine air circuit system parameter prediction model, and the diesel engine air circuit system parameters are predicted according to the diesel engine air circuit system parameter prediction model.

[0011] In some embodiments, the diesel engine air circuit system further includes a turbine;

[0012] The method for establishing a compressor parameter prediction model based on the diesel engine speed, the average cylinder exhaust temperature, the cylinder cycle fuel injection quantity, and the compressor outlet air mass flow rate includes:

[0013] The mass flow rate of air entering the turbine is determined based on the diesel engine speed, the cylinder cycle fuel injection quantity, and the compressor outlet air mass flow rate.

[0014] Based on the diesel engine speed, the average cylinder exhaust temperature, the cylinder cycle fuel injection quantity, and the air mass flow rate entering the turbine, a compressor parameter prediction model is established using a convolutional neural network model.

[0015] In some embodiments, determining the air mass flow rate entering the turbine based on the diesel engine speed, the cylinder cycle fuel injection quantity, and the compressor outlet air mass flow rate includes:

[0016] The mass flow rate of diesel fuel entering the diesel engine air circuit system is calculated based on the cylinder cycle injection quantity and the diesel engine speed.

[0017] The mass flow rate of the air entering the turbine is calculated based on the mass flow rate of the diesel fuel entering the diesel engine air circuit system and the mass flow rate of the air at the compressor outlet.

[0018] In some embodiments, establishing the compressor parameter prediction model based on the diesel engine speed, the average cylinder exhaust temperature, the cylinder cycle fuel injection quantity, and the air mass flow rate entering the turbine, combined with a convolutional neural network model, includes:

[0019] The diesel engine speed, the average cylinder exhaust temperature, the cylinder cycle fuel injection mass, and the air mass flow rate entering the turbine are used as inputs to the convolutional neural network model to train and obtain the compressor parameter prediction model.

[0020] In some embodiments, establishing an intercooler parameter prediction model based on the diesel engine speed, the compressor outlet air mass flow rate, and the compressor parameter prediction model includes:

[0021] The compressor outlet predicted pressure and the compressor outlet predicted temperature are determined based on the compressor parameter prediction model.

[0022] Based on the diesel engine speed, the compressor outlet air mass flow rate, the compressor outlet predicted temperature, and the compressor outlet predicted pressure, a backpropagation neural network model is established to predict the intercooler parameters.

[0023] In some embodiments, establishing the intercooler parameter prediction model based on the diesel engine speed, the compressor outlet air mass flow rate, the compressor outlet predicted temperature, and the compressor outlet predicted pressure, combined with a backpropagation neural network model, includes:

[0024] The diesel engine speed, the compressor outlet air mass flow rate, the compressor outlet predicted temperature, and the compressor outlet predicted pressure are used as inputs to the backpropagation neural network model and normalized.

[0025] Configure the hidden layers, activation functions, and adaptive learning rate of the backpropagation neural network model and train it.

[0026] The output data of the trained backpropagation neural network model is denormalized to obtain the intercooler parameter prediction model.

[0027] In some embodiments, the adaptive learning rate is calculated using the following formula:

[0028]

[0029] Where γ is the learning rate of the BP neural network, γ0 is the initial learning rate of the BP neural network, and e k Let e ​​be the output error of the BP neural network at time k. k+1 The output error of the BP neural network at time k+1 is given.

[0030] In some embodiments, establishing a cylinder parameter prediction model based on the diesel engine speed, the diesel engine charging efficiency, and the intercooler parameter prediction model includes:

[0031] The predicted intercooler outlet pressure and the predicted intercooler outlet temperature are determined based on the intercooler parameter prediction model.

[0032] The cylinder parameter prediction model is established based on the diesel engine speed, the diesel engine charging efficiency, the intercooler outlet predicted pressure, the intercooler outlet predicted temperature, and the preset diesel engine displacement and air constant.

[0033] In some embodiments, obtaining the diesel engine charging efficiency, cylinder average exhaust temperature, and compressor outlet air mass flow rate includes:

[0034] Based on the diesel engine speed and the cylinder cycle injection quantity, and using a preset diesel engine simulation model, the diesel engine charging efficiency, the cylinder average exhaust temperature, and the compressor outlet mass flow rate are determined respectively.

[0035] In some embodiments, determining the diesel engine charging efficiency based on a preset diesel engine simulation model, according to the diesel engine speed and the cylinder cycle injection quantity, includes:

[0036] The diesel engine speed and the cylinder cycle fuel injection quantity are input into the preset diesel engine simulation model to obtain the diesel engine cylinder charging efficiency.

[0037] Based on the diesel engine speed and the diesel engine cylinder charging efficiency, a model of the diesel engine charging efficiency is established using a polynomial fitting method.

[0038] Accordingly, the diesel engine air circuit system parameter prediction device described in this application embodiment is applied to a diesel engine air circuit system, which includes at least: a diesel engine, a compressor, an intercooler, and a cylinder; the device includes:

[0039] The acquisition module is used to acquire diesel engine speed, diesel engine charging efficiency, cylinder cycle fuel injection quantity, cylinder average exhaust temperature, and compressor outlet air mass flow rate.

[0040] The compressor parameter prediction model establishment module is used to establish a compressor parameter prediction model based on the diesel engine speed, the cylinder average exhaust temperature, the cylinder cycle fuel injection quantity, and the compressor outlet air mass flow rate.

[0041] The intercooler parameter prediction model establishment module is used to establish an intercooler parameter prediction model based on the diesel engine speed, the compressor outlet air mass flow rate, and the compressor parameter prediction model.

[0042] The cylinder parameter prediction model establishment module is used to establish a cylinder parameter prediction model based on the diesel engine speed, the diesel engine charging efficiency, and the intercooler parameter prediction model.

[0043] The model connection module is used to connect the compressor parameter prediction model, the intercooler parameter prediction model and the cylinder parameter prediction model according to the preset diesel engine air circuit system connection relationship to obtain the diesel engine air circuit system parameter prediction model.

[0044] The prediction module is used to predict the parameters of the diesel engine air circuit system based on the diesel engine air circuit system parameter prediction model.

[0045] Accordingly, an electronic device described in this application includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-mentioned diesel engine air circuit system parameter prediction method.

[0046] Accordingly, the computer-readable storage medium described in the embodiments of this application stores a computer program thereon, which, when executed by a processor, implements the above-described method for predicting parameters of a diesel engine air circuit system.

[0047] Beneficial Effects: Compared with the prior art, the diesel engine air circuit system parameter prediction method, apparatus, equipment, and storage medium of this application embodiment include: acquiring diesel engine speed, diesel engine charging efficiency, cylinder cycle fuel injection quantity, cylinder average exhaust temperature, and compressor outlet air mass flow rate; establishing a compressor parameter prediction model based on diesel engine speed, cylinder average exhaust temperature, cylinder cycle fuel injection quantity, and compressor outlet air mass flow rate; establishing an intercooler parameter prediction model based on diesel engine speed, compressor outlet air mass flow rate, and compressor parameter prediction model; establishing a cylinder parameter prediction model based on diesel engine speed, diesel engine charging efficiency, and intercooler parameter prediction model; connecting the compressor parameter prediction model, intercooler parameter prediction model, and cylinder parameter prediction model according to a preset diesel engine air circuit system connection relationship to obtain a diesel engine air circuit system parameter prediction model, and predicting the diesel engine air circuit system parameters based on the diesel engine air circuit system parameter prediction model. Therefore, this method enables the prediction of compressor, intercooler, and cylinder parameters in a diesel engine's air circuit system, achieving comprehensive parameter prediction and thus improving the accuracy and reliability of parameter prediction. This addresses the technical problems of incomplete parameter modeling and inaccurate parameter prediction in existing technologies. Furthermore, because it allows for the prediction of parameters of key components in the diesel engine's air circuit system, such as the compressor, intercooler, and cylinder, it can reduce the cost of parameter monitoring devices in the diesel engine's air circuit system and improve the effectiveness of diesel engine operating status monitoring. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is a flowchart of a diesel engine air circuit system parameter prediction method provided in the embodiments of this application;

[0050] Figure 2 This is a flowchart of another diesel engine air circuit system parameter prediction method provided in the embodiments of this application;

[0051] Figure 3 This is a schematic diagram of the simulation model of the diesel engine air circuit system parameter prediction model provided in the embodiments of this application in MATLAB / SIMILINK software;

[0052] Figure 4 This is a schematic diagram of the actual collected diesel engine speed provided in the embodiments of this application;

[0053] Figure 5 This is a schematic diagram of the actual collected cylinder cycle fuel injection quantity provided in the embodiments of this application;

[0054] Figure 6 This is a schematic diagram of the actual average exhaust temperature collected in the embodiments of this application;

[0055] Figure 7 This is a schematic diagram of the actual collected compressor air mass flow rate provided in the embodiments of this application;

[0056] Figure 8 This is a schematic diagram comparing the actual value and the predicted value of the compressor outlet pressure provided in the embodiments of this application;

[0057] Figure 9 This is a schematic diagram illustrating the compressor outlet pressure prediction accuracy provided in the embodiments of this application;

[0058] Figure 10 This is a schematic diagram comparing the actual and predicted values ​​of the compressor outlet temperature provided in the embodiments of this application;

[0059] Figure 11 This is a schematic diagram illustrating the compressor outlet temperature prediction accuracy provided in the embodiments of this application;

[0060] Figure 12 This is a schematic diagram comparing the actual and predicted values ​​of the intercooler outlet pressure provided in the embodiments of this application;

[0061] Figure 13 This is a schematic diagram illustrating the intercooler outlet pressure prediction accuracy provided in the embodiments of this application;

[0062] Figure 14 This is a schematic diagram comparing the actual and predicted values ​​of the intercooler outlet temperature provided in the embodiments of this application;

[0063] Figure 15 This is a schematic diagram illustrating the accuracy of intercooler outlet temperature prediction provided in the embodiments of this application;

[0064] Figure 16 This is a schematic diagram comparing the actual value and the predicted value of the total cylinder intake mass flow rate provided in the embodiments of this application;

[0065] Figure 17 This is a schematic diagram illustrating the prediction accuracy of the total cylinder intake mass flow rate provided in the embodiments of this application;

[0066] Figure 18 This is a schematic diagram of the principle structure of a diesel engine air circuit system parameter prediction device provided in the embodiments of this application;

[0067] Figure 19 This is a structural diagram of the electronic device provided in the embodiments of this application.

[0068] Figure label:

[0069] 101-Acquisition module; 102-Compressor parameter prediction model establishment module; 103-Intercooler parameter prediction model establishment module; 104-Cylinder parameter prediction model establishment module; 105-Model connection module; 106-Prediction module; 100-Diesel engine air circuit system parameter prediction device. Detailed Implementation

[0070] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0071] It should be understood that although the terms first, second, etc., may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one component from another. Therefore, the first component discussed below may be referred to as the second component without departing from the teachings of this application. As used herein, the term "and / or" includes all combinations of any and more of the associated listed items.

[0072] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of exemplary embodiments and may not be to scale. The modules or processes shown in the drawings are not necessarily essential for implementing this application and therefore should not be used to limit the scope of protection of this application.

[0073] Figure 1 This is a flowchart illustrating a method for predicting parameters of a diesel engine air circuit system, as provided in an embodiment of this application. This application provides a method for predicting parameters of a diesel engine air circuit system, applicable to the process of comprehensively predicting the parameters of the diesel engine air circuit system. This method can be executed by a diesel engine air circuit system parameter prediction device, which can be implemented in software and / or hardware, and can be configured in the processor of the diesel engine air circuit system. Please refer to... Figure 1 The method includes the following steps:

[0074] Step 110: Obtain the diesel engine speed, diesel engine charging efficiency, cylinder cycle fuel injection quantity, cylinder average exhaust temperature, and compressor outlet air mass flow rate.

[0075] The range of diesel engine speed and cylinder cycle fuel injection quantity can be set according to actual conditions, and no specific limitation is made here.

[0076] Among them, the diesel engine charging efficiency, cylinder average exhaust temperature, and compressor outlet air mass flow rate can be obtained by combining the diesel engine speed and cylinder cycle fuel injection quantity with the diesel engine simulation model.

[0077] The diesel engine simulation model can be created using GT-Power software, and the specific settings can be adjusted according to the actual situation. No specific limitations are made here.

[0078] Step 120: Establish a compressor parameter prediction model based on diesel engine speed, average cylinder exhaust temperature, cylinder cycle fuel injection quantity, and compressor outlet air mass flow rate.

[0079] Among them, the compressor parameter prediction model can predict the compressor's outlet temperature and outlet pressure.

[0080] Specifically, a compressor parameter prediction model can be established using diesel engine speed, average cylinder exhaust temperature, cylinder cycle fuel injection quantity, and compressor outlet air mass flow rate. On the one hand, it can predict the compressor parameters; on the other hand, it can provide support for the establishment of a subsequent intercooler parameter prediction model, thereby enabling the prediction of intercooler parameters.

[0081] Step 130: Establish an intercooler parameter prediction model based on diesel engine speed, compressor outlet air mass flow rate, and compressor parameter prediction model.

[0082] Among them, the intercooler parameter prediction model can predict the outlet pressure and outlet temperature of the intercooler.

[0083] Specifically, an intercooler parameter prediction model can be established using diesel engine speed, compressor outlet air mass flow rate, and compressor parameter prediction models. On the one hand, this allows for the prediction of intercooler parameters; on the other hand, it provides support for the establishment of subsequent cylinder parameter prediction models, thereby enabling the prediction of cylinder parameters.

[0084] Step 140: Establish a cylinder parameter prediction model based on diesel engine speed, diesel engine charging efficiency, and intercooler parameter prediction model.

[0085] Among them, the cylinder parameter prediction model can predict the total intake mass flow rate of the cylinder.

[0086] Step 150: Connect the compressor parameter prediction model, intercooler parameter prediction model and cylinder parameter prediction model according to the preset diesel engine air circuit system connection relationship to obtain the diesel engine air circuit system parameter prediction model, and predict the diesel engine air circuit system parameters according to the diesel engine air circuit system parameter prediction model.

[0087] The pre-defined connection relationship of the diesel engine air circuit system can be determined according to the specific connection relationship of each part of the diesel engine air circuit system structure, and no specific limitation is made here.

[0088] Specifically, after establishing the compressor parameter prediction model, intercooler parameter prediction model, and cylinder parameter prediction model, these models are connected according to the preset diesel engine air circuit system connection relationships. This yields the diesel engine air circuit system parameter prediction model, which enables comprehensive prediction of the parameters of key components such as the compressor, intercooler, and cylinder. This allows for fault analysis and monitoring of these key components, ensuring the safe and reliable operation of the diesel engine air circuit system. Furthermore, the ability to predict the parameters of each key component reduces the installation cost of diesel engine air circuit system sensors and improves the effectiveness of diesel engine operating status monitoring.

[0089] In the technical solution of this embodiment, the working principle of the diesel engine air circuit system parameter prediction method is as follows: (See reference) Figure 1 First, the diesel engine speed, diesel engine charging efficiency, cylinder injection quantity, average cylinder exhaust temperature, and compressor outlet air mass flow rate are obtained. Then, a compressor parameter prediction model is established based on the diesel engine speed, average cylinder exhaust temperature, cylinder injection quantity, and compressor outlet air mass flow rate. Next, an intercooler parameter prediction model is established based on the diesel engine speed, compressor outlet air mass flow rate, and compressor parameter prediction model. A cylinder parameter prediction model is then established based on the diesel engine speed, diesel engine charging efficiency, and intercooler parameter prediction model. Finally, according to the preset diesel engine air circuit system connection relationship, the compressor parameter prediction model, intercooler parameter prediction model, and cylinder parameter prediction model are connected to obtain the diesel engine air circuit system parameter prediction model, and the diesel engine air circuit system parameters are predicted based on this model. Therefore, this method enables comprehensive prediction of parameters for key components in the diesel engine's air circuit system, thereby improving the accuracy and reliability of parameter prediction. This facilitates fault analysis and monitoring of these key components, ensuring the safe and reliable operation of the diesel engine's air circuit system and resolving the technical problems of incomplete parameter modeling and inaccurate parameter prediction in existing technologies. Furthermore, because it allows for the prediction of parameters for each key component, it reduces the cost of parameter monitoring devices such as sensors in the diesel engine's air circuit system and improves the effectiveness of diesel engine operating status monitoring.

[0090] The technical solution of this embodiment provides a method for predicting parameters of a diesel engine's air circuit system. This method includes: acquiring diesel engine speed, diesel engine charging efficiency, cylinder cycle fuel injection quantity, cylinder average exhaust temperature, and compressor outlet air mass flow rate; establishing a compressor parameter prediction model based on the diesel engine speed, cylinder average exhaust temperature, cylinder cycle fuel injection quantity, and compressor outlet air mass flow rate; establishing an intercooler parameter prediction model based on the diesel engine speed, compressor outlet air mass flow rate, and compressor parameter prediction model; establishing a cylinder parameter prediction model based on the diesel engine speed, diesel engine charging efficiency, and intercooler parameter prediction model; connecting the compressor parameter prediction model, intercooler parameter prediction model, and cylinder parameter prediction model according to a preset diesel engine air circuit system connection relationship to obtain a diesel engine air circuit system parameter prediction model; and predicting the parameters of the diesel engine air circuit system based on the diesel engine air circuit system parameter prediction model. Therefore, this method enables the prediction of compressor, intercooler, and cylinder parameters in a diesel engine's air circuit system, achieving comprehensive parameter prediction and thus improving the accuracy and reliability of parameter prediction. This addresses the technical problems of incomplete parameter modeling and inaccurate parameter prediction in existing technologies. Furthermore, because it allows for the prediction of parameters of key components in the diesel engine's air circuit system, such as the compressor, intercooler, and cylinder, it can reduce the cost of parameter monitoring devices in the diesel engine's air circuit system and improve the effectiveness of diesel engine operating status monitoring.

[0091] Figure 2 This is a flowchart of another diesel engine air circuit system parameter prediction method provided in the embodiments of this application. Optionally, based on the above embodiments, please refer to... Figure 2 The method includes the following steps:

[0092] Step 210: Based on the diesel engine speed and cylinder cycle injection quantity, and using a preset diesel engine simulation model, determine the diesel engine charging efficiency, cylinder average exhaust temperature, and compressor outlet mass flow rate.

[0093] The preset diesel engine simulation model can be a calibrated diesel engine simulation model from commercial software. This calibrated diesel engine simulation model can be created using GT-Power software.

[0094] Among them, by using the diesel engine speed and cylinder cycle fuel injection quantity, and based on a preset diesel engine simulation model, the actual values ​​of compressor outlet pressure, compressor outlet temperature, intercooler outlet pressure, intercooler outlet temperature, and cylinder total intake mass flow rate can also be obtained.

[0095] Specifically, the diesel engine speed and cylinder cycle injection quantity range are set according to certain settings or conditions. Then, the diesel engine speed and cylinder cycle injection quantity are used as inputs to the diesel engine simulation model. Under each set of diesel engine speed and cylinder cycle injection quantity settings, the actual values ​​of the cylinder average exhaust temperature, compressor outlet mass flow rate, compressor outlet pressure, compressor outlet temperature, intercooler outlet pressure, intercooler outlet temperature, and total cylinder intake mass flow rate are recorded in the diesel engine simulation model. There are various ways to set the range of diesel engine speed and cylinder cycle injection quantity. As one implementation, optionally, in the diesel engine simulation model, under operating conditions of 100%, 75%, 50%, and 25%, the cylinder cycle injection quantity and diesel engine speed are selected as variables. Within the range of the two variables, the simulation is performed with the diesel engine speed increasing at equal intervals and in a stepwise manner, and the cylinder cycle injection quantity changing back and forth in each speed segment (i.e., the minimum / maximum injection quantity corresponding to each speed segment is the same), and the output data under each group of cylinder cycle injection quantity and diesel engine speed are recorded respectively.

[0096] It should be noted that the selected cylinder cycle injection quantity and diesel engine speed settings for each operating condition should ensure coverage of the torque and power corresponding to the propulsion characteristics of that operating condition, and also cover a certain range of fluctuations in the corresponding torque and power, such as approximately 15%. Therefore, by using a high-precision diesel engine simulation model, the performance parameters of the diesel engine's air circuit system under different operating conditions, influenced by varying cylinder cycle injection quantities, can be obtained. This provides sufficient data for establishing parameter prediction models for subsequent key components. Compared to collecting data from actual engines, this method offers better coverage and density, thereby improving the accuracy of model establishment and, consequently, the accuracy of model predictions.

[0097] For example, the propulsion characteristics that the cylinder cycle fuel injection quantity and diesel engine speed should cover can be: the diesel engine power and speed have a cubic relationship, i.e., P = kn 3 Diesel engine torque and speed have a quadratic relationship, i.e., T = kn. 2 Where P is the power of the diesel engine, T is the torque of the diesel engine, n is the speed of the diesel engine, and k is the propulsion characteristic coefficient.

[0098] As an implementation option, the range of cylinder cycle fuel injection quantity and diesel engine speed settings should cover the torque and power corresponding to the propulsion characteristics of the operating condition, and cover a certain range of fluctuation in the corresponding torque and power, such as 15%. For example, before collecting data for 75% of the operating conditions, various combinations of diesel engine speed and cylinder cycle fuel injection quantity should be tested to determine that the torque and power output by the diesel engine simulation model roughly meet the requirements of covering 60% to 90% of the torque and power, as well as the interval sampling data between the two.

[0099] Step 220: Determine the mass flow rate of air entering the turbine based on the diesel engine speed, cylinder cycle fuel injection quantity, and compressor outlet air mass flow rate.

[0100] As one implementation method, optionally, the air mass flow rate entering the turbine is determined based on the diesel engine speed, the cylinder cycle fuel injection quantity, and the compressor outlet air mass flow rate, including: calculating the diesel mass flow rate entering the diesel engine air circuit system based on the cylinder cycle fuel injection quantity and the diesel engine speed; and calculating the air mass flow rate entering the turbine based on the diesel mass flow rate entering the diesel engine air circuit system and the compressor outlet air mass flow rate.

[0101] The formula for calculating the mass flow rate of diesel fuel entering the diesel engine's air circuit system is as follows:

[0102] y mass =6×10 -6 un / 120

[0103] Among them, y mass U represents the mass flow rate of diesel fuel entering the diesel engine's air circuit system (kg / s), u represents the circulating fuel injection quantity of each cylinder (mg), and n represents the diesel engine speed (r / min).

[0104] The method for calculating the air mass flow rate entering the turbine based on the diesel mass flow rate entering the diesel engine air circuit system and the air mass flow rate at the compressor outlet can be as follows: the air mass flow rate entering the turbine is obtained by adding the diesel mass flow rate entering the diesel engine air circuit system and the air mass flow rate at the compressor outlet.

[0105] Step 230: Based on the diesel engine speed, average cylinder exhaust temperature, cylinder cycle fuel injection quantity, and air mass flow rate entering the turbine, a compressor parameter prediction model is established using a convolutional neural network model.

[0106] Optionally, based on the diesel engine speed, average cylinder exhaust temperature, cylinder cycle fuel injection quantity, and air mass flow rate entering the turbine, a compressor parameter prediction model is established using a convolutional neural network model. This includes: using the diesel engine speed, average cylinder exhaust temperature, cylinder cycle fuel injection quantity, and air mass flow rate entering the turbine as inputs to the convolutional neural network model, and training it to obtain the compressor parameter prediction model.

[0107] For example, the network structure of a convolutional neural network model (i.e., a CNN neural network model) can be: "input layer - convolutional layer - pooling layer - fully connected layer - output layer".

[0108] Specifically, the diesel mass flow rate entering the diesel engine's air passage system is calculated based on the cylinder cycle injection quantity and diesel engine speed obtained in step 210. Then, the diesel mass flow rate entering the diesel engine's air passage system and the compressor outlet air mass flow rate are added together to calculate the air mass flow rate entering the turbine. Next, using the diesel engine speed, average cylinder exhaust temperature, cylinder cycle injection mass, and air mass flow rate entering the turbine as inputs, a CNN neural network is selected as the identification method and trained to obtain a compressor parameter prediction model. Therefore, combining diesel engine mechanism data with a CNN neural network can improve the accuracy of the compressor parameter prediction model.

[0109] Step 240: Determine the predicted compressor outlet pressure and predicted compressor outlet temperature based on the compressor parameter prediction model.

[0110] Because the compressor parameter prediction model is obtained by combining diesel engine mechanism data with a CNN neural network, the prediction accuracy of the compressor parameter prediction model is relatively high. Therefore, the accuracy of the compressor outlet pressure and temperature prediction obtained from the compressor parameter prediction model is also high, which is beneficial to improving the establishment and accuracy of the subsequent intercooler parameter prediction model.

[0111] Step 250: Based on the diesel engine speed, compressor outlet air mass flow rate, compressor outlet predicted temperature, and compressor outlet predicted pressure, and combined with the backpropagation neural network model, establish an intercooler parameter prediction model.

[0112] Specifically, the diesel engine speed and compressor outlet air mass flow rate obtained in step 210, and the compressor outlet predicted temperature and compressor outlet predicted pressure obtained in step 240 are used as inputs. The backpropagation neural network model (i.e., BP neural network model) is selected as the method to identify the intercooler outlet parameters, and a model characterizing the intercooler outlet temperature and pressure is obtained, namely the intercooler parameter prediction model.

[0113] Optionally, based on diesel engine speed, compressor outlet air mass flow rate, compressor outlet predicted temperature, and compressor outlet predicted pressure, and combined with a backpropagation neural network model, an intercooler parameter prediction model is established. This includes: using diesel engine speed, compressor outlet air mass flow rate, compressor outlet predicted temperature, and compressor outlet predicted pressure as inputs to the backpropagation neural network model and performing normalization processing; setting the hidden layers, activation functions, and adaptive learning rate of the backpropagation neural network model and training it; and performing inverse normalization processing on the output data of the trained backpropagation neural network model to obtain the intercooler parameter prediction model.

[0114] For example, using four variables—diesel engine speed, compressor outlet predicted temperature, compressor outlet predicted pressure, and compressor outlet air mass flow rate—as input, the input data is normalized. A hidden layer containing five neurons is set, and an activation function and adaptive learning rate are set. The output of the trained BP neural network is then denormalized to obtain the intercooler participation prediction model.

[0115] The activation function is set as follows:

[0116] f(x) = (e -2x +1) / (e -2x -1) where f(x) is the activation function.

[0117] The normalization calculation formula is as follows:

[0118]

[0119] The formula for calculating inverse normalization is as follows:

[0120]

[0121] Where x is the actual input data, x max The maximum value corresponding to normalization, x min The minimum value corresponding to normalization. is the normalized input data, is the output data calculated by the BP neural network, is the maximum value of the output data calculated by the BP neural network, is the minimum value of the output data calculated by the BP neural network, and is the output data after denormalization.

[0122] The formula for calculating the adaptive learning rate is as follows:

[0123]

[0124] Where γ is the learning rate of the BP neural network, γ0 is the initial learning rate of the BP neural network, and e k Let e ​​be the output error of the BP neural network at time k.k+1 The output error of the BP neural network at time k+1 is given.

[0125] Step 260: Determine the predicted intercooler outlet pressure and predicted intercooler outlet temperature based on the intercooler parameter prediction model.

[0126] Because the intercooler parameter prediction model is obtained by combining diesel engine mechanism data with a BP neural network, the prediction accuracy of the intercooler parameter prediction model is relatively high. Therefore, the predicted intercooler outlet pressure and temperature obtained from the intercooler parameter prediction model are also highly accurate, which is beneficial to improving the establishment and accuracy of subsequent cylinder parameter prediction models.

[0127] Step 270: Establish a cylinder parameter prediction model based on diesel engine speed, diesel engine charging efficiency, intercooler outlet predicted pressure, intercooler outlet predicted temperature, and preset diesel engine displacement and air constant.

[0128] Among them, the diesel engine charging efficiency can be determined based on a preset diesel engine simulation model by measuring the diesel engine speed and the amount of fuel injected in the cylinder cycle.

[0129] Optionally, based on a preset diesel engine simulation model, the diesel engine charging efficiency is determined according to the diesel engine speed and cylinder cycle injection quantity. This includes: inputting the diesel engine speed and cylinder cycle injection quantity into the preset diesel engine simulation model to obtain the diesel engine cylinder charging efficiency; and establishing a diesel engine charging efficiency model using a polynomial fitting method based on the diesel engine speed and diesel engine cylinder charging efficiency.

[0130] The method for establishing the diesel engine charging efficiency model can be as follows: For example, using the diesel engine speed and total intake mass flow rate data of the diesel engine cylinder recorded in step 210, considering that the charging efficiency has a functional correspondence with the diesel engine speed, a cubic polynomial fitting is used to identify the coefficients of each power from speed 0 to 3, and the diesel engine charging efficiency model is obtained.

[0131] The formula for calculating the diesel engine charging efficiency is as follows:

[0132] y intakeeff =c3n 3 +c2n 2 +c1n+c0

[0133] Among them, y intakeeff Let n be the diesel engine charging efficiency, n be the diesel engine speed (r / min), and c3, c2, c1, and c0 be the coefficients corresponding to the powers of the diesel engine speed in the cubic polynomial.

[0134] The calculation formula for the cylinder parameter prediction model is as follows:

[0135] y air =(nP cooler y intakeeff V) / (120RT cooler )

[0136] Among them, y air Where n is the total intake air mass flow rate of the cylinder (kg / s), n is the diesel engine speed (r / min), and P is the total intake air mass flow rate of the cylinder. cooler T is the predicted outlet pressure (bar) of the intercooler. cooler V represents the predicted outlet temperature of the intercooler, and V is the diesel engine displacement (m³ / s). 3 R is the air constant (kJ / (kg·K)).

[0137] Step 280: Connect the compressor parameter prediction model, intercooler parameter prediction model and cylinder parameter prediction model according to the preset diesel engine air circuit system connection relationship to obtain the diesel engine air circuit system parameter prediction model, and predict the diesel engine air circuit system parameters according to the diesel engine air circuit system parameter prediction model.

[0138] In the technical solution of this embodiment, the working principle of the diesel engine air circuit system parameter prediction method is as follows: (See reference) Figure 2First, based on the diesel engine speed and cylinder cycle injection quantity, and using a pre-set diesel engine simulation model, the diesel engine charging efficiency, cylinder average exhaust temperature, and compressor outlet mass flow rate are determined. Then, based on the diesel engine speed, cylinder cycle injection quantity, and compressor outlet mass flow rate, the air mass flow rate entering the turbine is determined. Next, based on the diesel engine speed, cylinder average exhaust temperature, cylinder cycle injection quantity, and air mass flow rate entering the turbine, a compressor parameter prediction model is established using a convolutional neural network model. The predicted compressor outlet pressure and temperature are determined based on this model. Based on the diesel engine speed, compressor outlet air mass flow rate, predicted compressor outlet temperature, and predicted compressor outlet pressure, an intercooler parameter prediction model is established using a backpropagation neural network model. The predicted intercooler outlet pressure and temperature are determined based on this model. Finally, a cylinder parameter prediction model is established based on the diesel engine speed, diesel engine charging efficiency, intercooler outlet predicted pressure and temperature, and a pre-set diesel engine displacement and air constant. Finally, according to the preset connection relationship of the diesel engine air circuit system, the compressor parameter prediction model, intercooler parameter prediction model, and cylinder parameter prediction model are connected to obtain the diesel engine air circuit system parameter prediction model. The parameters of the diesel engine air circuit system are then predicted based on this model. Therefore, this method enables comprehensive prediction of the parameters of key components in the diesel engine air circuit system, thereby improving the accuracy and reliability of parameter prediction. This facilitates fault analysis and monitoring of the parameters of key components, ensuring the safe and reliable operation of the diesel engine air circuit system and solving the technical problems of incomplete parameter modeling and inaccurate parameter prediction in existing technologies. Furthermore, because it enables prediction of the parameters of each key component, it can reduce the cost of parameter monitoring devices such as sensors in the diesel engine air circuit system and improve the effectiveness of diesel engine operating status monitoring.

[0139] In some embodiments, the prediction accuracy of each prediction model may be simulated and tested. Figure 3 This is a schematic diagram of the simulation model of the diesel engine air circuit system parameter prediction model provided in the embodiments of this application in MATLAB / SIMILINK software. (See also...) Figure 3In MATLAB / SIMILINK software, compressor parameter prediction models, intercooler prediction models, and cylinder prediction models are established, and these models are connected to obtain a simulation test model for the diesel engine air circuit system parameter prediction model. For example, diesel engine speed, average exhaust temperature, compressor air mass flow rate, and cylinder cycle fuel injection quantity are used as inputs to the compressor parameter prediction model. The compressor outlet predicted temperature and pressure, along with the compressor air mass flow rate and diesel engine speed, are used as inputs to the intercooler parameter prediction model. The intercooler outlet predicted temperature and pressure, along with the diesel engine speed and charging efficiency, are used as inputs to the cylinder parameter prediction model. These input-output relationships are then used to connect the prediction models to obtain the diesel engine air circuit system parameter prediction model. The model is then run in the MATLAB / SIMILINK software platform, and the data collected in step 210 is compared to test the accuracy of the diesel engine air circuit system parameter prediction model.

[0140] In some embodiments, exemplary, this application uses a simulation model of a marine four-stroke medium-speed diesel engine with a cylinder bore of 270mm, a stroke of 390mm, and a rated speed of 750r / min for data acquisition and modeling simulation experiments.

[0141] Figure 4 This is a schematic diagram of the actual collected diesel engine speed provided in the embodiments of this application. Figure 5 This is a schematic diagram of the actual collected cylinder cycle fuel injection quantity provided in the embodiments of this application. Figure 6 This is a schematic diagram of the actual average exhaust temperature collected in the embodiments of this application. Figure 7 This is a schematic diagram of the actual collected compressor air mass flow rate provided in this embodiment of the application. For example, firstly, using the aforementioned diesel engine bench test data in GT-Power software, the established diesel engine simulation model is calibrated to ensure the model's accuracy meets requirements. For the calibrated diesel engine simulation model, the cylinder cycle injection quantity and diesel engine speed are set as input variables, ensuring that the torque and power under various operating conditions of the diesel engine are covered in the collected data. The steady-state output of the average exhaust temperature, compressor outlet air mass flow rate, compressor outlet temperature, compressor outlet pressure, intercooler outlet temperature, intercooler outlet pressure, and total intake air mass flow rate of the diesel engine cylinders, calculated by the diesel engine simulation model, are collected. The actual values ​​of the diesel engine speed, cylinder cycle injection quantity, average exhaust temperature, and compressor air mass flow rate of the actual collected diesel engine air circuit system are respectively referred to... Figures 4 to 7 .

[0142] Then, using diesel engine speed, cylinder cycle fuel injection quantity, average exhaust temperature, and compressor outlet air mass flow rate as inputs, a compressor parameter prediction model is established. A CNN neural network is used, and the neural network settings are shown in Table 1, to obtain the compressor parameter prediction model in this example.

[0143] Table 1 CNN Parameter Settings

[0144] Serial Number parameter Value 1 Input layer 5*1*1 2 Convolutional layer 1 The convolutional kernel dimension is 3*1, with 16 convolutional kernels. 3 Pooling layer The convolution kernel has a dimension of 3*1 and a stride of 2. 4 Fully connected layer 384 neurons 5 Output layer 2*1 6 Maximum number of training sessions 1000 7 Optimization Algorithm Adam 8 Initial learning rate 0.001 9 Learning rate decline factor 0.1

[0145] Figure 8 This is a schematic diagram comparing the actual value and the predicted value of the compressor outlet pressure provided in the embodiments of this application. Figure 9 This is a schematic diagram of the compressor outlet pressure prediction accuracy provided in the embodiments of this application. Figure 10 This is a schematic diagram comparing the actual and predicted values ​​of the compressor outlet temperature provided in the embodiments of this application. Figure 11 This is a schematic diagram illustrating the compressor outlet temperature prediction accuracy provided in an embodiment of this application. For example, the predicted compressor outlet pressure and temperature values ​​obtained from the compressor parameter prediction model, as well as the corresponding prediction accuracy measurements, please refer to [link to relevant documentation]. Figures 8 to 11 .

[0146] Secondly, an intercooler parameter prediction model was established using diesel engine speed, compressor outlet predicted temperature, compressor outlet predicted pressure, and compressor outlet air mass flow rate as inputs. Using four variables—diesel engine speed, compressor outlet predicted temperature, compressor outlet predicted pressure, and compressor outlet air mass flow rate—as inputs, the input data was normalized. A hidden layer containing five neurons was set, and an activation function was configured. The output data of the trained BP neural network was then de-normalized to obtain the intercooler parameter prediction model.

[0147] Figure 12 This is a schematic diagram comparing the actual value and the predicted value of the intercooler outlet pressure provided in the embodiments of this application. Figure 13 This is a schematic diagram of the intercooler outlet pressure prediction accuracy provided in the embodiments of this application. Figure 14 This is a schematic diagram comparing the actual and predicted values ​​of the intercooler outlet temperature provided in the embodiments of this application. Figure 15 This is a schematic diagram illustrating the predicted accuracy of the intercooler outlet temperature provided in this embodiment. For example, the predicted intercooler outlet pressure and temperature obtained from the intercooler parameter prediction model, as well as the corresponding prediction accuracy measurements, please refer to [link to relevant documentation]. Figures 12 to 15 .

[0148] Secondly, by using multi-condition data, the diesel engine's charging coefficient is identified. Combined with diesel engine speed, predicted intercooler outlet temperature, and predicted intercooler outlet pressure, a diesel engine cylinder parameter prediction model is established. Using diesel engine speed and total intake air mass flow rate, a polynomial fitting method is employed to calculate the charging efficiency model as a function of engine speed. Using charging efficiency, diesel engine speed, predicted intercooler outlet temperature, and predicted intercooler outlet pressure as inputs, and combining diesel engine displacement and air constant values, a mechanistic method is used to calculate a model characterizing the prediction of diesel engine cylinder parameters.

[0149] Furthermore, using the diesel engine speed and total intake air mass flow rate data recorded in the above steps, considering the functional relationship between charging efficiency and speed, a cubic polynomial fitting is used to identify the coefficients of each power from 0 to 3 of the speed, resulting in the following charging efficiency model:

[0150] y intakeeff =6.2656338×10 -8 n 3 +0.000132n 2 +0.090815n-19.687224

[0151] Among them, y intakeeff The gas charging efficiency of the diesel engine is given by n, and the engine speed (r / min) is given by n.

[0152] Furthermore, using charging efficiency, diesel engine speed, predicted intercooler outlet temperature, and predicted intercooler outlet pressure as inputs, and combining the diesel engine displacement and air constant values, a model characterizing the total intake air mass flow rate of the diesel engine cylinders is calculated using a mechanistic method. For example, the diesel engine displacement is: V = 0.134 m³ / s. 3 The air constant is: R = 0.287 kJ / (kg·K).

[0153] Figure 16 This is a schematic diagram comparing the actual value and the predicted value of the total intake mass flow rate of the cylinder provided in the embodiments of this application. Figure 17 This is a schematic diagram illustrating the prediction accuracy of the total cylinder intake mass flow rate provided in this embodiment. For example, please refer to the predicted value of the total cylinder intake mass flow rate obtained from the cylinder parameter prediction model and the corresponding prediction accuracy measurement. Figure 16 and Figure 17 .

[0154] Finally, according to the connection relationship of the diesel engine air circuit system, the various prediction models established above are connected to obtain the diesel engine air circuit system parameter prediction model. The model is run in the software platform and compared with the data collected in step 210 to test the accuracy of the air circuit system parameter prediction model. For example, diesel engine speed, average exhaust temperature, compressor air mass flow rate, and cyclic fuel injection quantity are used as inputs to the compressor parameter prediction model; compressor outlet predicted temperature, compressor outlet predicted pressure, compressor air mass flow rate, and diesel engine speed are used as inputs to the intercooler parameter prediction model; the intercooler outlet predicted temperature and intercooler outlet predicted temperature and pressure output by the intercooler parameter prediction model, along with diesel engine speed and charging efficiency, should be used as inputs to the cylinder parameter prediction model. The models are connected according to this input-output relationship to obtain the diesel engine air circuit system parameter prediction model. The established model is simulated in MATLAB / SIMILINK software, using some data collected in step 210 to test the accuracy of the diesel engine air circuit system parameter prediction model. The results can be found in [link to MATLAB / SIMILINK software]. Figures 8 to 17 .

[0155] Accordingly, this application also provides a diesel engine air circuit system parameter prediction device. Figure 18 This is a schematic block diagram of a diesel engine air circuit system parameter prediction device provided in an embodiment of this application. Please refer to... Figure 18 The diesel engine air circuit system parameter prediction device 100 includes: an acquisition module 101 for acquiring diesel engine speed, diesel engine charging efficiency, cylinder cycle injection quantity, cylinder average exhaust temperature, and compressor outlet air mass flow rate; a compressor parameter prediction model establishment module 102 for establishing a compressor parameter prediction model based on diesel engine speed, cylinder average exhaust temperature, cylinder cycle injection quantity, and compressor outlet air mass flow rate; and an intercooler parameter prediction model establishment module 103 for establishing a compressor parameter prediction model based on diesel engine speed, compressor outlet air mass flow rate, and compressor parameters. The prediction model establishes an intercooler parameter prediction model; the cylinder parameter prediction model establishment module 104 is used to establish a cylinder parameter prediction model based on the diesel engine speed, diesel engine charging efficiency, and the intercooler parameter prediction model; the model connection module 105 is used to connect the compressor parameter prediction model, the intercooler parameter prediction model, and the cylinder parameter prediction model according to the preset diesel engine air circuit system connection relationship to obtain the diesel engine air circuit system parameter prediction model; the prediction module 106 is used to predict the diesel engine air circuit system parameters based on the diesel engine air circuit system parameter prediction model.

[0156] The technical solution of this embodiment provides a diesel engine air circuit system parameter prediction device, which includes: an acquisition module for acquiring diesel engine speed, diesel engine charging efficiency, cylinder cycle fuel injection quantity, cylinder average exhaust temperature, and compressor outlet air mass flow rate; a compressor parameter prediction model establishment module for establishing a compressor parameter prediction model based on diesel engine speed, cylinder average exhaust temperature, cylinder cycle fuel injection quantity, and compressor outlet air mass flow rate; and an intercooler parameter prediction model establishment module for establishing a compressor parameter prediction model based on diesel engine speed, compressor outlet air mass flow rate, and compressor outlet air mass flow rate. The system comprises three modules: an air mass flow rate and compressor parameter prediction model to establish an intercooler parameter prediction model; a cylinder parameter prediction model establishment module to establish a cylinder parameter prediction model based on diesel engine speed, diesel engine charging efficiency, and the intercooler parameter prediction model; a model connection module to connect the compressor, intercooler, and cylinder parameter prediction models according to a preset diesel engine air circuit system connection relationship, resulting in a diesel engine air circuit system parameter prediction model; and a prediction module to predict the parameters of the diesel engine air circuit system based on the prediction model. Therefore, this device can predict the compressor, intercooler, and cylinder parameters in the diesel engine air circuit system, achieving comprehensive parameter prediction, thereby improving the accuracy and reliability of parameter prediction and solving the technical problems of incomplete parameter modeling and inaccurate parameter prediction in existing technologies. Furthermore, because it can predict the parameters of key components in the diesel engine air circuit system such as the compressor, intercooler, and cylinder, it can reduce the cost of parameter monitoring devices in the diesel engine air circuit system and improve the effectiveness of diesel engine operating status monitoring.

[0157] In some embodiments, the compressor parameter prediction model establishment module 102 includes: an air mass flow rate determination unit for entering the turbine, used to determine the air mass flow rate entering the turbine based on the diesel engine speed, cylinder cycle injection quantity, and compressor outlet air mass flow rate; and a compressor parameter prediction model establishment unit, used to establish a compressor parameter prediction model based on the diesel engine speed, cylinder average exhaust temperature, cylinder cycle injection quantity, and air mass flow rate entering the turbine, combined with a convolutional neural network model.

[0158] In some embodiments, the air mass flow rate determination unit for the turbine is further configured to calculate the diesel mass flow rate entering the diesel engine air circuit system based on the cylinder cycle fuel injection quantity and the diesel engine speed; and to calculate the air mass flow rate entering the turbine based on the diesel mass flow rate entering the diesel engine air circuit system and the compressor outlet air mass flow rate.

[0159] In some embodiments, the compressor parameter prediction model building unit is further used to train the compressor parameter prediction model by taking the diesel engine speed, cylinder average exhaust temperature, cylinder cycle fuel injection mass and air mass flow rate entering the turbine as inputs to the convolutional neural network model.

[0160] In some embodiments, the intercooler parameter prediction model establishment module 103 includes: a compressor outlet pressure and temperature determination unit, used to determine the compressor outlet predicted pressure and compressor outlet predicted temperature according to the compressor parameter prediction model; and an intercooler parameter prediction model establishment unit, used to establish an intercooler parameter prediction model based on the diesel engine speed, compressor outlet air mass flow rate, compressor outlet predicted temperature and compressor outlet predicted pressure, combined with a backpropagation neural network model.

[0161] In some embodiments, the intercooler parameter prediction model establishment unit is further configured to take the diesel engine speed, compressor outlet air mass flow rate, compressor outlet predicted temperature, and compressor outlet predicted pressure as inputs to the backpropagation neural network model and perform normalization processing; set the hidden layer, activation function, and adaptive learning rate of the backpropagation neural network model and train it; and perform inverse normalization processing on the output data of the trained backpropagation neural network model to obtain the intercooler parameter prediction model.

[0162] In some embodiments, the adaptive learning rate is calculated using the following formula:

[0163]

[0164] Where γ is the learning rate of the BP neural network, γ0 is the initial learning rate of the BP neural network, and e k Let e ​​be the output error of the BP neural network at time k. k+1 The output error of the BP neural network at time k+1 is given.

[0165] In some embodiments, the cylinder parameter prediction model building module 104 includes: an intercooler outlet predicted pressure and temperature determination unit, used to determine the intercooler outlet predicted pressure and intercooler outlet predicted temperature according to the intercooler parameter prediction model; and a cylinder parameter prediction model building unit, used to build a cylinder parameter prediction model based on the diesel engine speed, diesel engine charging efficiency, intercooler outlet predicted pressure, intercooler outlet predicted temperature, and preset diesel engine displacement and air constant.

[0166] In some embodiments, the acquisition module 101 is further configured to determine the diesel engine charging efficiency, cylinder average exhaust temperature, and compressor outlet mass flow rate based on a preset diesel engine simulation model, according to the diesel engine speed and cylinder cycle injection quantity.

[0167] In some embodiments, the acquisition module 101 is further configured to input the diesel engine speed and cylinder cycle fuel injection quantity into a preset diesel engine simulation model to obtain the diesel engine cylinder charging efficiency; and to establish a diesel engine charging efficiency model using a polynomial fitting method based on the diesel engine speed and diesel engine cylinder charging efficiency.

[0168] Accordingly, this application also provides an electronic device, please refer to... Figure 19 , Figure 19 A structural diagram of an electronic device according to an embodiment of this application is provided. The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the above-described diesel engine air circuit system parameter prediction method. Since the diesel engine air circuit system parameter prediction method has been described in detail above, it will not be repeated here.

[0169] Accordingly, embodiments of this application also provide a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the above-described diesel engine air circuit system parameter prediction method. Since the diesel engine air circuit system parameter prediction method has been described in detail above, it will not be repeated here.

[0170] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0171] The above provides a detailed description of the diesel engine air circuit system parameter prediction method, apparatus, equipment, and storage medium provided in the embodiments of this application, and uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the technical solutions and core ideas of this application; those skilled in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for predicting parameters of a diesel engine's air circuit system, characterized in that, This method is applied to predict parameters of key components in a diesel engine's airflow system, which includes at least: a diesel engine, a compressor, an intercooler, and a cylinder; the key components include the compressor, the intercooler, and the cylinder; the method includes: The system obtains diesel engine speed, diesel engine charging efficiency, cylinder cycle fuel injection quantity, cylinder average exhaust temperature, and compressor outlet air mass flow rate. A compressor parameter prediction model is established based on the diesel engine speed, the average cylinder exhaust temperature, the cylinder cycle fuel injection quantity, and the compressor outlet air mass flow rate. This includes: determining the air mass flow rate entering the turbine based on the diesel engine speed, the cylinder cycle fuel injection quantity, and the compressor outlet air mass flow rate; and training the convolutional neural network model using the diesel engine speed, the average cylinder exhaust temperature, the cylinder cycle fuel injection quantity, and the air mass flow rate entering the turbine as inputs to obtain the compressor parameter prediction model. Establishing an intercooler parameter prediction model based on the diesel engine speed, the compressor outlet air mass flow rate, and the compressor parameter prediction model includes: determining the compressor outlet predicted pressure and the compressor outlet predicted temperature based on the compressor parameter prediction model; using the diesel engine speed, compressor outlet air mass flow rate, compressor outlet predicted temperature, and compressor outlet predicted pressure as inputs to a backpropagation neural network model and performing normalization processing; setting the hidden layers, activation functions, and adaptive learning rate of the backpropagation neural network model and training it; and performing inverse normalization processing on the output data of the trained backpropagation neural network model to obtain the intercooler parameter prediction model. A cylinder parameter prediction model is established based on the diesel engine speed, the diesel engine charging efficiency, and the intercooler parameter prediction model. According to the preset diesel engine air circuit system connection relationship, the compressor parameter prediction model, the intercooler parameter prediction model and the cylinder parameter prediction model are connected to obtain the diesel engine air circuit system parameter prediction model, and the diesel engine air circuit system parameters are predicted according to the diesel engine air circuit system parameter prediction model. The compressor parameter prediction model is used to predict the parameters of the compressor and to provide support for the establishment of the intercooler parameter prediction model, so as to predict the parameters of the intercooler. The intercooler parameter prediction model is used to predict the intercooler parameters and to support the establishment of the cylinder parameter prediction model, so as to predict the cylinder parameters. The cylinder parameter prediction model is used to predict the total intake mass flow rate of the cylinder.

2. The method for predicting parameters of a diesel engine air circuit system according to claim 1, characterized in that, The step of determining the air mass flow rate entering the turbine based on the diesel engine speed, the cylinder cycle fuel injection quantity, and the compressor outlet air mass flow rate includes: The mass flow rate of diesel fuel entering the diesel engine air circuit system is calculated based on the cylinder cycle injection quantity and the diesel engine speed. The mass flow rate of the air entering the turbine is calculated based on the mass flow rate of the diesel fuel entering the diesel engine air circuit system and the mass flow rate of the air at the compressor outlet.

3. The method for predicting parameters of a diesel engine air circuit system according to claim 1, characterized in that, The formula for calculating the adaptive learning rate is: in, The learning rate for the BP neural network. The initial learning rate for the BP neural network. Let k be the output error of the BP neural network at time k. The output error of the BP neural network at time k+1 is given.

4. The method for predicting parameters of a diesel engine air circuit system according to claim 1, characterized in that, The step of establishing a cylinder parameter prediction model based on the diesel engine speed, the diesel engine charging efficiency, and the intercooler parameter prediction model includes: The predicted intercooler outlet pressure and the predicted intercooler outlet temperature are determined based on the intercooler parameter prediction model. The cylinder parameter prediction model is established based on the diesel engine speed, the diesel engine charging efficiency, the intercooler outlet predicted pressure, the intercooler outlet predicted temperature, and the preset diesel engine displacement and air constant.

5. The method for predicting parameters of a diesel engine air circuit system according to claim 1, characterized in that, The acquisition of the diesel engine's charging efficiency, average cylinder exhaust temperature, and compressor outlet air mass flow rate includes: Based on the diesel engine speed and the cylinder cycle injection quantity, and using a preset diesel engine simulation model, the diesel engine charging efficiency, the cylinder average exhaust temperature, and the compressor outlet mass flow rate are determined respectively.

6. The method for predicting parameters of a diesel engine air circuit system according to claim 5, characterized in that, The step of determining the diesel engine charging efficiency based on the diesel engine speed and the cylinder cycle fuel injection quantity, using a preset diesel engine simulation model, includes: The diesel engine speed and the cylinder cycle fuel injection quantity are input into the preset diesel engine simulation model to obtain the diesel engine cylinder charging efficiency. Based on the diesel engine speed and the diesel engine cylinder charging efficiency, a model of the diesel engine charging efficiency is established using a polynomial fitting method.

7. A device for predicting parameters of a diesel engine's air circuit system, characterized in that, This device is used to predict parameters of key components in a diesel engine's airflow system, which includes at least: a diesel engine, a compressor, an intercooler, and a cylinder; the key components include the compressor, the intercooler, and the cylinder; the device includes: The acquisition module is used to acquire diesel engine speed, diesel engine charging efficiency, cylinder cycle fuel injection quantity, cylinder average exhaust temperature, and compressor outlet air mass flow rate. The compressor parameter prediction model establishment module is used to establish a compressor parameter prediction model based on the diesel engine speed, the cylinder average exhaust temperature, the cylinder cycle fuel injection quantity, and the compressor outlet air mass flow rate. The intercooler parameter prediction model establishment module is used to establish an intercooler parameter prediction model based on the diesel engine speed, the compressor outlet air mass flow rate, and the compressor parameter prediction model. The cylinder parameter prediction model establishment module is used to establish a cylinder parameter prediction model based on the diesel engine speed, the diesel engine charging efficiency, and the intercooler parameter prediction model. The model connection module is used to connect the compressor parameter prediction model, the intercooler parameter prediction model and the cylinder parameter prediction model according to the preset diesel engine air circuit system connection relationship to obtain the diesel engine air circuit system parameter prediction model. The prediction module is used to predict the parameters of the diesel engine air circuit system based on the diesel engine air circuit system parameter prediction model. The compressor parameter prediction model is used to predict the parameters of the compressor and to provide support for the establishment of the intercooler parameter prediction model, so as to predict the parameters of the intercooler. The intercooler parameter prediction model is used to predict the intercooler parameters and to support the establishment of the cylinder parameter prediction model, so as to predict the cylinder parameters. The cylinder parameter prediction model is used to predict the total intake mass flow rate of the cylinder. The compressor parameter prediction model building module is also used to: determine the air mass flow rate entering the turbine based on the diesel engine speed, the cylinder cycle injection quantity, and the compressor outlet air mass flow rate; and use the diesel engine speed, the cylinder average exhaust temperature, the cylinder cycle injection quantity, and the air mass flow rate entering the turbine as inputs to a convolutional neural network model to train and obtain the compressor parameter prediction model. The intercooler parameter prediction model establishment module is further configured to: determine the compressor outlet predicted pressure and the compressor outlet predicted temperature based on the compressor parameter prediction model; use the diesel engine speed, the compressor outlet air mass flow rate, the compressor outlet predicted temperature, and the compressor outlet predicted pressure as inputs to the backpropagation neural network model and perform normalization processing; set the hidden layers, activation functions, and adaptive learning rates of the backpropagation neural network model and perform training; and perform inverse normalization processing on the output data of the trained backpropagation neural network model to obtain the intercooler parameter prediction model.

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 processor executes the computer program, it implements the diesel engine air circuit system parameter prediction method according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the diesel engine air circuit system parameter prediction method according to any one of claims 1-6.

Images