Engine fuel real-time mixing method and device
Through the real-time engine fuel mixing method, the physical and chemical properties parameters of the mixed fuel are dynamically adjusted using optimization algorithms, which solves the problem that the existing technology is difficult to achieve low fuel consumption and low pollutant emissions under all operating conditions, and realizes that the engine under different operating conditions Optimized fuel consumption and emissions.
Patent Information
- Application Number
- CN202411487377.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-24
- Publication Date
- 2025-01-17
AI Technical Summary
The prior art is difficult to achieve low fuel consumption and low pollutant emissions under the entire engine operating conditions, and the physical and chemical properties of the mixed fuel are fixed, so the optimal performance cannot be achieved under all operating conditions.
Using the real-time engine fuel mixing method, by collecting historical data and real-time operating condition parameters, the fuel consumption and emission prediction model is trained, and the physical and chemical properties of the mixed fuel is iteratively optimized, and the mixing ratio of the first fuel and the second fuel is dynamically adjusted. Based on Real-time operating conditions optimize fuel consumption and emission forecast values to achieve the preset objective function value.
The fuel consumption and emission data optimization under all operating conditions is achieved, ensuring that the engine has low fuel consumption and low pollutant emissions under different conditions.
Smart Images
Figure CN119321371A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of engine technology, and in particular to a method and device for real-time mixing of engine fuel. Background Art
[0002] As people pay more and more attention to environmental protection, the development of efficient, low-carbon and clean engines has become an inevitable trend. As the number of motor vehicles increases, using renewable green fuels to partially replace traditional fossil fuels is the most direct and effective way to alleviate energy pressure and reduce pollutant emissions without changing the engine structure.
[0003] The mixed application of renewable alternative fuels and traditional fossil fuels or multiple renewable alternative fuels is a feasible technical route at present, such as biodiesel and ethanol gasoline that have been applied to the market. The current performance development of mixed fuels is mainly through engine bench tests and numerical simulation research, exploring the fuel consumption and emission characteristics of mixed fuels, obtaining the fuel mixing ratio with the best comprehensive performance under all engine working conditions, and formulating mixed fuels based on this research result for use in engines.
[0004] In the related art, since the physical and chemical properties of the mixed fuel are fixed values after mixing, it can usually only achieve optimal performance under certain engine operating conditions, and cannot achieve low fuel consumption and low pollutant emissions under all operating conditions. Summary of the invention
[0005] The purpose of this application is to provide a real-time engine fuel mixing method and device, which can achieve low fuel consumption and low pollutant emissions under all operating conditions.
[0006] To achieve the above objectives, this application provides the following solutions:
[0007] In a first aspect, the present application provides a method for real-time mixing of engine fuel, comprising:
[0008] Collecting a historical data set of a mixed fuel engine; the historical data set includes engine operating parameters, mixed fuel physicochemical property parameters, engine fuel consumption and emission data; the mixed fuel physicochemical property parameters are determined according to the physicochemical property parameters of the first fuel and the physicochemical property parameters of the second fuel;
[0009] Determine a training set based on the historical data set;
[0010] The training set is used to train the fuel consumption and emission prediction model to obtain a trained fuel consumption and emission prediction model;
[0011] collecting real-time engine operating parameters of the mixed fuel engine;
[0012] Based on the real-time engine operating parameters, the mixed fuel physical and chemical property parameters of the mixed fuel engine are iteratively optimized by using an optimization algorithm, and the optimized mixed fuel physical and chemical property parameters are output; each time the mixed fuel physical and chemical property parameters of the mixed fuel engine are iteratively optimized, the real-time engine operating parameters and the currently optimized mixed fuel physical and chemical property parameters are input into a trained fuel consumption and emission prediction model, and the engine fuel consumption prediction value and emission data prediction value are output, and the objective function value of the optimization algorithm is calculated according to the fuel consumption prediction value and the emission data prediction value. When the objective function value reaches the preset requirement, the optimized mixed fuel physical and chemical property parameters are output;
[0013] The mixing ratio of the first fuel and the second fuel is determined according to the optimized physical and chemical property parameters of the mixed fuel.
[0014] Optionally, the physical and chemical property parameters of the mixed fuel include density, lower heating value, kinematic viscosity, cetane number, oxygen content and aromatic hydrocarbon content.
[0015] Optionally, the density, lower heating value, cetane number, oxygen content and aromatic hydrocarbon content of the mixed fuel physicochemical property parameters are calculated according to the formula X=mX 1 +(1-m)X 2 Sure;
[0016] The kinematic viscosity of the mixed fuel physicochemical property parameters is calculated according to the formula Sure;
[0017] Where X is the physical and chemical property parameter of the mixed fuel composed of the first fuel and the second fuel, X 1 is the physical and chemical property parameter of the first fuel, X 2 is the physical and chemical property parameter of the second fuel, and m is the mass fraction of the first fuel in the mixed fuel.
[0018] Optionally, the fuel consumption and emission prediction model is a deep neural network, a random forest or a support vector machine.
[0019] Optionally, the objective function of the optimization algorithm is expressed as: Y = ω 1 BSFC+ω 2 CO+ω 3 HC+ω 4 NOx+ω 5 PM;
[0020] Among them, Y is the objective function value, ω 1 ,ω 2 ,ω 3 ,ω 4 and ω 5All of them are weight coefficients, BSFC is fuel consumption, CO is carbon monoxide emissions, HC is hydrocarbon emissions, NOx is nitrogen oxide emissions, and PM is particulate matter emissions; the emission data includes the carbon monoxide emissions, the hydrocarbon emissions, the nitrogen oxide emissions and the particulate matter emissions.
[0021] Optionally, the optimization algorithm is a genetic algorithm or a particle swarm optimization algorithm.
[0022] Optionally, when the optimization algorithm is a genetic algorithm, based on the real-time engine operating parameters, the physical and chemical property parameters of the mixed fuel of the mixed fuel engine are iteratively optimized by using the optimization algorithm, and the optimized physical and chemical property parameters of the mixed fuel are output, which specifically includes:
[0023] Initializing individuals in the population; each of the individuals includes real-time engine operating parameters and real-time engine operating parameters;
[0024] Calculating the fitness of each individual; the fitness is the objective function value;
[0025] Selecting an individual as a parent from each of the individuals according to the fitness;
[0026] The individuals that serve as the parent generation are reproduced for the next generation to obtain offspring individuals;
[0027] performing random mutation on the offspring individuals;
[0028] Determine whether the fitness of each individual after mutation meets the preset requirements;
[0029] If there is a mutated individual that meets the preset requirements, the physical and chemical property parameters of the mixed fuel corresponding to the mutated individual that meets the preset requirements are output as the optimized physical and chemical property parameters of the mixed fuel;
[0030] If there is no mutated individual that meets the preset requirements, an individual as a parent is selected from each of the mutated individuals according to the fitness, and the step of returning to reproduce the individual as the parent for the next generation to obtain an offspring individual is performed.
[0031] In a second aspect, the present application provides an engine fuel real-time mixing device, comprising a controller, a fuel tank A, a fuel tank B, a mixing tank, a flow valve A and a flow valve B, wherein the flow valve A and the flow valve B are both connected to the controller; the flow valve A is connected between the fuel tank A and the mixing tank, and the flow valve B is connected between the fuel tank B and the mixing tank; the fuel tank A is used to store a first fuel, and the fuel tank B is used to store a second fuel;
[0032] The controller is used to execute the above-mentioned real-time engine fuel mixing method, output the mixing ratio of the first fuel and the second fuel in real time, calculate the flow rate of the first fuel flowing through the flow valve A and the flow rate of the second fuel flowing through the flow valve B according to the currently required fuel amount and the mixing ratio; control the flow valve A according to the flow rate of the first fuel flowing through the flow valve A, and control the flow valve B according to the flow rate of the second fuel flowing through the flow valve B.
[0033] Optionally, the engine fuel real-time mixing device also includes a sensor, which is used to collect real-time engine operating parameters of the mixed fuel engine in real time and send the real-time engine operating parameters to the controller; the real-time engine operating parameters include speed and torque.
[0034] Optionally, the engine fuel real-time mixing device further comprises a fuel supply system, wherein the fuel supply system is connected to the mixing tank, and the fuel supply system is used to deliver the mixed fuel in the mixing tank to the mixed fuel engine.
[0035] According to the specific embodiments provided in this application, this application discloses the following technical effects:
[0036] The present application provides a real-time mixing method and device for engine fuel. Based on real-time engine operating parameters, the physical and chemical property parameters of the mixed fuel of the mixed fuel engine are iteratively optimized by adopting an optimization algorithm, and the optimized physical and chemical property parameters of the mixed fuel are output. During each optimization process, the objective function value of the optimization algorithm is calculated according to the fuel consumption prediction value and the emission data prediction value. When the objective function value reaches the preset requirement, the optimized physical and chemical property parameters of the mixed fuel are output, so that under each operating condition, the fuel consumption and emission data are optimized by optimizing the physical and chemical property parameters of the mixed fuel, thereby achieving low fuel consumption and low pollutant emissions of the mixed fuel engine under all operating conditions. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0038] Figure 1 A schematic flow chart of a method for real-time mixing of engine fuel provided in one embodiment of the present application;
[0039] Figure 2 A schematic diagram of the principle of a real-time engine fuel mixing method provided in one embodiment of the present application;
[0040] Figure 3 A schematic structural diagram of a real-time engine fuel mixing device provided in one embodiment of the present application. DETAILED DESCRIPTION
[0041] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0042] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.
[0043] The present application provides a method for real-time mixing of engine fuel, such as Figure 1 and Figure 2 As shown, the engine fuel real-time mixing method includes steps 101 to 106.
[0044] Step 101: Collect a historical data set of a mixed fuel engine; the historical data set includes engine operating parameters, mixed fuel physicochemical property parameters, engine fuel consumption and emission data; the mixed fuel physicochemical property parameters are determined based on the physicochemical property parameters of the first fuel and the physicochemical property parameters of the second fuel.
[0045] Step 102: Determine a training set based on the historical data set.
[0046] Step 103: Use the training set to train the fuel consumption and emission prediction model to obtain a trained fuel consumption and emission prediction model.
[0047] Step 104: Collecting real-time engine operating parameters of the mixed fuel engine.
[0048] Step 105: Based on the real-time engine operating parameters, the mixed fuel physical and chemical property parameters of the mixed fuel engine are iteratively optimized by adopting an optimization algorithm, and the optimized mixed fuel physical and chemical property parameters are output; each time the mixed fuel physical and chemical property parameters of the mixed fuel engine are iteratively optimized, the real-time engine operating parameters and the currently optimized mixed fuel physical and chemical property parameters are input into the trained fuel consumption and emission prediction model, and the engine fuel consumption prediction value and emission data prediction value are output. The objective function value of the optimization algorithm is calculated according to the fuel consumption prediction value and the emission data prediction value. When the objective function value reaches the preset requirement, the optimized mixed fuel physical and chemical property parameters are output.
[0049] Step 106: Determine the mixing ratio of the first fuel and the second fuel according to the optimized physical and chemical property parameters of the mixed fuel.
[0050] The present application discloses a real-time engine fuel mixing method, which is a data-driven real-time engine fuel mixing method, wherein data-driven is a problem-solving method that starts from raw data or observations, uses heuristic rules, searches for and establishes relationships between internal features, and thereby discovers some theorems or laws. The present application is based on real-time engine operating parameters, and under each operating condition, optimizes the fuel consumption and emission data by optimizing the physical and chemical property parameters of the mixed fuel, thereby achieving low fuel consumption and low pollutant emissions of the mixed fuel engine under all operating conditions.
[0051] In an exemplary embodiment, step 101 specifically includes collecting test data of a mixed fuel engine bench test as a historical data set, and the engine operating parameters include rotation speed and torque.
[0052] The physical and chemical property parameters of the mixed fuel include density, lower heating value, kinematic viscosity, cetane number, oxygen content and aromatic hydrocarbon content.
[0053] Emission data include carbon monoxide emissions, hydrocarbon emissions, nitrogen oxide emissions, and particulate matter emissions. The historical data set is the fuel consumption and emission data set of mixed fuel engines under different working conditions.
[0054] The density, lower calorific value, cetane number, oxygen content and aromatic hydrocarbon content of the mixed fuel physical and chemical properties are calculated according to the formula X = mX 1 +(1-m)X 2 Sure.
[0055] The kinematic viscosity of the mixed fuel physical and chemical properties is calculated according to the formula Sure.
[0056] Wherein, X is the physical and chemical property parameter of the mixed fuel composed of the first fuel and the second fuel, that is, the physical and chemical property parameter of the mixed fuel, X 1 is the physical and chemical property parameter of the first fuel, X 2 is the physical and chemical property parameter of the second fuel, and m is the mass fraction of the first fuel in the mixed fuel.
[0057] Among them, step 102 specifically includes: cleaning the data in the historical data set, the cleaning specifically includes removing outliers and missing values, normalizing the data in the cleaned historical data set using min-max to obtain a preprocessed historical data set, mapping the original data to between [0, 1], and eliminating the impact of dimensional differences between different parameters.
[0058] The normalized formula is expressed as: Among them, xn is the normalized data of a parameter, x is the original data of the parameter, and x min is the minimum value of the original data of this parameter, x max is the maximum value in the original data of this parameter.
[0059] The preprocessed historical data set is divided into 70% of the data as the training set of the model and 30% of the data as the test set of the model.
[0060] The fuel consumption and emission prediction model is a deep neural network, a random forest or a support vector machine.
[0061] The input parameters of the fuel consumption and emission prediction model are x = (S, T, ρ, LHV, v, CN, OC, AC), and the output parameters are y = (BSFC, CO, HC, NOx, PM).
[0062] Wherein, S is the speed, T is the torque, ρ is the density, LHV is the lower heating value, v is the kinematic viscosity, CN is the cetane number, OC is the oxygen content, AC is the aromatic hydrocarbon content, BSFC is the fuel consumption of the mixed fuel engine, CO is the carbon monoxide emission, HC is the hydrocarbon emission, NOx is the nitrogen oxide emission, and PM is the particulate matter emission.
[0063] If the fuel consumption and emission prediction model is a deep neural network, the relationship between the input parameters and output parameters of the fuel consumption and emission prediction model is: y = f (L) (W (L) f (L-1) (W (L-1) …f (1) (W (1) x+b (1) )+…+b (L-1) )+b (L) ).
[0064] Among them, L represents the number of hidden layers, f (L) represents the activation function of the Lth layer, W (L) represents the weight matrix of the Lth layer, b (L) Represents the bias vector of the Lth layer.
[0065] The root mean square error (MSE) is used as the loss function of the fuel consumption and emission prediction model. The formula of the loss function is:
[0066] Where n represents the number of samples, y i is the true value of the i-th sample, Represents the predicted value of the i-th sample.
[0067] When the loss function meets the preset requirements, the model training is stopped. The trained model can predict the corresponding output parameters y = (BSFC, CO, HC, NOx, PM) that meet the accuracy requirements based on the given input parameters x = (S, T, ρ, LHV, v, CN, OC, AC), and accurately predict the corresponding fuel consumption and emissions based on the engine operating parameters and the physical and chemical properties of the fuel.
[0068] This application uses an optimization algorithm to optimize the physical and chemical properties of the fuel so that it can achieve optimal fuel consumption and emissions at different engine speeds and torques.
[0069] The objective function of the optimization algorithm is: Y = ω 1 BSFC+ω 2 CO+ω 3 HC+ω 4 NOx+ω 5 PM.
[0070] Among them, Y is the objective function value, ω 1 ,ω 2 ,ω 3 ,ω 4 and ω 5 are all weight coefficients.
[0071] The optimization algorithm is a genetic algorithm or a particle swarm optimization algorithm.
[0072] When the optimization algorithm is a genetic algorithm, step 105 specifically includes steps 1051 to 1058.
[0073] Step 1051: Initialize individuals in the population; each of the individuals includes real-time engine operating parameters and real-time engine operating parameters.
[0074] The individuals in the population represent a set of solutions x = (S, T, ρ, LHV, v, CN, OC, AC), which contains a total of 8 variables. It should be noted that S and T are obtained according to the real-time data of the engine and remain consistent in all individuals. The remaining ρ, LHV, v, CN, OC, AC must satisfy the formula for determining the physical and chemical properties of the mixed fuel, that is, a mixed fuel with corresponding physical and chemical properties can be obtained by mixing two fuels to ensure that the optimized physical and chemical properties of the fuel are within a reasonable range.
[0075] The formula for determining the physical and chemical properties of mixed fuels includes X = mX 1 +(1-m)X 2 and
[0076] Step 1052: Calculate the fitness of each individual; the fitness is the objective function value. Calculate the fitness of individuals in the population, that is, calculate the objective function value Y according to the individual x in the population.
[0077] Step 1053: Select an individual as a parent from each of the individuals according to the fitness. The probability of an individual being selected as a parent is proportional to the value of its fitness.
[0078] Step 1054: The next generation individuals are reproduced on the individuals that serve as the parent generation to obtain offspring individuals.
[0079] Step 1055: Randomly mutate the offspring individuals so that each individual after mutation satisfies the formula for determining the physical and chemical property parameters of the mixed fuel.
[0080] Step 1056: Determine whether the fitness of each mutated individual meets the preset requirements.
[0081] If the output of step 1056 is yes, execute step 1057, and if the output of step 1056 is no, execute step 1058.
[0082] After optimization, the fitness of the individual meets the preset requirements, that is, the physical and chemical properties of the fuel meet the preset requirements of the engine's fuel consumption and emissions. Meeting the preset requirements means that the fitness is less than the preset value.
[0083] Step 1057: Outputting the physical and chemical property parameters of the mixed fuel corresponding to the mutated individuals that meet the preset requirements as the optimized physical and chemical property parameters of the mixed fuel.
[0084] Step 1058: Select an individual as a parent from each of the mutated individuals according to the fitness, and return to step 1054.
[0085] The mass ratio of the first fuel in the mixed fuel is calculated based on the optimized physical and chemical property parameters of the mixed fuel combined with the physical and chemical property parameter determination formula, and then the mixing ratio of the two fuels is calculated. Further, the fuel is mixed by a real-time fuel mixing device according to the required fuel amount and mixing ratio.
[0086] The data-driven fuel mixing method of the present application obtains the optimal mixed fuel ratio for fuel consumption and emission performance under different engine operating conditions by constructing an engine fuel consumption and emission prediction model and a fuel physical and chemical property optimization model.
[0087] In an exemplary embodiment, the present application also provides an engine fuel real-time mixing device, which includes a controller, a fuel tank A, a fuel tank B, a mixing tank, a flow valve A and a flow valve B, wherein the flow valve A and the flow valve B are both connected to the controller; the flow valve A is connected between the fuel tank A and the mixing tank, and the flow valve B is connected between the fuel tank B and the mixing tank; the fuel tank A is used to store a first fuel, and the fuel tank B is used to store a second fuel.
[0088] An engine fuel real-time mixing device also includes an oil pipeline A and an oil pipeline B, wherein the oil pipeline A is connected to a flow valve A and both ends of the oil pipeline A are connected to a mixing tank, and the oil pipeline B is connected to a flow valve B and both ends of the oil pipeline B are connected to a mixing tank.
[0089] The engine fuel real-time mixing method is written into the controller in the form of a program.
[0090] The controller is used to execute the engine fuel real-time mixing method in real time after receiving the engine real-time operating condition parameters ( Figure 3 The invention relates to a mixed fuel calculation method, which outputs the mixing ratio of the first fuel and the second fuel in real time, calculates the flow rate of the first fuel flowing through the flow valve A and the flow rate of the second fuel flowing through the flow valve B according to the current required fuel amount and the mixing ratio; controls the flow valve A according to the flow rate of the first fuel flowing through the flow valve A, and controls the flow valve B according to the flow rate of the second fuel flowing through the flow valve B.
[0091] The two fuels flow through the flow valve and the oil pipeline and then converge into the mixing tank for real-time mixing. At this time, the mixed fuel in the mixing tank is the mixed fuel with the best fuel consumption and emission performance under the real-time working conditions.
[0092] The engine fuel real-time mixing device also includes a sensor, which is connected to the engine. The sensor is used to collect real-time engine operating parameters of the mixed fuel engine in real time and send the real-time engine operating parameters to the controller; the real-time engine operating parameters include speed and torque.
[0093] The engine fuel real-time mixing device also includes a fuel supply system, which is connected to the mixing tank and is used to transport the mixed fuel in the mixing tank to the mixed fuel engine.
[0094] The present application provides a real-time engine fuel mixing method that can obtain the optimal mixing ratio of the mixed fuel of the engine under different operating conditions. The fuel is mixed in real time according to the ratio by controlling the mixing device, and the mixed fuel with the optimal mixing ratio for the current operating condition is supplied to the engine through the fuel supply system, thereby achieving efficient and clean combustion of the mixed fuel engine within the full operating range, reducing fuel consumption and pollutant emissions.
[0095] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0096] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.
Claims
1. A real-time mixing method for engine fuel, characterized in that: The engine fuel real-time mixing method comprises: Collecting a historical data set of a mixed fuel engine; the historical data set includes engine operating parameters, mixed fuel physicochemical property parameters, engine fuel consumption and emission data; the mixed fuel physicochemical property parameters are determined according to the physicochemical property parameters of the first fuel and the physicochemical property parameters of the second fuel; Determine a training set based on the historical data set; The training set is used to train the fuel consumption and emission prediction model to obtain a trained fuel consumption and emission prediction model; collecting real-time engine operating parameters of the mixed fuel engine; Based on the real-time engine operating parameters, the mixed fuel physical and chemical property parameters of the mixed fuel engine are iteratively optimized by using an optimization algorithm, and the optimized mixed fuel physical and chemical property parameters are output; each time the mixed fuel physical and chemical property parameters of the mixed fuel engine are iteratively optimized, the real-time engine operating parameters and the currently optimized mixed fuel physical and chemical property parameters are input into a trained fuel consumption and emission prediction model, and the engine fuel consumption prediction value and emission data prediction value are output, and the objective function value of the optimization algorithm is calculated according to the fuel consumption prediction value and the emission data prediction value. When the objective function value reaches the preset requirement, the optimized mixed fuel physical and chemical property parameters are output; The mixing ratio of the first fuel and the second fuel is determined according to the optimized physical and chemical property parameters of the mixed fuel.
2. The engine fuel real-time mixing method according to claim 1, characterized in that: The physical and chemical property parameters of the mixed fuel include density, lower heating value, kinematic viscosity, cetane number, oxygen content and aromatic hydrocarbon content.
3. The engine fuel real-time mixing method according to claim 2, characterized in that: The density, lower heating value, cetane number, oxygen content and aromatic hydrocarbon content of the mixed fuel physical and chemical property parameters are determined according to the formula X=mX1+(1-m)X2; The kinematic viscosity of the mixed fuel physicochemical property parameters is calculated according to the formula Sure; Wherein, X is the physical and chemical property parameter of the mixed fuel composed of the first fuel and the second fuel, X1 is the physical and chemical property parameter of the first fuel, X2 is the physical and chemical property parameter of the second fuel, and m is the mass fraction of the first fuel in the mixed fuel.
4. The engine fuel real-time mixing method according to claim 1, characterized in that: The fuel consumption and emission prediction model is a deep neural network, a random forest or a support vector machine.
5. The engine fuel real-time mixing method according to claim 1, characterized in that: The objective function of the optimization algorithm is expressed as: Y = ω1BSFC + ω2CO + ω3HC + ω4NOx + ω5PM; Among them, Y is the objective function value, ω1, ω2, ω3, ω4 and ω5 are weight coefficients, BSFC is fuel consumption, CO is carbon monoxide emissions, HC is hydrocarbon emissions, NOx is nitrogen oxide emissions, PM is particulate matter emissions; the emission data includes the carbon monoxide emissions, the hydrocarbon emissions, the nitrogen oxide emissions and the particulate matter emissions.
6. The engine fuel real-time mixing method according to claim 1, characterized in that: The optimization algorithm is a genetic algorithm or a particle swarm optimization algorithm.
7. The engine fuel real-time mixing method according to claim 6, characterized in that: When the optimization algorithm is a genetic algorithm, based on the real-time engine operating parameters, the physical and chemical property parameters of the mixed fuel of the mixed fuel engine are iteratively optimized by using the optimization algorithm, and the optimized physical and chemical property parameters of the mixed fuel are output, which specifically includes: Initializing individuals in the population; each of the individuals includes real-time engine operating parameters and real-time engine operating parameters; Calculating the fitness of each individual; the fitness is the objective function value; Selecting an individual as a parent from each of the individuals according to the fitness; The individuals that serve as the parent generation are reproduced for the next generation to obtain offspring individuals; performing random mutation on the offspring individuals; Determine whether the fitness of each individual after mutation meets the preset requirements; If there is a mutated individual that meets the preset requirements, the physical and chemical property parameters of the mixed fuel corresponding to the mutated individual that meets the preset requirements are output as the optimized physical and chemical property parameters of the mixed fuel; If there is no mutated individual that meets the preset requirements, an individual as a parent is selected from each of the mutated individuals according to the fitness, and the step of returning to reproduce the individual as the parent for the next generation to obtain an offspring individual is performed.
8. A real-time mixing device for engine fuel, characterized in that: The engine fuel real-time mixing device comprises a controller, a fuel tank A, a fuel tank B, a mixing tank, a flow valve A and a flow valve B, wherein the flow valve A and the flow valve B are both connected to the controller; the flow valve A is connected between the fuel tank A and the mixing tank, and the flow valve B is connected between the fuel tank B and the mixing tank; the fuel tank A is used to store a first fuel, and the fuel tank B is used to store a second fuel; The controller is used to execute the real-time engine fuel mixing method described in any one of claims 1 to 7, output the mixing ratio of the first fuel and the second fuel in real time, calculate the flow rate of the first fuel flowing through the flow valve A and the flow rate of the second fuel flowing through the flow valve B according to the currently required fuel quantity and the mixing ratio; control the flow valve A according to the flow rate of the first fuel flowing through the flow valve A, and control the flow valve B according to the flow rate of the second fuel flowing through the flow valve B.
9. The engine fuel real-time mixing device according to claim 8, characterized in that: The engine fuel real-time mixing device further comprises a sensor, the sensor being used to collect real-time engine operating parameters of the mixed fuel engine in real time and send the real-time engine operating parameters to the controller; The real-time engine operating parameters include rotation speed and torque.
10. The engine fuel real-time mixing device according to claim 8, characterized in that: The engine fuel real-time mixing device also includes a fuel supply system, which is connected to the mixing tank and is used to transport the mixed fuel in the mixing tank to the mixed fuel engine.
Citation Information
Cited By
Nozzle structure optimization method and device of methanol-diesel direct injection engine and computer storage medium
CN120030706A