Fuel control method of methanol-diesel dual-fuel engine

Abstract

The invention relates to the technical field of dual-fuel engines, in particular to a fuel control method for a methanol-diesel dual-fuel engine, which comprises the following steps: acquiring real-time data of a rotating speed value, a load value and a temperature value of the engine; inputting the real-time data into a pre-established engine working condition model, and outputting fuel demand characteristic parameters of the current working condition; inputting the fuel demand characteristic parameters into a pre-established injection proportion model, and outputting an injection proportion value of diesel oil and methanol; based on the injection proportion value, a fuel injection scheme of diesel oil and methanol is generated; according to the fuel injection scheme, a time sequence control algorithm is adopted to generate a diesel oil injection instruction and a methanol injection instruction with a time phase difference, and the mixing effect of diesel oil and methanol is monitored in real time; the injection proportion of diesel oil and methanol can be accurately adjusted, full mixing of the two kinds of fuel can be guaranteed through real-time monitoring, the fuel utilization efficiency is improved, emission is reduced, and stable operation and performance output of an engine are guaranteed.

Description

Technical Field

[0001] The invention relates to the technical field of dual-fuel engines, and in particular to a fuel control method for a methanol-diesel dual-fuel engine. Background Art

[0002] In a dual-fuel engine system, the injection control of diesel and methanol is a key technical link. As the main fuel, diesel is responsible for igniting the mixture, while methanol, as an auxiliary fuel, can optimize the combustion process and reduce emissions. However, in the current system, the injection of diesel and methanol is managed by independent control units ECU respectively. This separate control method leads to insufficient synergy between the two fuels. Specifically, the injection timing and injection amount of diesel cannot be dynamically matched with the injection timing and amount of methanol. For example, when the engine operating conditions change, the diesel injection control unit adjusts the injection strategy according to the load and speed, while the methanol injection control unit may lag or advance the response, resulting in the time and proportion of the two fuels entering the cylinder being inconsistent. This incoordination will directly affect the quality of the mixture formation, and then affect the combustion stability.

[0003] Therefore, how to achieve dynamic coordination of two fuel injections is a technical problem that needs to be urgently solved in the current dual-fuel engine system. Summary of the invention

[0004] The purpose of the present invention is to overcome the above-mentioned shortcomings and provide a fuel control method for a methanol-diesel dual-fuel engine, which can not only accurately adjust the injection ratio of diesel and methanol, but also ensure the full mixing of the two fuels through real-time monitoring, thereby improving fuel utilization efficiency, reducing emissions, and ensuring the stable operation and performance output of the engine.

[0005] To achieve the above object, the specific scheme of the present invention is as follows: A fuel control method for a methanol-diesel dual-fuel engine, specifically comprising: obtaining real-time data of engine speed value, load value and temperature value; inputting the real-time data into a pre-established engine operating condition model, and outputting fuel demand characteristic parameters of the current operating condition;

[0006] Input the fuel demand characteristic parameters into the pre-established injection ratio model, and output the injection ratio value of diesel and methanol;

[0007] Generate a fuel injection plan of diesel and methanol based on the injection ratio value;

[0008] According to the fuel injection scheme, a timing control algorithm is used to generate diesel injection instructions and methanol injection instructions with a time phase difference, and the mixing effect of diesel and methanol is monitored in real time.

[0009] Optionally, the step of inputting the real-time data into a pre-established engine operating condition model and outputting the fuel demand characteristic parameters of the current operating condition comprises: inputting the speed value, the load value and the temperature value into the engine operating condition model based on polynomial regression to obtain the fuel demand characteristic parameters of the current operating condition;

[0010] If the fuel demand characteristic parameter is greater than a preset threshold, the relationship between the fuel demand characteristic parameter and the speed value, load value and temperature value is fitted by the least squares method to generate a corrected fuel demand characteristic parameter.

[0011] Optionally, the inputting of the speed value, the load value and the temperature value into the engine operating condition model based on polynomial regression to obtain the fuel demand characteristic parameters of the current operating condition includes: ;

[0012] In the formula, represents the fuel demand characteristic parameter, n represents the engine speed value, L represents the load value, T represents the temperature value, β0 represents the constant term coefficient, and β1 to β6 represent the regression coefficients of each item.

[0013] Optionally, the generating of the corrected fuel demand characteristic parameter by fitting the relationship between the fuel demand characteristic parameter and the speed value, the load value and the temperature value by the least square method includes: ;

[0014] In the formula, represents the fuel demand characteristic parameter, n represents the engine speed value, L represents the engine load value, T represents the engine temperature value, and k1, k2, k3 and k4 represent the coefficients to be fitted.

[0015] Optionally, the step of inputting the fuel demand characteristic parameter into a pre-established injection ratio model and outputting the injection ratio value of diesel and methanol comprises: inputting the fuel demand characteristic parameter into a pre-established injection ratio model, wherein the injection ratio model is trained using a linear regression algorithm and fuel demand characteristic parameters of historical engine operating conditions; the training data comprises the injection ratio of diesel and methanol and the corresponding fuel demand characteristic parameters;

[0016] The trained injection ratio model is used to predict the diesel and methanol injection ratio under the current working conditions; ;

[0017] Where R represents the injection ratio of diesel and methanol, α1, α2 and α3 are regression coefficients, X1, X2 and X3 are fuel demand characteristic parameters, and θ is the bias constant.

[0018] Optionally, the trained injection ratio model is used to predict the diesel and methanol injection ratio under the current operating conditions, including:

[0019] According to the prediction results, the model prediction error is calculated, where ;

[0020] In the formula, E represents the model prediction error, n is the number of samples, and y i is the actual injection ratio value, is the injection ratio value predicted by the model.

[0021] Optionally, generating a fuel injection scheme of diesel and methanol based on the injection ratio value includes: determining a power load parameter and an emission index parameter in combination with a diesel engine performance curve;

[0022] According to the power load parameters and emission index parameters, the combustion efficiency coefficient of diesel and the critical mixing ratio threshold of methanol are calculated;

[0023] The diesel combustion efficiency coefficient is calculated by using the thermal efficiency formula through the calculation of diesel combustion calorific value and the measurement of actual output power;

[0024] According to the injection ratio value and the physical and chemical properties of methanol, the critical mixing ratio threshold of methanol is determined by using a flash point tester;

[0025] Generate a target ratio range of methanol and diesel based on the injection ratio value, and determine the injection timing distribution in combination with the combustion efficiency coefficient;

[0026] Determine whether the injection timing distribution exceeds the constraint of the critical mixture ratio threshold, and if so, adjust the boundary conditions of the target ratio range;

[0027] A fuel double-pulse control map including injection quantity, phase difference and duration is generated according to the adjusted boundary conditions.

[0028] Optionally, the thermal efficiency formula is used to calculate the diesel combustion efficiency coefficient, including:

[0029] The thermal efficiency formula is , where η is the combustion efficiency coefficient, P is the actual output power, m d is the diesel quality, Q d is the calorific value of diesel.

[0030] Optionally, the step of generating the fuel dual pulse control map includes:

[0031] According to the target ratio range and injection timing distribution, the injection quantity and phase difference at each time point are calculated to determine the duration of each injection pulse.

[0032] Optionally, the method of using a timing control algorithm to generate a diesel injection instruction and a methanol injection instruction with a time phase difference includes: using a PID control algorithm to calculate the injection amount difference between diesel and methanol according to the injection ratio value of the two, and generating an initial injection instruction;

[0033] According to the initial injection command and the fuel injection plan, a timer control tool is used to generate an injection command with a time difference.

[0034] The present invention has the following beneficial effects: the present invention obtains the engine operating condition data in real time and inputs it into a pre-established operating condition model to obtain the fuel demand characteristic parameters under the current operating condition. Subsequently, these parameters are input into the injection ratio model to calculate the optimal injection ratio of diesel and methanol; based on this ratio, a detailed fuel injection scheme is generated, and a timing control algorithm is used to generate an injection instruction with a time phase difference. In this way, not only can the injection ratio of diesel and methanol be accurately adjusted, but also the full mixing of the two fuels can be ensured through real-time monitoring, thereby improving fuel utilization efficiency, reducing emissions, and ensuring the stable operation and performance output of the engine. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 The figure is a schematic flow chart of the fuel control method of the methanol-diesel dual-fuel engine of the present invention.

[0036] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments, but the implementation scope of the present invention is not limited thereto.

[0037] like Figure 1 As shown, the fuel control method of a methanol-diesel dual-fuel engine provided in this embodiment may specifically include the following steps:

[0038] Step S100: acquiring real-time data of engine speed value, load value and temperature value; inputting the real-time data into a pre-established engine operating condition model, and outputting fuel demand characteristic parameters of the current operating condition.

[0039] Specifically, the real-time data of the engine is obtained, including the speed value, load value and temperature value; then the speed value, load value and temperature value are input into the pre-established engine operating condition model based on polynomial regression. The training process of the engine operating condition model based on polynomial regression includes: taking the injection ratio of diesel and methanol and its corresponding fuel demand characteristic parameters as training data, the fuel demand characteristic parameters in the training data include engine speed, load and temperature, and using a linear regression algorithm to train the injection ratio model. Through model calculation, the fuel demand characteristic parameters of the current working condition are obtained.

[0040] The calculation formula of the fuel demand characteristic parameter can be set as follows: ;

[0041] In the formula, represents the fuel demand characteristic parameter, n represents the engine speed value, L represents the load value, T represents the temperature value, β0 represents the constant term coefficient, and β1 to β6 represent the regression coefficients of each item.

[0042] Furthermore, if the fuel demand characteristic parameter is greater than a preset threshold, the relationship between the fuel demand characteristic parameter and the speed value, load value and temperature value is fitted by the least square method to generate a corrected fuel demand characteristic parameter. By real-time monitoring and correction of the fuel demand characteristic parameter, it can be ensured that the engine can maintain the best fuel economy under different working conditions.

[0043] The fitting formula of fuel demand characteristic parameters can be set as follows: ;

[0044] In the formula, represents the fuel demand characteristic parameter, n represents the engine speed value, L represents the engine load value, T represents the engine temperature value, and k1, k2, k3 and k4 represent the coefficients to be fitted.

[0045] For example, the sensor collects data of the engine speed value such as 2000 rpm, the load value such as 80%, and the temperature value such as 90° C. in real time. These data are input into the pre-established engine operating condition model based on polynomial regression, and the model form is:

[0046] , where β0=1.2, β1=0.003, β2=0.005, β3=0.002, β4=-0.0001, β5=-0.0002, β6=-0.0001; through model calculation, the fuel demand characteristic parameter F=15.6 of the current working condition is obtained. If F is greater than the preset threshold value 15, the relationship between F and n, L, and T is fitted by the least squares method to generate the corrected fuel demand characteristic parameter F'=14.8. The fitting formula is:

[0047] , where k1=0.002, k2=0.004, k3=0.001, k4=1.1.

[0048] In practical applications, the fuel demand characteristic parameters of the engine during operation depend on three key indicators: speed, load and temperature. The polynomial regression model can accurately describe the relationship between these parameters, thereby achieving accurate prediction of fuel demand. The engine speed may vary between 2,000 and 6,000 rpm, the load value ranges from 10% to 90%, and the temperature value fluctuates between 60 degrees Celsius and 120 degrees Celsius. For example, when the speed is 3,000 rpm, the load value is 60%, and the temperature is 80 degrees Celsius, the fuel demand characteristic parameter calculated by the polynomial regression model is 0.75. This value reflects the actual fuel demand of the engine under this working condition. If the fuel demand characteristic parameter exceeds the preset threshold, such as 0.85, it needs to be corrected. The correction process uses the least squares method to fit the relationship between the parameters by establishing a linear equation group. For example, when a heavy truck is transporting long distances, the fuel demand characteristic parameter may exceed the threshold due to the large load and long duration. At this time, the correction coefficient obtained by fitting the least squares method can more accurately reflect the fuel demand characteristics of the engine under high load conditions.

[0049] The coefficients in the polynomial regression model reflect the degree of influence of different parameters on fuel demand. A large speed coefficient indicates that speed changes have a significant impact on fuel demand, while a relatively small temperature coefficient indicates that the impact of temperature changes is relatively small. For example, when the speed rises rapidly during the startup phase, the fuel demand characteristic parameter will increase significantly, while the impact of changes in ambient temperature on fuel demand is relatively small. The calculation and correction process of the fuel demand characteristic parameter is actually an important means to optimize engine performance under different operating conditions.

[0050] This embodiment can effectively reduce fuel consumption and extend the service life of the engine through this dynamic adjustment mechanism. Through the precise control of the fuel demand characteristic parameters, the optimal operating state of the engine under different working conditions can be achieved. The dynamically adjusted fuel demand characteristic parameters can ensure that the engine maintains good power output and fuel economy in each process.

[0051] Step S200: inputting fuel demand characteristic parameters into a pre-established injection ratio model, and outputting the injection ratio value of diesel and methanol.

[0052] Specifically, the fuel demand characteristic parameters are input into a pre-established injection ratio model, which is trained using the fuel demand characteristic parameters of the engine's historical operating conditions using a linear regression algorithm. The training data includes the injection ratio of diesel and methanol and their corresponding fuel demand characteristic parameters. The trained injection ratio model is used to predict the injection ratio of diesel and methanol under the current operating conditions. In actual application, the fuel demand characteristic parameters under the current operating conditions are input into the trained injection ratio model to predict the injection ratio of diesel and methanol.

[0053] The injection ratio of diesel and methanol can be obtained by the following formula: ;

[0054] Where R represents the injection ratio of diesel and methanol, α1, α2 and α3 are regression coefficients, X1, X2 and X3 are fuel demand characteristic parameters, and θ is the bias constant.

[0055] Furthermore, based on the prediction results, the model prediction error is calculated: ;

[0056] In the formula, E represents the model prediction error, n is the number of samples, and y i is the actual injection ratio value, is the injection ratio value predicted by the model.

[0057] In practical applications, the key to the application of the injection ratio model is to use the fuel demand characteristic parameters to predict the optimal ratio of diesel and methanol. For example, when the fuel demand characteristic parameter is 0.75, the diesel and methanol injection ratio calculated by the linear regression model is about 7:3. This ratio can ensure that the engine obtains the best combustion efficiency and emission performance under this working condition. The linear regression algorithm establishes the relationship between the injection ratio and the fuel demand characteristic parameters by analyzing historical data. For example, when the fuel demand characteristic parameters range from 0.6 to 0.85, the corresponding diesel and methanol injection ratio varies between 8:2 and 6:4. This dynamic adjustment mechanism can automatically optimize the fuel ratio according to changes in working conditions.

[0058] The quality of model training data directly affects the prediction accuracy. When collecting training data, it is necessary to cover the operating status of the engine under different load conditions. From no-load to full-load conditions, the recorded fuel demand characteristic parameters and the corresponding optimal injection ratio can form a complete data set, providing a reliable basis for model training. The calculation and control of prediction errors are important links to ensure the practicality of the model. For example, the average error between the injection ratio predicted by the model and the actual optimal ratio is controlled within 3%. This level of accuracy can meet actual production needs while leaving appropriate adjustment space. The regression coefficient reflects the degree of influence of different characteristic parameters on the injection ratio. For example, the characteristic parameter coefficient related to speed is the largest, indicating that the speed change has the most significant impact on the fuel ratio. The temperature-related characteristic parameter coefficient is small, indicating that the impact of temperature changes on the injection ratio is relatively small.

[0059] The dynamic prediction capability of the injection ratio model plays an important role in optimizing engine performance. For example, if the operating conditions change greatly due to frequent starts and stops, the injection ratio of diesel and methanol can be adjusted in real time to maintain the best combustion state. From idling to acceleration, the injection ratio will automatically adjust with the changes in the fuel demand characteristic parameters, ensuring both power output and controlling emission levels. In practical applications, the prediction results of the model need to take into account the physical constraints of the engine. For example, when working in a low-temperature environment, in order to ensure reliability, the injection ratio of diesel needs to be appropriately increased. By correcting the output results of the injection ratio model, the adaptability of the vehicle in low-temperature environments is improved.

[0060] Step S201: The injection ratio model is trained using the fuel demand characteristic parameters of the historical engine operating conditions using a linear regression algorithm, specifically including:

[0061] Obtain the fuel demand characteristic parameters of the engine's historical operating conditions, including engine speed, load, and temperature. Collect the injection ratio data of diesel and methanol and match them with the fuel demand characteristic parameters. Use the fuel demand characteristic parameters as independent variables and the injection ratio of diesel and methanol as dependent variables to construct a training data set. Use the linear regression algorithm in the Scikit-learn library to initialize the regression model. Use the training data set to train the linear regression model to minimize the prediction error. During the training process, determine the values ​​of the regression coefficients α1, α2, α3 and the bias constant θ.

[0062] Exemplarily, the fuel demand characteristic parameters of the historical working conditions of the engine are obtained, including data with an engine speed of 2000rpm, a load of 75%, and a temperature of 85°C. The injection ratio data of diesel and methanol are collected, for example, the diesel injection amount is 10mL and the methanol injection amount is 5mL, and matched with the fuel demand characteristic parameters. The fuel demand characteristic parameters are used as independent variables, and the injection ratio of diesel and methanol is used as the dependent variable to construct a training data set, specifically including 1000 sets of historical working condition data. The linear regression algorithm in the Scikit-learn library is used to initialize the regression model and set the random seed to 42. The linear regression model is trained using the training data set to minimize the prediction error, using the mean square error as the loss function, and the number of iterations is 1000 times. During the training process, the values ​​of regression coefficients α1 of 0.8, α2 of 0.6, α3 of 0.4, and bias constant θ of 0.1 are determined. The fuel demand characteristic parameters under the current working conditions are input into the trained linear regression model, for example, the parameters of engine speed of 2500rpm, load of 80%, and temperature of 90°C are input. Through model calculation, the injection ratio of diesel and methanol under the current working conditions is predicted, and the diesel injection amount is 12mL and the methanol injection amount is 6mL.

[0063] For another example, 1000 sets of data are extracted from the historical database, each set contains the injection ratio of diesel and methanol and the corresponding engine speed, load, and temperature values. According to the training data set, the fuel demand characteristic parameters are defined as engine speed, load, and temperature, corresponding to variables X1, X2, and X3, respectively. For example, the engine speed range is 800-4000rpm, the load range is 20%-100%, and the temperature range is 60-120℃. The Scikit-learn library in Python is used to initialize the linear regression algorithm model, and the model parameters are set to regression coefficients α1, α2, α3, and bias constant θ, for example, α1=0.5, α2=0.3, α3=0.2, and θ=0.1 are initialized. By minimizing the prediction error, the linear regression model is trained to determine the specific values ​​of the regression coefficients α1, α2, α3, and bias constant θ. For example, after training, α1=0.6, α2=0.4, α3=0.1, and θ=0.05 are obtained. The trained linear regression model is saved as an injection ratio model for subsequent prediction of the injection ratio of diesel and methanol. For example, the model is saved as a file "injection ratio model.pkl". The fuel demand characteristic parameters under the current working conditions are obtained, including engine speed, load and temperature. For example, the current engine speed is 1500rpm, the load is 80%, and the temperature is 90°C. The fuel demand characteristic parameters of the current working conditions are input into the trained injection ratio model to obtain the predicted value R of the injection ratio of diesel and methanol. According to the predicted value R and the actual injection ratio value y i , calculate the model prediction error E, for example, E=0.02. If the prediction error E exceeds the preset threshold, re-extract the historical operating data, adjust the model parameters, and optimize the injection ratio model. For example, when E>0.05, retrain the model and update the regression coefficient and bias constant.

[0064] Step S300: Generate a fuel injection plan of diesel and methanol based on the injection ratio value.

[0065] Specifically, the power load parameter and emission index parameter are determined in combination with the diesel engine performance curve. According to the power load parameter and emission index parameter, the diesel combustion efficiency coefficient and the critical mixing ratio threshold of methanol are calculated; the diesel combustion efficiency coefficient is calculated by the diesel combustion calorific value calculation and the actual output power measurement, and the thermal efficiency formula is used to calculate the diesel combustion efficiency coefficient; wherein, the thermal efficiency formula is: , where η is the combustion efficiency coefficient, P is the actual output power, m d is the diesel quality, Q d is the calorific value of diesel.

[0066] According to the injection ratio value and the physical and chemical properties of methanol, the critical mixing ratio threshold of methanol is determined using a flash point tester.

[0067] The target ratio range of methanol and diesel is generated according to the injection ratio value (the target ratio range of methanol and diesel is generated using the linear interpolation method, and the linear interpolation method formula is: M ratio =M min +(M max -M min )×(PP min ) / (P max -P min ), where M ratio is the mixing ratio of methanol to diesel, M min and M max is the preset minimum and maximum mixing ratio, P is the current power load parameter, and P min and P min These are the preset minimum and maximum dynamic load parameters.

[0068] The injection timing distribution is determined in combination with the combustion efficiency coefficient; it is determined whether the injection timing distribution exceeds the constraint of the critical mixture ratio threshold value, and if so, the boundary conditions of the target ratio range are adjusted; according to the adjusted boundary conditions, a fuel dual-pulse control map including injection amount, phase difference and duration is generated to achieve precise mixed combustion control of methanol and diesel.

[0069] Furthermore, the method for generating the fuel dual-pulse control map is: according to the target ratio range and the injection timing distribution, the injection amount and phase difference at each time point are calculated to determine the duration of each injection pulse.

[0070] For example, the diesel engine performance curve is an important basis for analyzing the power load parameters and emission index parameters. For example, the engine performance data can be collected through the speed sensor and the torque sensor, and it is found that at different vehicle speeds, the power load parameter varies between 0.4 and 0.9, while the emission index parameter shows an upward trend as the load increases. When driving at a constant speed of 80 kilometers per hour, the diesel combustion efficiency coefficient reaches 42%, and the critical mixing ratio threshold of methanol is 35%. Under this condition, the diesel combustion calorific value is 42 megajoules per kilogram, and the actual output power is 200 kilowatts. The combustion efficiency coefficient calculated by the thermal efficiency formula indicates that the combustion state is good. For example, when an agricultural tractor is working on cultivated land, the power load parameter fluctuates greatly, and the target ratio range of methanol and diesel needs to be adjusted in real time. When the power load parameter rises from 0.5 to 0.8, the methanol mixing ratio calculated by the linear interpolation method increases from 20% to 30%. This dynamic adjustment ensures the stable operation of the engine under variable load conditions. For example, when an engineering machinery hydraulic excavator is performing excavation operations, the injection timing distribution needs to be precisely controlled according to the combustion efficiency coefficient. When the combustion efficiency coefficient is 38%, the system advances the diesel injection to 15 degrees before the top dead center and delays the methanol injection to 5 degrees after the top dead center. This staggered injection strategy effectively improves the fuel mixing effect. For example, when fishing vessels are operating in the open sea, the generation of the fuel dual-pulse control map is particularly critical. When the engine speed is 1,600 rpm, the diesel injection amount is 60 mg per cycle, the methanol injection amount is 25 mg per cycle, the phase difference is maintained at 20 degrees, and the injection duration is 1.2 milliseconds and 0.8 milliseconds respectively. This precise injection control enables the engine to maintain the best combustion state during long-term operation. For example, when buses are operating in urban areas, due to frequent starts and stops causing load changes, the injection timing distribution needs to be monitored in real time. When it is detected that the injection timing distribution is close to the critical mixture ratio threshold, the control system automatically adjusts the upper limit of the target ratio range from 35% to 30% to ensure the safety and stability of the combustion process. This adaptive adjustment mechanism significantly improves the adaptability of dual-fuel engines under complex working conditions.

[0071] Step S400: According to the fuel injection scheme, a timing control algorithm is used to generate a diesel injection instruction and a methanol injection instruction with a time phase difference, and the mixing effect of diesel and methanol is monitored in real time.

[0072] Specifically, the PID control algorithm is used to calculate the injection amount difference between diesel and methanol according to the injection ratio value, and generate the initial injection instruction; according to the initial injection instruction and the fuel injection scheme, the timer control tool is used to generate the injection instruction with time difference. By real-time monitoring of the mixing effect of diesel and methanol, it is judged whether the mixing ratio meets the preset threshold. If the mixing ratio does not meet the threshold, the time phase difference of the injection instruction is adjusted. According to the adjusted time phase difference, the injection amount of diesel and methanol is recalculated. According to the adjusted injection amount, a new fuel ratio scheme is generated. The new fuel ratio scheme is used to perform precise injection control of diesel and methanol.

[0073] For example, in a diesel and methanol dual fuel injection system, the precise ratio of the two fuels can be achieved through proportional integral differential control. For example, a heavy truck engine uses a transverse pump nozzle injector, the original diesel injection pressure is 160 MPa, the methanol injection pressure is 60 MPa, and the injection volume difference is about 0.04 ml per cycle under high-speed cruising conditions. The injection command is calculated through the proportional control link, the integral link eliminates the steady-state error, and the differential link improves the dynamic response performance.

[0074] The timer control tool uses a high-precision crystal oscillator with a clock frequency of 20 MHz, which can achieve microsecond injection phase control. For example, on a certain type of engineering machinery, the diesel injection advance angle is set to a 12-degree crankshaft angle, and the methanol injection is delayed by 1.5 milliseconds, forming a stepped injection sequence. This timing arrangement ensures that the diesel first forms a high-temperature ignition source, and then the methanol is injected and fully atomized.

[0075] Real-time monitoring uses optical sensors to detect the concentration distribution of mixed fuels. For example, on a bus engine, the mixture ratio threshold is set at 25%. When the mixture ratio exceeds the threshold, the control system automatically adjusts the injection phase difference. By increasing the phase difference to 2 milliseconds, the mixture ratio can be reduced to a safe range. At the same time, the combustion data fed back by the cylinder pressure sensor shows that the adjusted phase difference can maintain a stable combustion process.

[0076] When the injection amount needs to be recalculated, the control system will comprehensively consider factors such as engine speed and load. For example, when a certain agricultural machinery is harvesting, the frequent load fluctuations cause the mixture ratio to be unstable. The system stabilizes combustion by adjusting the diesel baseline injection amount. When the load suddenly increases by 30%, the diesel injection amount increases by 20%, while the methanol injection amount only increases by 10% to ensure reliable ignition. During the execution of the fuel ratio scheme, the control system can use an adaptive algorithm to dynamically optimize the injection parameters. For example, under low-speed and heavy-load conditions, the main engine of a fishing boat improves the combustion effect by adjusting the injection duration in real time. When the speed drops to one thousand revolutions per minute, the diesel injection pulse width is appropriately extended to 0.8 milliseconds, while the methanol injection amount is kept unchanged to avoid the production of an overly rich mixture. This precise control method not only improves fuel economy, but also significantly reduces emissions.

[0077] The above description is only a preferred embodiment of the present invention. Therefore, any equivalent changes or modifications made according to the structure, characteristics and principles described in the scope of the patent application of the present invention are included in the protection scope of the patent application of the present invention.

Claims

1. A fuel control method for a methanol-diesel dual-fuel engine, characterized in that: include: Get real-time data of engine speed, load and temperature; Input real-time data into the pre-established engine operating condition model and output the fuel demand characteristic parameters of the current operating condition; Input the fuel demand characteristic parameters into the pre-established injection ratio model, and output the injection ratio value of diesel and methanol; Generate a fuel injection plan of diesel and methanol based on the injection ratio value; According to the fuel injection scheme, a timing control algorithm is used to generate diesel injection instructions and methanol injection instructions with a time phase difference, and the mixing effect of diesel and methanol is monitored in real time.

2. The fuel control method of a methanol-diesel dual-fuel engine according to claim 1, characterized in that: The inputting of real-time data into a pre-established engine operating condition model and outputting fuel demand characteristic parameters of the current operating condition includes: inputting speed value, load value and temperature value into the engine operating condition model based on polynomial regression to obtain the fuel demand characteristic parameters of the current operating condition; If the fuel demand characteristic parameter is greater than a preset threshold, the relationship between the fuel demand characteristic parameter and the speed value, load value and temperature value is fitted by the least squares method to generate a corrected fuel demand characteristic parameter.

3. The fuel control method of a methanol-diesel dual-fuel engine according to claim 2, characterized in that: The speed value, load value and temperature value are input into the engine operating condition model based on polynomial regression to obtain the fuel demand characteristic parameters of the current operating condition, including: ； In the formula, represents the fuel demand characteristic parameter, n represents the engine speed value, L represents the load value, T represents the temperature value, β0 represents the constant term coefficient, and β1 to β6 represent the regression coefficients of each item.

4. The fuel control method for a methanol-diesel dual-fuel engine according to claim 2, characterized in that: The method of fitting the relationship between the fuel demand characteristic parameter and the speed value, the load value and the temperature value by the least square method to generate the corrected fuel demand characteristic parameter includes: ； In the formula, represents the fuel demand characteristic parameter, n represents the engine speed value, L represents the engine load value, T represents the engine temperature value, and k1, k2, k3 and k4 represent the coefficients to be fitted.

5. The fuel control method of a methanol-diesel dual-fuel engine according to claim 1, characterized in that: The step of inputting the fuel demand characteristic parameter into a pre-established injection ratio model and outputting the injection ratio value of diesel and methanol comprises: inputting the fuel demand characteristic parameter into a pre-established injection ratio model, wherein the injection ratio model is trained using a linear regression algorithm and the fuel demand characteristic parameter of the historical working condition of the engine; the training data comprises the injection ratio of diesel and methanol and the corresponding fuel demand characteristic parameter; The trained injection ratio model is used to predict the diesel and methanol injection ratio under the current working conditions; ； Where R represents the injection ratio of diesel and methanol, α1, α2 and α3 are regression coefficients, X1, X2 and X3 are fuel demand characteristic parameters, and θ is the bias constant.

6. The fuel control method for a methanol-diesel dual-fuel engine according to claim 5, characterized in that: Use the trained injection ratio model to predict the diesel and methanol injection ratio under current operating conditions, including: According to the prediction results, the model prediction error is calculated, where ； In the formula, E represents the model prediction error, n is the number of samples, and y i is the actual injection ratio value, is the injection ratio value predicted by the model.

7. The fuel control method for a methanol-diesel dual-fuel engine according to claim 1, characterized in that: The generating of the fuel injection scheme of diesel and methanol based on the injection ratio value includes: determining the power load parameter and the emission index parameter in combination with the diesel engine performance curve; According to the power load parameters and emission index parameters, the combustion efficiency coefficient of diesel and the critical mixing ratio threshold of methanol are calculated; The diesel combustion efficiency coefficient is calculated by using the thermal efficiency formula through the calculation of diesel combustion calorific value and the measurement of actual output power; According to the injection ratio value and the physical and chemical properties of methanol, the critical mixing ratio threshold of methanol is determined by using a flash point tester; Generate a target ratio range of methanol and diesel based on the injection ratio value, and determine the injection timing distribution in combination with the combustion efficiency coefficient; Determine whether the injection timing distribution exceeds the constraint of the critical mixture ratio threshold, and if so, adjust the boundary conditions of the target ratio range; A fuel double-pulse control map including injection quantity, phase difference and duration is generated according to the adjusted boundary conditions.

8. The fuel control method for a methanol-diesel dual-fuel engine according to claim 7, characterized in that: The thermal efficiency formula is used to calculate the diesel combustion efficiency coefficient, including: The thermal efficiency formula is , where η is the combustion efficiency coefficient, P is the actual output power, m d is the diesel quality, Q d is the calorific value of diesel.

9. The fuel control method for a methanol-diesel dual-fuel engine according to claim 7, characterized in that: The step of generating the fuel dual pulse control map comprises: According to the target ratio range and injection timing distribution, the injection quantity and phase difference at each time point are calculated to determine the duration of each injection pulse.

10. The fuel control method of a methanol-diesel dual-fuel engine according to claim 1, characterized in that: The method of using a timing control algorithm to generate a diesel injection instruction and a methanol injection instruction with a time phase difference includes: using a PID control algorithm to calculate the injection amount difference between the diesel and methanol according to the injection ratio value, and generating an initial injection instruction; According to the initial injection command and the fuel injection plan, a timer control tool is used to generate an injection command with a time difference.

Images