Diesel oil-methanol mixed fuel engine control method and system

Abstract

The invention provides a diesel-methanol mixed fuel engine control method and system, and the method comprises the steps: obtaining real-time working condition data including the rotating speed, load and temperature parameters of an engine, and determining the optimal supply ratio of diesel to methanol under the current working condition according to the real-time working condition data in combination with a preset fuel characteristic difference model; calculating the concentration of the mixed gas of methanol and diesel oil according to the optimal supply proportion; and if the concentration of the mixed gas exceeds the preset threshold value, the injection pressure of methanol is adjusted, so that the concentration of the mixed gas returns to the target range. After the methanol injection frequency is increased, if the combustion rate is lower than the preset lower limit value, the injection direction of the methanol injector is adjusted, and the mixing uniformity is improved; and if the combustion rate is still lower than the preset lower limit value, the methanol injection opportunity is adjusted, methanol injection and diesel injection are optimally matched in time, it is ensured that the output power of the engine is stable, and meanwhile the aim of efficient and clean operation is achieved.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a diesel-methanol mixed fuel engine control method and system. Background Art

[0002] When using methanol as an alternative fuel, diesel engines need to accurately control the amount of methanol injected to achieve the best mixing ratio with diesel. However, there are significant differences between methanol and diesel in physical and chemical properties such as viscosity, surface tension, and vapor pressure, which brings difficulties to the calibration of given injection control. In addition, the combustion rate of methanol-air mixture is also different from that of diesel. Too high or too low concentration of the mixture will lead to problems such as unstable combustion and increased fuel consumption. At the same time, due to the low calorific value of methanol fuel, the engine will face the problem of reduced output power when using methanol. Therefore, it is necessary to design an injection system and combustion control algorithm for methanol characteristics, coordinate the supply ratio and injection timing of diesel and methanol fuels, and improve the engine's working efficiency while ensuring the smooth operation of the engine to compensate for the power loss caused by the low calorific value of methanol. This requires the injection system to be able to adjust the parameters such as the injection pressure, injection frequency, and injection direction of methanol in real time according to the engine operating conditions and fuel characteristics, improve the combustion process, maximize the substitution potential of methanol, and realize the efficient and clean operation of diesel-ethanol dual-fuel engines. Summary of the invention

[0003] The present invention provides a diesel-methanol mixed fuel engine control method, which mainly includes:

[0004] Acquire real-time operating data including engine speed, load and temperature parameters, and determine the optimal supply ratio of diesel and methanol under the current operating conditions based on the real-time operating data and the preset fuel characteristic difference model;

[0005] The concentration of the methanol-diesel mixture is calculated based on the optimal supply ratio; if the concentration of the mixture exceeds the preset threshold, the injection pressure of the methanol is adjusted to return the concentration of the mixture to the target range;

[0006] After the methanol injection pressure is adjusted, the preset combustion rate difference model is used to determine whether the current mixture combustion rate meets the engine's stable operation requirements. If the combustion rate is lower than the preset lower limit, the methanol injection frequency is increased to improve the mixture combustion rate.

[0007] After increasing the frequency of methanol injection, if the combustion rate is lower than the preset lower limit, the injection direction of the methanol injector is adjusted to improve mixing uniformity;

[0008] If the combustion rate is still below the preset lower limit, the timing of methanol injection is adjusted to achieve optimal timing coordination between methanol injection and diesel injection, ensuring stable engine output power while meeting the goal of efficient and clean operation.

[0009] The present invention provides a diesel-methanol mixed fuel engine control system, which mainly includes:

[0010] A real-time operating condition data acquisition module is used to acquire real-time operating condition data including engine speed, load and temperature parameters;

[0011] The fuel supply ratio calculation module is used to determine the optimal supply ratio of diesel and methanol under the current working conditions based on real-time working condition data and a preset fuel characteristic difference model;

[0012] The mixture concentration adjustment module is used to calculate the mixture concentration of methanol and diesel according to the optimal supply ratio; if the mixture concentration exceeds the preset threshold, the injection pressure of methanol is adjusted to make the mixture concentration return to the target range;

[0013] The combustion rate judgment module is used to judge whether the current mixed gas combustion rate meets the stable operation requirements of the engine through a preset combustion rate difference model after the methanol injection pressure is adjusted. If the combustion rate is lower than the preset lower limit, the methanol injection frequency is increased to improve the mixed gas combustion rate;

[0014] The injection parameter optimization module is used to adjust the injection direction of the methanol injector to improve the mixing uniformity if the combustion rate is lower than the preset lower limit after increasing the frequency of methanol injection; if the combustion rate is still lower than the preset lower limit, the timing of methanol injection is adjusted to achieve the best coordination between methanol injection and diesel injection in terms of time, ensuring stable engine output power while meeting the goal of efficient and clean operation.

[0015] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0016] The present invention discloses a control method for a diesel-methanol mixed fuel engine. The method dynamically adjusts the optimal supply ratio of diesel and methanol by real-time acquisition of engine operating condition data and combining with a preset fuel characteristic difference model. On this basis, the present invention accurately controls the concentration of the mixed gas and the combustion rate by adjusting parameters such as the methanol injection pressure, frequency, direction and timing to ensure stable and efficient operation of the engine. When the combustion rate is lower than the preset lower limit, the present invention can gradually optimize the methanol injection strategy, improve the mixing uniformity and form the best match with the diesel injection. This multi-dimensional, closed-loop control method can not only ensure the stability of the engine output power, but also achieve the goal of efficient and clean operation, providing effective technical support for the application of diesel-methanol dual-fuel engines. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 The present invention is a flow chart of a diesel-methanol mixed fuel engine control method.

[0018] Figure 2 It is a schematic diagram of a diesel-methanol mixed fuel engine control method and system of the present invention.

[0019] Figure 3 This is another schematic diagram of a diesel-methanol mixed fuel engine control method and system of the present invention.

[0020] Figure 4 The present invention is a structural schematic diagram of a diesel-methanol mixed fuel engine control method and system. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0022] like Figure 1-4 In this embodiment, a diesel-methanol mixed fuel engine control method and system may specifically include:

[0023] S101, acquiring real-time operating condition data including engine speed, load and temperature parameters, and determining the optimal supply ratio of diesel and methanol under the current operating condition based on the real-time operating condition data and a preset fuel characteristic difference model.

[0024] A database containing the difference of diesel and methanol fuel combustion characteristic parameters under different working conditions is obtained as the training data of the BP neural network model. At the same time, the real-time working condition parameters of the engine, including speed, load and intake volume, are obtained as the input of the model. Using the trained BP neural network model, a nonlinear mapping relationship between the real-time working condition parameters, fuel characteristic parameters and combustion efficiency is established, and a comprehensive index representing the combustion efficiency is output. The K-means clustering algorithm is used to divide the real-time working condition data points at different times into several typical working condition categories, and each typical working condition corresponds to a cluster center. The characteristic parameters of each cluster center are input into the BP neural network model to obtain the corresponding comprehensive index of combustion efficiency. For each typical working condition, the fuel mixing ratio is used as the optimization variable, and the genetic algorithm is used to search for the optimal mixing ratio that maximizes the comprehensive index of combustion efficiency. The fitness function of the genetic algorithm is the comprehensive index output by the BP neural network model, and the constraint condition is the value range of the mixing ratio. According to the optimal mixing ratio under each typical working condition searched by the genetic algorithm, a mapping relationship between the real-time working condition parameters and the optimal mixing ratio is established. In actual operation, the optimal mixing ratio of diesel and methanol is determined according to the real-time operating parameters of the engine, and the fuel mixing control instructions are output.

[0025] For example, the combustion characteristic parameters such as the ignition delay period, flame propagation speed, and calorific value of diesel and methanol under different working conditions can be obtained through bench tests. These data reflect the differences in the combustion behaviors of the two fuels under different conditions and provide a basis for subsequent modeling. Parameters such as speed and load can be obtained through the engine control unit (ECU), and the intake volume can be measured by a mass flow meter. These parameters jointly reflect the instantaneous operating state of the engine and are the key inputs of the model. In the process of establishing the BP neural network model, the operating condition parameters and fuel characteristic parameters can be used as input layer neurons, and the combustion efficiency index can be used as output layer neurons. The network weights are continuously adjusted through the back propagation algorithm, and a nonlinear mapping relationship is finally established. This method can effectively capture the characteristics of complex combustion processes. The application of the K-means clustering algorithm helps to simplify the optimization process. Assume that the real-time operating condition data is clustered into five categories, each representing a typical operating condition, such as idle, medium speed and low load, medium speed and high load, high speed and low load, and high speed and high load. This method can discretize the continuous operating condition space for subsequent optimization. Genetic algorithms have advantages in finding the optimal mixing ratio. The mixing ratio can be encoded as a chromosome, and the efficiency index output by the BP neural network is used as the fitness function. Through operations such as selection, crossover, and mutation, the optimal solution is obtained by evolution generation by generation. This method can quickly find the global optimal solution in a complex solution space. Finally, establishing the mapping relationship between the operating parameters and the optimal mixing ratio is the key to achieving real-time control. The fast mapping can be achieved by using a table lookup method or fitting a polynomial equation. In actual operation, the optimal mixing ratio is obtained by querying or calculating according to the current operating parameters, thereby achieving precise fuel ratio control. The technical effects of this method are mainly reflected in: First, an accurate model of the combustion process is established in a data-driven manner, overcoming the limitation that the traditional theoretical model is difficult to accurately describe the complex combustion process. Secondly, the intelligent optimization of the fuel ratio is realized by using a machine learning algorithm, which can better adapt to different working conditions compared to the traditional fixed ratio method. Finally, a real-time control strategy is adopted to keep the engine working in the best combustion state, which is conducive to improving fuel economy and reducing emissions.

[0026] S102, calculating the concentration of the mixed gas of methanol and diesel according to the optimal supply ratio; if the concentration of the mixed gas exceeds a preset threshold, adjusting the injection pressure of methanol to return the concentration of the mixed gas to the target range.

[0027] According to the stoichiometric equation, the optimal supply mass ratio of diesel and methanol is calculated, and the theoretical air-fuel ratio of the mixed fuel is determined accordingly. After the diesel and methanol are actually supplied, the actual concentration value of the mixed fuel is calculated according to the mass of the two. Through the system integration test, the concentration range required for safe and stable combustion under different working conditions is obtained, and it is set as the threshold range of concentration control. The actual concentration value of the mixed fuel is monitored in real time and compared with the preset threshold. If the concentration exceeds the threshold range, the adjustment mechanism of the methanol injection pressure is triggered. For different degrees of concentration over-limit, the response relationship curve between the methanol injection pressure and the fuel concentration is established in advance through experiments. According to the actual concentration over-limit, the corresponding target pressure value is obtained by looking up the table and used as the set value of the PID control algorithm. The PID controller uses the target pressure value as the set value and the actual pressure value as the feedback value. By adjusting the three parameters of proportion, integration and differentiation, the operation of the methanol injection device is controlled to realize the automatic adjustment of the injection pressure, and then the concentration of the mixed fuel is controlled within the threshold range. During the pressure adjustment process, the actual concentration value of the mixed fuel is continuously collected, compared with the target concentration value, and the concentration error is calculated. The concentration error is introduced into the PID controller to adaptively correct the control parameters, improve the adjustment accuracy and dynamic response speed. The concentration of the mixed fuel is continuously monitored for a long time, and the concentration change trend is predicted through time series analysis and other methods. When the predicted concentration value is at risk of exceeding the threshold range, the methanol injection pressure is fine-tuned in advance to avoid instability caused by rapid changes in concentration.

[0028] Exemplarily, the optimal supply mass ratio of diesel and methanol in a dual-fuel engine system is calculated based on a stoichiometric equation. For example, for a specific diesel and methanol mixed fuel, theoretical calculations may result in an optimal mass ratio of 7:3. This ratio takes into account the chemical composition and combustion characteristics of the two fuels, aiming to achieve optimal combustion efficiency and emission performance. According to this optimal mass ratio, the air-fuel ratio of diesel and methanol is multiplied by their respective ratio values ​​using a weighted average method to obtain the calculated air-fuel ratio of the mixed fuel. Assuming that the theoretical air-fuel ratio of pure diesel is 14.5:1 and the theoretical air-fuel ratio of pure methanol is 6.45:1, the theoretical air-fuel ratio of a 7:3 diesel-methanol mixed fuel is approximately 12.3:1. This value provides an important reference for subsequent fuel supply and air flow control. In actual operation, the system monitors the supply mass of diesel and methanol in real time and calculates the actual concentration value of the mixed fuel. For example, if the actual diesel and methanol mass ratio supplied is 6.8:3.2, which deviates slightly from the ideal ratio, the system will feed this information back to the control unit to prepare for subsequent adjustments. Through a large number of system integration tests, the concentration range required for safe and stable combustion under different working conditions can be obtained. For example, under low-speed and light-load conditions, the safe concentration range of the mixed fuel may be 28%-32% (expressed as the mass percentage of methanol); while under high-speed and heavy-load conditions, this range may be narrowed to 29%-31%. These data are set as the threshold range for concentration control to provide a basis for real-time control. The real-time monitoring system continuously tracks the actual concentration value of the mixed fuel and compares it with the preset threshold. When the concentration is detected to exceed the threshold range, the system triggers the adjustment mechanism of the methanol injection pressure. For example, if the mixed gas concentration of the mixed fuel increases to 33% under medium-speed and medium-load conditions, exceeding the preset upper limit of 32%, the system will start the adjustment process. In order to accurately control the methanol injection pressure, a response curve of the methanol injection pressure and fuel concentration can be established through a large number of tests. This curve may show that under certain conditions, reducing the methanol injection pressure from 8MPa to 7.5MPa can reduce the mass percentage of methanol in the mixed fuel from 33% to 31%. The system will obtain the corresponding target pressure value by looking up the table according to the actual concentration exceeding the limit. The PID controller uses this target pressure value as the set value and the actual pressure value as the feedback value, and controls the operation of the methanol injection device by adjusting the three parameters of proportion, integration, and differentiation. For example, if the initial P, I, and D parameters are 0.5, 0.3, and 0.1, respectively, the controller may dynamically adjust these parameters according to the size and change trend of the pressure error to achieve faster response speed and smaller steady-state error. During the pressure regulation process, the system will continuously collect the actual concentration value of the mixed fuel, compare it with the target concentration value, and calculate the concentration error. This error information is fed back to the PID controller for adaptive correction of control parameters.For example, if the concentration adjustment speed is found to be too slow, the system may increase the proportional coefficient; if concentration oscillation occurs, the differential coefficient may be reduced. By continuously monitoring the concentration of the mixed fuel for a long time, the system can use time series analysis methods to predict the concentration change trend. For example, if the concentration is observed to have a slow upward trend in the past 15 seconds and it is predicted that it may exceed the upper threshold in 30 seconds, the system will pre-start the fine-tuning of the methanol injection pressure and reduce the pressure by 0.1MPa to prevent combustion instability caused by a sharp change in concentration.

[0029] S103. After the methanol injection pressure is adjusted, a preset combustion rate difference model is used to determine whether the current mixture combustion rate meets the engine stable operation requirements. If the combustion rate is lower than the preset lower limit, the methanol injection frequency is increased to improve the mixture combustion rate.

[0030] According to the ANSYS Fluent numerical simulation software, a fuel combustion model under different methanol injection pressures and injection frequencies was established, and a series of theoretical combustion rate data were calculated. Using the multivariate linear regression analysis method, the injection pressure and frequency were taken as independent variables, and the combustion rate was taken as the dependent variable. The quantitative relationship expression between them was fitted to form a mapping relationship table between injection parameters and combustion rate. A methanol injection device was installed on the engine bench, and different engine speed and load conditions were designed. By adjusting the injection device, the methanol injection frequency was gradually reduced until the engine showed obvious working instability. The combustion rate at this time was recorded as the lower limit of the combustion rate required for stable operation of the engine under this condition. Multiple operating points were tested to obtain a query table for the lower limit of the engine combustion rate. During the operation of the engine, the ECU collected operating parameters such as engine speed, torque, and intake volume in real time. According to the current speed and load, two-dimensional interpolation was performed in the combustion rate lower limit query table to obtain the lower limit of the combustion rate required for stable operation of the engine under the current operating conditions. The oxygen sensor monitors the actual combustion rate of the mixed fuel in real time, compares it with the lower limit of the combustion rate obtained by looking up the table, and calculates the difference between the actual value and the lower limit. If the difference is negative, it means that the actual combustion rate is lower than the lower limit, and the methanol injection frequency adjustment mechanism needs to be triggered. According to the size of the combustion rate difference, interpolation query is performed in the mapping relationship table between injection parameters and combustion rate to obtain the methanol injection frequency correction amount that needs to be adjusted. For example, if the difference is -10%, the frequency needs to be increased by 2Hz. Add the frequency correction amount to the current injection frequency to obtain the corrected target injection frequency. Then, according to the flow characteristic curve of the electronically controlled injector, calculate the opening and closing time parameters of the injector at the target frequency. Generate a PWM pulse width modulation control instruction and send it to the control unit of the methanol injection device through the CAN bus to adjust the opening and closing time of the injector to achieve dynamic adjustment of the methanol injection frequency, so that the actual combustion rate meets the requirements of stable operation of the engine and ensures the high efficiency of mixed fuel combustion.

[0031] For example, numerical simulation is an important means to optimize the performance of dual-fuel engines. Using ANSYS Fluent software, the fuel combustion process under different methanol injection parameters can be simulated. For example, in one study, the combustion conditions when the injection pressure changed from 5MPa to 10MPa and the injection frequency changed from 10Hz to 50Hz were simulated. Through these simulations, a series of theoretical combustion rate data were obtained, laying the foundation for subsequent analysis. The multivariate linear regression analysis method was used to establish the relationship between injection parameters and combustion rate. Taking a certain study as an example, with injection pressure and frequency as independent variables and combustion rate as dependent variable, the following relationship was fitted: combustion rate = 0.5×injection pressure + 0.3×injection frequency + 2.1. This expression intuitively reflects the degree of influence of injection parameters on combustion rate and provides a theoretical basis for actual control. Engine bench test is a key step in verifying the theoretical model. In one experiment, the researchers gradually reduced the methanol injection frequency under the conditions of 1500rpm and 50% load. When the frequency dropped to 15Hz, the engine showed an unstable working phenomenon with a torque drop of 20%, and the corresponding combustion rate was 25g / s. This value is recorded as the lower limit of the combustion rate under this condition. By conducting similar tests at multiple operating points, a comprehensive combustion rate lower limit query table is finally formed. The core of the real-time control system is to accurately judge the current operating conditions and make corresponding adjustments. For example, when the engine is running at 2000rpm and 75% load, the ECU obtains the lower limit of the combustion rate under this condition by looking up the table as 30g / s. At the same time, the oxygen sensor detects that the actual combustion rate is 27g / s, which is 3g / s lower than the lower limit. The system then triggers the adjustment mechanism and determines that the methanol injection frequency needs to be increased by 2Hz according to the mapping relationship table between injection parameters and combustion rate. Accurate control of the electronically controlled injector is the key to achieving combustion optimization. Assuming that the current injection frequency is 20Hz, it needs to be increased to 22Hz according to the above calculation. By consulting the injector flow characteristic curve, it is determined that at a frequency of 22Hz, the opening time of the injector in each injection cycle should be 2.5ms. Based on this, the control system generates corresponding PWM control instructions and sends them to the injection device through the CAN bus to achieve accurate adjustment of the methanol injection frequency. This control strategy based on model prediction and real-time feedback can effectively ensure the combustion efficiency of the mixed fuel, improve the overall performance of the engine, reduce fuel consumption, and reduce harmful emissions.

[0032] S104. After increasing the frequency of methanol injection, if the combustion rate is lower than a preset lower limit, the injection direction of the methanol injector is adjusted to improve mixing uniformity.

[0033] ANSYS Fluent software was used to establish a three-dimensional model of the engine combustion chamber under different injection directions and divide the structured grid. On the basis of the grid, the finite volume method was used to discretize the control equations, and the realizable k-ε turbulence model was used to calculate the transport equations of turbulent kinetic energy k and turbulent dissipation rate ε, and solve the velocity, pressure and temperature distribution of the mixture in the combustion chamber. The mixture uniformity index UI was introduced, which was defined as the standard deviation of the mixture equivalence ratio in each grid unit, where the equivalence ratio represents the ratio of the actual air-fuel ratio to the stoichiometric ratio. The quadratic polynomial was selected as the regression model, and a quantitative relationship expression with the injection direction as the independent variable and UI as the dependent variable was established to obtain the "injection direction-UI" quadratic polynomial regression model; the goodness of fit was judged by the root mean square error and the determination coefficient R². A fast-response flame ionization current sensor was installed on the engine test bench. Its basic working principle is that charged particles will be generated in the high-temperature flame, which can form a weak ionization current between the electrodes, and the current signal can characterize the change process of the flame. The ignition process of the mixture under different injection directions is collected by an oscilloscope; the ignition delay period is defined as the time interval from the start of fuel injection to the detection of the flame signal by the ionization current sensor. The maximum ignition delay period when the engine is running stably is tested, and a two-dimensional query table of "injection direction-critical ignition delay period" is established. The ECU collects operating parameters such as engine speed, torque, and intake volume in real time through the CAN bus. A simplified engine mean model is used as the state space model of the Kalman filter, in which the state equation is the first-order inertia link of the engine speed and torque, and the observation equation is a linear combination of speed and torque. The speed and torque signals are filtered. Combined with the "injection direction-critical ignition delay period" query table established by pre-calibration, the theoretical optimal injection direction is determined by looking up the table under the current working conditions. A wide-range oxygen sensor is installed on the exhaust pipe to monitor the exhaust oxygen concentration in real time, and the actual equivalent ratio of the mixture is calculated by the concentration-equivalence ratio conversion formula obtained by pre-calibration. The deviation between the actual equivalence ratio and the target value is compared. If the deviation exceeds the preset threshold, it is considered that the uniformity of the mixture does not meet the standard. Query the quadratic polynomial regression model of "injection direction-UI" established by fitting, and calculate the correction amount of injection direction. Generate the injector angle adjustment instruction and send it to the injector drive control unit through the CAN bus. Ensure that the mixture reaches the ideal uniformity, improve the combustion process, and improve the engine combustion efficiency.

[0034] For example, the optimization of dual-fuel engines involves multiple aspects, among which the uniformity of the mixture and the combustion efficiency are key factors. ANSYS Fluent software plays an important role in this process. By establishing a three-dimensional model and meshing, it can simulate the internal conditions of the combustion chamber under different injection directions. For example, in a study, the distribution of the mixture when the injection angle changes from 0° to 60° was simulated. By calculating the velocity, pressure and temperature distribution, a series of theoretical data were obtained, laying the foundation for subsequent analysis. The introduction of the mixture uniformity index UI provides the possibility for quantitative analysis. In practical applications, it may be found that when the injection angle is 30°, the UI value reaches the minimum, indicating that the mixture distribution is the most uniform at this time. By establishing a quadratic polynomial regression model, an expression similar to UI=0.02θ²-1.2θ+18 can be obtained, where θ represents the injection angle. This model not only intuitively reflects the relationship between the injection direction and the uniformity of the mixture, but also provides a theoretical basis for real-time control. In a bench test, researchers may observe that when the injection angle increases from 15° to 45°, the ignition delay period decreases from 2.5ms to 1.8ms. This relationship is recorded as a lookup table to provide a reference for subsequent real-time control. For example, under the condition of 2000rpm and 75% load, the system may look up the table to obtain the optimal injection angle of 35°, and the corresponding critical ignition delay period is 2.0ms. The application of Kalman filter in signal processing reflects the advanced nature of the control system. Assume that in a certain test, the original speed signal fluctuates around 1800rpm, and the filtered signal stabilizes at 1805rpm. This smoothing process helps to improve the accuracy of working condition judgment and lays the foundation for subsequent injection control. The use of wide-range oxygen sensor reflects the importance of closed-loop control. For example, the system may detect that the oxygen concentration in the exhaust gas is 5%, which is converted to an equivalence ratio of 0.9, which is 10% different from the target value of 1.0. At this time, the control system will calculate the need to adjust the injection angle by 2° to improve the mixing uniformity based on the "injection direction-UI" model. Finally, the correction command is sent to the injector drive unit through the CAN bus to achieve precise control. This fine adjustment ensures the ideal uniformity of the mixture, thereby improving combustion efficiency and reducing emissions.

[0035] S105. If the combustion rate is still lower than the preset lower limit, the timing of methanol injection is adjusted to achieve the best coordination between methanol injection and diesel injection in terms of time, thereby ensuring stable engine output power and meeting the goal of efficient and clean operation.

[0036] The engine speed and torque signals are collected in real time, and the collected data are curve fitted using the least squares method to obtain a smooth speed and torque curve. According to the fitted curve, the theoretical combustion rate under the current working condition is obtained by querying the engine performance map. The in-cylinder pressure is measured by a pressure sensor, and the pressure signal is fast Fourier transformed to extract the frequency domain characteristics of the pressure signal. According to the fundamental component amplitude A and the in-cylinder pressure peak P_max in the frequency domain characteristics, the actual combustion rate r_actual is calculated according to the formula r_actual=k·A / P_max, where k is the calibration coefficient. The actual combustion rate is compared with the theoretical value. If the actual value is lower than 90% of the theoretical value, it is determined that the combustion rate is low. In the case of a low combustion rate, the pre-calibrated "methanol injection time-combustion rate" two-dimensional query table is read from the ECU memory, and the current speed and torque are used as indexes. The optimal methanol injection time t_opt required to increase the combustion rate to the theoretical value is calculated by the bilinear interpolation method. According to the engine crankshaft position sensor signal, the crankshaft angle θ_opt corresponding to the optimal methanol injection time t_opt is determined. The crankshaft angle is used as the pulse center of the injector drive signal, and the pulse width w and duty cycle d are adjusted to make the start time t_start and duration t_dur of methanol injection meet: t_start=θ_opt-w·d / 2, t_dur=w·d. The control command (t_start, t_dur) is sent to the injector drive module through the CAN bus to accurately control the methanol injection process. A diesel-methanol injection time synergy model based on a feedforward neural network is established, with engine speed n, torque T, and combustion rate r as inputs, and the injection time interval Δt of the two fuels as output. The hidden layer is set to 2 layers, and the number of nodes in each layer is 10 and 5 respectively. The sample pairs (n, T, r, Δt) are selected from the historical operating condition database, and the network parameters are trained using the Levenberg-Marquardt algorithm. The trained neural network model is called online, and Δt is dynamically adjusted to form the best mixing distribution of the mixed fuel in the combustion chamber to ensure a smooth and fast combustion rate.

[0037] For example, real-time acquisition of engine speed and torque signals is the basis for optimization control. Least squares fitting can filter out noise and obtain a smooth curve. For example, the original speed data fluctuates around 2000rpm, and a stable 2005rpm curve is obtained after fitting, providing a reliable basis for subsequent analysis. The engine performance map is an important reference tool. By querying the map, the theoretical combustion rate under specific working conditions can be obtained. For example, under the working conditions of 2005rpm and 200Nm, the map shows that the theoretical combustion rate is 15m / s. This benchmark value provides a reference for subsequent judgment. The pressure sensor measures the in-cylinder pressure, and the fast Fourier transform reveals the frequency domain characteristics of the pressure signal. The fundamental component amplitude A reflects the intensity of combustion, while the in-cylinder pressure peak P_max represents the limit of the combustion process. The actual combustion rate can be estimated by the formula r_actual=k·A / P_max. Assuming that A=500kPa, P_max=8000kPa, and the calibration coefficient k=0.2 are measured, r_actual=12.5m / s is calculated. By comparing the actual combustion rate with the theoretical value, the combustion condition can be judged. In this example, the actual value of 12.5m / s is lower than 90% of the theoretical value of 15m / s, indicating that the combustion rate is low and needs to be adjusted. This comparison method can detect combustion anomalies in time and provide a basis for adjusting the control strategy. The two-dimensional query table of "methanol injection timing-combustion rate" established by pre-calibration is an efficient optimization tool. Through bilinear interpolation, the best injection time can be quickly found. For example, under the current working conditions, the best injection time t_opt is obtained by looking up the table as -15°CA ATDC (i.e., 15° crankshaft angle before top dead center). The choice of this time directly affects the combustion efficiency and emission performance. The crankshaft position sensor signal is used to accurately locate the injection time. Converting t_opt into the crankshaft angle θ_opt, and then adjusting the pulse center, width and duty cycle of the injector drive signal accordingly, can achieve precise fuel injection control. For example, if the pulse width w = 30°CA and the duty cycle d = 0.6, the injection start time t_start = -24°CA ATDC and the duration t_dur = 18°CA can be calculated. The introduction of the neural network model reflects the intelligence of the control strategy. Taking the engine speed, torque and combustion rate as input, the injection time interval of the two fuels is output, which can achieve more refined fuel coordination control. For example, the model may output that the optimal injection time interval Δt is 2.5ms under the conditions of 2005rpm, 200Nm, and 12.5m / s. This dynamic adjustment ensures the optimal distribution of the mixed fuel in the combustion chamber, which helps to improve combustion efficiency and reduce emissions.

[0038] The present invention provides a diesel-methanol mixed fuel engine control system, which mainly includes:

[0039] A real-time operating condition data acquisition module is used to acquire real-time operating condition data including engine speed, load and temperature parameters;

[0040] The fuel supply ratio calculation module is used to determine the optimal supply ratio of diesel and methanol under the current working conditions based on real-time working condition data and a preset fuel characteristic difference model;

[0041] The mixed gas concentration adjustment module is used to calculate the mixed gas concentration of methanol and diesel according to the optimal supply ratio; if the mixed gas concentration exceeds the preset threshold, the injection pressure of methanol is adjusted to make the mixed gas concentration return to the target range. ;

[0042] The combustion rate judgment module is used to judge whether the current mixed gas combustion rate meets the stable operation requirements of the engine through a preset combustion rate difference model after the methanol injection pressure is adjusted. If the combustion rate is lower than the preset lower limit, the methanol injection frequency is increased to improve the mixed gas combustion rate;

[0043] The injection parameter optimization module is used to adjust the injection direction of the methanol injector to improve the mixing uniformity if the combustion rate is lower than the preset lower limit after increasing the frequency of methanol injection; if the combustion rate is still lower than the preset lower limit, the timing of methanol injection is adjusted to achieve the best coordination between methanol injection and diesel injection in terms of time, ensuring stable engine output power while meeting the goal of efficient and clean operation.

[0044] Although the present invention has been described in detail above by general description and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made to the present invention. Therefore, these modifications or improvements made without departing from the spirit of the present invention all belong to the scope of protection claimed by the present invention.

Claims

1. A diesel-methanol mixed fuel engine control method, characterized in that: The method comprises: Acquire real-time operating data including engine speed, load and temperature parameters, and determine the optimal supply ratio of diesel and methanol under the current operating conditions based on the real-time operating data and the preset fuel characteristic difference model; According to the optimal supply ratio, the concentration of the methanol-diesel mixture is calculated; if the concentration of the mixture exceeds the preset threshold, the injection pressure of methanol is adjusted to return the concentration of the mixture to the target range. ; After the methanol injection pressure is adjusted, the preset combustion rate difference model is used to determine whether the current mixture combustion rate meets the engine's stable operation requirements. If the combustion rate is lower than the preset lower limit, the methanol injection frequency is increased to improve the mixture combustion rate. After increasing the frequency of methanol injection, if the combustion rate is lower than the preset lower limit, the injection direction of the methanol injector is adjusted to improve mixing uniformity; If the combustion rate is still below the preset lower limit, the timing of methanol injection is adjusted to achieve optimal timing coordination between methanol injection and diesel injection, ensuring stable engine output power while meeting the goal of efficient and clean operation.

2. The method according to claim 1, characterized in that The acquiring of real-time operating data including engine speed, load and temperature parameters, and determining the optimal supply ratio of diesel to methanol under the current operating conditions according to the real-time operating data and in combination with a preset fuel property difference model, comprises: Obtaining a difference database containing combustion characteristic parameters of diesel and methanol fuels under different working conditions, the difference database is used as training data for the BP neural network model; Obtaining the real-time operating parameters of the engine, including speed, load and intake volume, as inputs to the BP neural network model; Using the trained BP neural network model, a nonlinear mapping relationship between real-time operating parameters, fuel characteristic parameters and combustion efficiency is established, and a comprehensive index representing combustion efficiency is output; The K-means clustering algorithm is used to divide the real-time working condition data points at different times into several typical working condition categories, and each typical working condition corresponds to a cluster center; The characteristic parameters of each cluster center are input into the BP neural network model to obtain the corresponding comprehensive index of combustion efficiency; For each typical working condition, the fuel mixture ratio is used as the optimization variable, and the genetic algorithm is used to search for the optimal mixture ratio that maximizes the comprehensive index of combustion efficiency. The fitness function of the genetic algorithm is the comprehensive index output by the BP neural network model, and the constraint condition is the value range of the mixture ratio. According to the optimal mixing ratio under each typical working condition obtained by searching with the genetic algorithm, a mapping relationship between the real-time working condition parameters and the optimal mixing ratio is established; In actual operation, the optimal mixing ratio of diesel and methanol is determined according to the real-time operating parameters of the engine, and the fuel mixing control instructions are output.

3. The method according to claim 1, characterized in that The method of calculating the concentration of the mixed gas of methanol and diesel according to the optimal supply ratio; if the concentration of the mixed gas exceeds a preset threshold, adjusting the injection pressure of methanol to return the concentration of the mixed gas to a target range includes: Obtaining a stoichiometric equation of diesel and methanol, calculating an optimal supply mass ratio of diesel and methanol according to the stoichiometric equation, and determining a theoretical air-fuel ratio of the mixed fuel based on the optimal supply mass ratio; Monitor the actual supply quality of diesel and methanol in real time, and calculate the actual concentration value of the mixed fuel based on the actual supply quality; Obtain the concentration range required for safe and stable combustion under different working conditions obtained in advance through system integration tests, and set the concentration range as the threshold range for concentration control; Determine whether the actual concentration value exceeds the threshold range, and if so, trigger the adjustment mechanism of the methanol injection pressure; Obtain a response relationship curve between methanol injection pressure and fuel concentration established in advance through experiments, and obtain a corresponding target pressure value by looking up a table according to the excess of the actual concentration value; The target pressure value is used as the set value of the PID control algorithm, and the actual pressure value is used as the feedback value. The operation of the methanol injection device is controlled by adjusting the proportional, integral and differential parameters of the PID controller to achieve automatic adjustment of the injection pressure. During the pressure regulation process, the actual concentration value of the mixed fuel is continuously collected, the concentration error between the actual concentration value and the target concentration value is calculated, and the concentration error is introduced into the PID controller for adaptive correction of the control parameters; The mixed fuel concentration is monitored continuously for a long time, and the concentration change trend is predicted through time series analysis. When the predicted concentration value is at risk of exceeding the threshold range, the methanol injection pressure is fine-tuned in advance to avoid instability caused by rapid changes in concentration.

4. The method according to claim 1, characterized in that: After the methanol injection pressure is adjusted, a preset combustion rate difference model is used to determine whether the current mixed gas combustion rate meets the engine stable operation requirement. If the combustion rate is lower than the preset lower limit, the methanol injection frequency is increased to improve the mixed gas combustion rate, including: Obtaining a pre-established mapping relationship table of fuel injection parameters and combustion rate, wherein the mapping relationship table includes multiple sets of fuel injection pressure, injection frequency and corresponding theoretical combustion rate data; Obtaining a pre-tested engine combustion rate lower limit value query table, the query table containing combustion rate lower limit value data under multiple engine speed and load conditions; Obtain the current speed and load parameters of the engine, perform two-dimensional interpolation in the query table, and obtain the lower limit of the combustion rate required for stable operation of the engine under the current working conditions; Obtaining an actual combustion rate of the mixed fuel, comparing the actual combustion rate with a lower limit value, and calculating a difference between the actual value and the lower limit value; If the difference is less than zero, an interpolation query is performed in the mapping relationship table to obtain the fuel injection frequency correction amount that needs to be adjusted; Determine the corrected target injection frequency according to the frequency correction amount and the current injection frequency; According to the target injection frequency, the corresponding injector opening and closing time parameters are determined, and a PWM control instruction is generated and sent to the fuel injection device through the CAN bus to adjust the injector opening and closing time, thereby realizing dynamic adjustment of the fuel injection frequency and making the actual combustion rate meet the requirements of stable engine operation.

5. The method according to claim 1, characterized in that After the methanol injection frequency is increased, if the combustion rate is lower than a preset lower limit, the injection direction of the methanol injector is adjusted to improve the mixing uniformity, including: Obtain the speed and torque signals of the engine under the current working condition, use a simplified engine mean model as the state space model of the Kalman filter, and perform filtering and estimation on the speed and torque signals; According to the estimated values ​​of the speed and torque of the engine under the current working condition, the theoretical optimal injection direction under the current working condition is determined by searching in a pre-calibrated two-dimensional query table of "injection direction-critical ignition delay period"; Obtain the exhaust oxygen concentration signal monitored in real time by the wide-band oxygen sensor installed on the exhaust pipe, and calculate the actual equivalent ratio of the current mixed gas according to the pre-calibrated concentration-equivalent ratio conversion formula; If the deviation between the actual equivalence ratio and the target equivalence ratio exceeds a preset threshold, the correction amount of the injection direction is calculated in the pre-fitted "injection direction-mixture uniformity" quadratic polynomial regression model; According to the injection direction correction amount, an injector angle adjustment instruction is generated and sent to the injector drive control unit through the CAN bus to adjust the injection direction of the injector to ensure that the mixture reaches the ideal uniformity.

6. The method according to claim 1, characterized in that If the combustion rate is still lower than the preset lower limit, the timing of methanol injection is adjusted to achieve the best coordination between methanol injection and diesel injection in terms of time, thereby ensuring stable engine output power and meeting the goal of efficient and clean operation, including: Obtain engine speed and torque signals, use the least square method to perform curve fitting on the speed and torque signals, and obtain smooth speed curves and torque curves; According to the smooth speed curve and torque curve, the theoretical combustion rate under the current working condition is obtained by querying the pre-established engine performance map; Acquire the in-cylinder pressure signal, perform fast Fourier transform on the in-cylinder pressure signal, and extract the frequency domain characteristics of the in-cylinder pressure signal; According to the amplitude of the fundamental component in the frequency domain characteristics and the peak value of the in-cylinder pressure, the actual combustion rate is calculated according to a preset formula; Determining whether the actual burning rate is lower than a preset percentage threshold of the theoretical burning rate, and if so, determining that the burning rate is low; When it is determined that the combustion rate is too low, the optimal methanol injection time required to increase the combustion rate to the theoretical value is calculated by bilinear interpolation method from the pre-calibrated two-dimensional query table of "methanol injection time-combustion rate" with the current speed and torque as indexes; Obtain the engine crankshaft position sensor signal and determine the target crankshaft angle corresponding to the optimal methanol injection time; According to the target crankshaft angle, the pulse parameters of the injector drive signal are adjusted to control the start time and duration of methanol injection; Send the methanol injection control command to the injector drive module through the bus to accurately control the methanol injection process; Obtain historical operating data samples and use machine learning algorithm training to establish a diesel-methanol injection time coordination model based on a feedforward neural network; The collaborative model is called online, with engine speed, torque and combustion rate as input, to dynamically adjust the injection time interval of the two fuels so that the mixed fuel forms the best mixing distribution and ensures a smooth and fast combustion rate.

7. A diesel-methanol mixed fuel engine control system, characterized in that: The system comprises: A real-time operating condition data acquisition module is used to acquire real-time operating condition data including engine speed, load and temperature parameters; The fuel supply ratio calculation module is used to determine the optimal supply ratio of diesel and methanol under the current working conditions based on real-time working condition data and a preset fuel characteristic difference model; The mixed gas concentration adjustment module is used to calculate the mixed gas concentration of methanol and diesel according to the optimal supply ratio; if the mixed gas concentration exceeds the preset threshold, the injection pressure of methanol is adjusted to make the mixed gas concentration return to the target range. ; The combustion rate judgment module is used to judge whether the current mixed gas combustion rate meets the stable operation requirements of the engine through a preset combustion rate difference model after the methanol injection pressure is adjusted. If the combustion rate is lower than the preset lower limit, the methanol injection frequency is increased to improve the mixed gas combustion rate; The injection parameter optimization module is used to adjust the injection direction of the methanol injector to improve the mixing uniformity if the combustion rate is lower than the preset lower limit after increasing the frequency of methanol injection; if the combustion rate is still lower than the preset lower limit, the timing of methanol injection is adjusted to achieve the best coordination between methanol injection and diesel injection in terms of time, ensuring stable engine output power while meeting the goal of efficient and clean operation.

Images