A long-term online prediction method for injection quantity in high-pressure fuel systems based on real-time training optimization of nuclear extreme learning machines

Abstract

The purpose of the present invention is to provide a long-term online prediction method for the injection quantity of a high-pressure fuel system based on real-time training optimization of a nuclear extreme learning machine, which belongs to the field of fuel injection. First, an injection quantity data set and an engine power data set are established, and a nuclear extreme learning machine V1 model is trained based on the injection quantity data set; then, the V1 model is used to predict the injection quantity according to different working conditions and supplemented to the power data set; the V2 model is trained based on the new power data set to optimize its power prediction capability. During the long-term operation of the engine, the rail pressure and injection pulse width are monitored in real time, the injection quantity is predicted online through the V1 model, and the power is predicted through the V2 model in combination with the real-time data; according to the deviation between the predicted power and the actual power, the injection pulse width is dynamically adjusted based on the MPC algorithm, the injection quantity data set is updated, and the V1 model is retrained in real time. The present invention can achieve high-precision long-term online prediction of injection quantity, has real-time training and optimization capabilities, and does not require downtime for retraining.

Description

Technical Field

[0001] The present invention relates to a fuel system control method, in particular to a fuel injection prediction method. Background Art

[0002] The dynamic injection stability of high-pressure fuel systems directly impacts engine performance, fuel economy, and emissions. A MAP charting the cyclic injection quantity as a function of pressure and injection pulse width is embedded in the electronic control system. This control strategy then adjusts the injection quantity based on the actual engine operating conditions using a lookup table. This strategy is adaptable to different engines. However, the actual operating environment of a multi-cylinder engine differs from the single-cylinder measurement environment used when creating the calibration chart. This leads to inconsistencies between the common rail pressure and the fuel pressure during the injector injection process, making it difficult to maintain a high degree of consistency between the actual injection quantity and the desired injection quantity.

[0003] Current model-based injection quantity control methods rely on an accurate injection quantity prediction model for precise control. While feature recognition-based or data-driven models have improved prediction accuracy to a certain extent, they also have significant limitations. These models typically rely on extensive historical data for training, which fails to account for future changes in system parameters. During long-term engine operation, engine conditions and environmental factors change. However, these models fail to account for the impact of changes in key structural and drive parameters on injection quantity caused by wear of system components and dimensional tolerances over time. This makes existing injection quantity prediction methods less than ideal for long-term prediction in practical applications. Summary of the Invention

[0004] The purpose of the present invention is to provide a long-term online prediction method for the injection quantity of a high-pressure fuel system based on real-time training optimization of a nuclear extreme learning machine, which can solve the problem that the performance of the engine changes after long-term operation, resulting in the inability to accurately predict the injection quantity online in real time.

[0005] The object of the present invention is achieved like this:

[0006] The present invention provides a long-term online prediction method for injection quantity of a high-pressure fuel system based on real-time training optimization of a nuclear extreme learning machine, which is characterized by comprising the following steps:

[0007] (1) Experiment on the injector: Use a single injection instrument to measure the injection volume of the injector under different working conditions, and establish an injection volume data set of rail pressure, injection pulse width, and injection volume; Experiment on the engine: Measure and record the rail pressure, injection pulse width, air-fuel ratio, intake pressure, intake temperature, and power under different working conditions, and establish an engine power data set;

[0008] (2) Using rail pressure and injection pulse width as input and injection quantity as output, a kernel extreme learning machine V1 model is constructed and the V1 model is trained based on the injection quantity dataset;

[0009] (3) Based on the rail pressure and injection pulse width conditions at different speeds and loads in the engine power data set, the kernel extreme learning machine V1 model is used to predict the injection amount, and the predicted injection amount is added to the engine power data set;

[0010] (4) Using injection quantity, air-fuel ratio, intake pressure, and intake temperature as inputs and power as output, a kernel extreme learning machine V2 model is constructed. The V2 model is trained based on the new engine power data set in step (3), and the model is optimized using a genetic algorithm.

[0011] (5) During engine operation, the injection quantity is predicted online by the V1 model based on the real-time rail pressure and injection pulse width of the current cycle. The power is predicted online by the V2 model based on the injection quantity predicted by the V1 model and the real-time air-fuel ratio, intake pressure, and intake temperature.

[0012] (6) According to the deviation between the predicted power and the actual power, the injection pulse width is adjusted based on the MPC algorithm until the deviation between the actual power and the predicted power is less than 5%. The adjusted injection pulse width is then recorded and updated in the injection quantity data set as the injection characteristic after component aging. The V1 model is then retrained in real time based on the updated injection quantity data set to obtain the kernel extreme learning machine V 1_new model, thereby realizing long-term online prediction of injection quantity.

[0013] The present invention may also include:

[0014] 1. The conditions of the injection quantity dataset and the engine power dataset in step (1) are specifically as follows:

[0015] In the injection quantity data set, the operating conditions include rail pressure conditions and injection pulse width conditions. The rail pressure conditions include all rail pressure conditions with an interval of 10 MPa between the idle rail pressure and the rated rail pressure. The injection pulse width conditions include all injection pulse width conditions with an interval of 0.1 ms between the minimum injection start pulse width and the rated pulse width.

[0016] In the engine power data set, the operating conditions include speed conditions and load conditions. The speed conditions include all speed conditions between idle and rated speed with an interval of 10% of the rated speed. The load conditions include all load conditions between no load and full load with an interval of 10%.

[0017] 2. The output functions of the kernel extreme learning machine V1 and V2 models are:

[0018]

[0019] Where x is the input matrix of rail pressure and injection pulse width, n is the dimension of the input matrix, I is the unit matrix, C is the regularization coefficient, β is the weight value between the hidden layer and the injection amount output matrix, and H is the output matrix of the hidden layer; g(x,x i ) is the Gaussian kernel function, expressed as:

[0020]

[0021] Where γ is the kernel parameter.

[0022] 3. The MPC algorithm in step (6) adjusts the injection pulse width as follows:

[0023] Calculate the predicted power P under the current cycle predict (t) and actual power P actual Deviation of (t):

[0024] P error (t) = P predict (t)-P actual (t)

[0025] Adjust the injection pulse width of the next cycle through feedback with dynamic characteristics:

[0026] W(t+1)=W(t)+λ1·P error (t)+λ2·∫P error (t)dt+λ3·(P error (t)-P error (t-1))

[0027] Where W(t) is the injection pulse width in the current cycle, and λ1, λ2, and λ3 are feedback adjustment coefficients.

[0028] The advantages of the present invention are:

[0029] (1) The present invention can train and optimize the injection quantity prediction model in real time based on the deviation between the predicted engine power and the real-time power, and realize high-precision long-term online prediction of the injection quantity of the high-pressure fuel system by continuously dynamically learning and updating the model parameters.

[0030] (2) Compared with the traditional injection quantity prediction model, the nuclear extreme learning machine prediction model constructed in the present invention has real-time training and optimization capabilities, and does not require the engine to be shut down to retrain the model, so that the high-pressure fuel system can respond to changes in injection quantity in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 is a flow chart of the present invention;

[0032] Figure 2Schematic diagram of the training and optimization process of the kernel extreme learning machine V2 model;

[0033] Figure 3 Schematic diagram of the real-time retraining process of the kernel extreme learning machine V1 model. DETAILED DESCRIPTION

[0034] The present invention will be described in more detail below with reference to the accompanying drawings:

[0035] Combine Figure 1-3 The present invention provides a long-term online prediction method for injection quantity of a high-pressure fuel system based on real-time training optimization of a nuclear extreme learning machine, comprising the following steps:

[0036] Step S1: Conducting an experiment on a high-pressure fuel system test bench, using a single injection instrument to measure the injection amount of the injector under different operating conditions, and establishing an injection amount data set for rail pressure, injection pulse width, and injection amount; conducting an experiment on an engine test bench, measuring and recording the rail pressure, injection pulse width, air-fuel ratio, intake pressure, intake temperature, and power under different operating conditions, and establishing an engine power data set;

[0037] Step S2: Using the rail pressure and injection pulse width as input and the injection amount as output, a core extreme learning machine V1 model is constructed, and the V1 model is trained based on the injection amount dataset;

[0038] Step S3: Based on the rail pressure and injection pulse width conditions at different speeds and loads in the engine power data set, the kernel extreme learning machine V1 model is used to predict the injection amount, and the predicted injection amount is added to the engine power data set;

[0039] In step S4, the injection amount, air-fuel ratio, intake pressure, and intake temperature are used as inputs and the power is used as output to construct the kernel extreme learning machine V2 model. The V2 model is trained based on the new engine power data set in step S3. The genetic algorithm is used to optimize the model, such as Figure 2 As shown;

[0040] Step S5: During engine operation, the injection quantity is predicted online using the V1 model based on the real-time rail pressure and injection pulse width of the current cycle, and the power is predicted online using the V2 model based on the injection quantity predicted by the V1 model and the real-time air-fuel ratio, intake pressure, and intake temperature.

[0041] Step S6, as Figure 3 As shown in Figure 1, according to the deviation between the predicted power and the actual power, the injection pulse width is adjusted based on the MPC algorithm until the deviation between the actual power and the predicted power is less than 5%. The adjusted injection pulse width is then recorded and updated in the injection quantity dataset as the injection characteristic after component aging. The V1 model is then retrained in real time based on the updated injection quantity dataset to obtain the kernel extreme learning machine V 1_newmodel, thereby realizing long-term online prediction of injection quantity.

[0042] The specific working conditions of the data set in step S1 are:

[0043] In the injection quantity data set, the operating conditions include rail pressure and injection pulse width. The rail pressure conditions include all rail pressure conditions with an interval of 10 MPa between the idle rail pressure and the rated rail pressure, and the injection pulse width conditions include all injection pulse width conditions with an interval of 0.1 ms between the minimum start pulse width and the rated pulse width.

[0044] In the engine power data set, the operating conditions include speed and load. The speed conditions include all speed conditions between idle and rated speed with an interval of 10% of the rated speed, and the load conditions include all load conditions between no load and full load with an interval of 10%.

[0045] The output functions of the kernel extreme learning machine V1 and V2 models are:

[0046]

[0047] Where x is the input matrix of rail pressure and injection pulse width, n is the dimension of the input matrix, I is the unit matrix, C is the regularization coefficient, β is the weight value between the hidden layer and the injection amount output matrix, and H is the output matrix of the hidden layer; g(x,x i ) is the Gaussian kernel function, expressed as:

[0048]

[0049] Where γ is the kernel parameter.

[0050] The MPC algorithm in step S6 adjusts the injection pulse width specifically as follows:

[0051] Calculate the predicted power P under the current cycle predict (t) and actual power P actual Deviation of (t):

[0052] P error (t) = P predict (t)-P actual (t) (3)

[0053] Adjust the injection pulse width of the next cycle through feedback with dynamic characteristics:

[0054] W(t+1)=W(t)+λ1·P error (t)+λ2·∫P error (t)dt+λ3·(P error (t)-P error (t-1)) (4)

[0055] Where W(t) is the injection pulse width in the current cycle, and λ1, λ2, and λ3 are feedback adjustment coefficients.

Claims

1. A long-term online prediction method for injection quantity in a high-pressure fuel system based on real-time training optimization of a nuclear extreme learning machine, characterized by: The following steps are involved: (1) Experiment on the injector: Use a single injection instrument to measure the injection volume of the injector under different working conditions, and establish an injection volume data set of rail pressure, injection pulse width, and injection volume; Experiment on the engine: Measure and record the rail pressure, injection pulse width, air-fuel ratio, intake pressure, intake temperature, and power under different working conditions, and establish an engine power data set; (2) Using rail pressure and injection pulse width as input and injection quantity as output, a kernel extreme learning machine V1 model is constructed and the V1 model is trained based on the injection quantity dataset; (3) Based on the rail pressure and injection pulse width conditions at different speeds and loads in the engine power data set, the kernel extreme learning machine V1 model is used to predict the injection amount, and the predicted injection amount is added to the engine power data set; (4) Using injection quantity, air-fuel ratio, intake pressure, and intake temperature as inputs and power as output, a kernel extreme learning machine V2 model is constructed. The V2 model is trained based on the new engine power data set in step (3), and the model is optimized using a genetic algorithm. (5) During engine operation, the injection quantity is predicted online by the V1 model based on the real-time rail pressure and injection pulse width of the current cycle. The power is predicted online by the V2 model based on the injection quantity predicted by the V1 model and the real-time air-fuel ratio, intake pressure, and intake temperature. (6) According to the deviation between the predicted power and the actual power, the injection pulse width is adjusted based on the MPC algorithm until the deviation between the actual power and the predicted power is less than 5%. The adjusted injection pulse width is then recorded and updated in the injection quantity data set as the injection characteristic after component aging. The V1 model is then retrained in real time based on the updated injection quantity data set to obtain the kernel extreme learning machine V 1_new model, thereby realizing long-term online prediction of injection quantity.

2. The method for long-term online prediction of injection quantity of a high-pressure fuel system based on real-time training optimization of a nuclear extreme learning machine according to claim 1 is characterized by: The conditions of the injection quantity dataset and the engine power dataset in step (1) are specifically as follows: In the injection quantity data set, the operating conditions include rail pressure conditions and injection pulse width conditions. The rail pressure conditions include all rail pressure conditions with an interval of 10 MPa between the idle rail pressure and the rated rail pressure. The injection pulse width conditions include all injection pulse width conditions with an interval of 0.1 ms between the minimum injection start pulse width and the rated pulse width. In the engine power data set, the operating conditions include speed conditions and load conditions. The speed conditions include all speed conditions between idle and rated speed with an interval of 10% of the rated speed. The load conditions include all load conditions between no load and full load with an interval of 10%.

3. The method for long-term online prediction of injection quantity of a high-pressure fuel system based on real-time training optimization of a nuclear extreme learning machine according to claim 1 is characterized by: The output functions of the kernel extreme learning machine V1 and V2 models are: Where x is the input matrix of rail pressure and injection pulse width, n is the dimension of the input matrix, I is the unit matrix, C is the regularization coefficient, β is the weight value between the hidden layer and the injection amount output matrix, and H is the output matrix of the hidden layer; g(x,x i ) is the Gaussian kernel function, expressed as: Where γ is the kernel parameter.

4. The method for long-term online prediction of injection quantity of a high-pressure fuel system based on real-time training optimization of a nuclear extreme learning machine according to claim 1 is characterized by: The MPC algorithm in step (6) adjusts the injection pulse width as follows: Calculate the predicted power P under the current cycle predict (t) and actual power P actual Deviation of (t): P error (t)=P predict (t)-P actual (t) Adjust the injection pulse width of the next cycle through feedback with dynamic characteristics: W(t+1)=W(t)+λ1·P error (t)+λ2·∫P error (t)dt+λ3·(P error (t)-P error (t-1)) Where W(t) is the injection pulse width in the current cycle, and λ1, λ2, and λ3 are feedback adjustment coefficients.

Images