A dual-mode PID real-time correction method for injector injection quantity based on virtual prediction of pressure fluctuations

Abstract

The purpose of this invention is to provide a dual-mode PID real-time correction method for injector injection quantity based on virtual prediction of pressure fluctuations, belonging to the field of engine engineering. First, pressure sensors are installed at 1 / 4 and 3 / 4 of the high-pressure pipeline to measure the injector's return flow rate. An ARIMA model is constructed to virtually predict pressure fluctuations at 3 / 4, effectively replacing the sensors, and a support vector machine model is used to predict the return flow rate. Subsequently, a flow model of the high-pressure pipeline is constructed, and the total fuel flow rate exiting the high-pressure pipeline is calculated by combining the real-time measured pressure at 1 / 4 and the virtual predicted pressure at 3 / 4. By subtracting this from the predicted return flow rate, the actual injection quantity of the injector is obtained. Based on the deviation between the actual and target injection quantities, a dual-mode PID method is proposed to correct the injection pulse width in real time, thereby achieving closed-loop control of the injection quantity. This invention utilizes virtual prediction to avoid the complexity and cost of multiple sensors, and improves prediction accuracy under complex operating conditions through a dual-model prediction approach.

Description

Technical Field

[0001] The present invention relates to an engine injection device, specifically an injector control method. Background Technology

[0002] Common rail fuel injection technology is a key technology in internal combustion engines, widely used in dual-fuel and low-carbon fuel engines. With the development of engine technology, especially in high-power marine engines, the requirements for precise control of fuel injection are becoming increasingly stringent. Traditional fuel injection system control methods mostly rely on open-loop control or use closed-loop control based on feedback variables such as engine speed.

[0003] In modern high-pressure fuel systems, traditional control methods struggle to provide sufficient accuracy and rapid response under complex operating conditions due to issues such as nonlinear pressure fluctuations, fluid dynamics within the pipeline, and injector response delays during the injection process. Particularly in ultra-high-pressure injection environments, these dynamic factors make controlling the injection quantity even more difficult, leading to uneven injection across cylinders and consequently affecting overall engine performance and emissions. Summary of the Invention

[0004] The purpose of this invention is to provide a dual-mode PID real-time correction method for injector injection quantity based on pressure fluctuation virtual prediction, which can solve the problems of inaccurate real-time online prediction of injection quantity and accurate closed-loop control of injection quantity.

[0005] The objective of this invention is achieved as follows:

[0006] This invention discloses a dual-mode PID real-time correction method for injector injection quantity based on virtual prediction of pressure fluctuations, characterized by the following steps:

[0007] (1) Connect the common rail and the injector through a high-pressure pipeline. Install pressure sensors at 1 / 4 and 3 / 4 of the high-pressure pipeline respectively. Under different injection conditions, measure the fuel pressure fluctuation at the two points. At the same time, use a flow meter to measure the backflow of the injector. After obtaining the pressure fluctuation data set and the backflow data set, remove the pressure sensor at 3 / 4 of the high-pressure pipeline.

[0008] (2) Construct an automatic regression integral moving average (ARIMA) pressure fluctuation prediction model with pressure fluctuation at 1 / 4 as input and pressure fluctuation at 3 / 4 as output. Parameter identification is performed based on the pressure fluctuation dataset. The ARIMA pressure fluctuation prediction model performs virtual prediction of pressure fluctuation at 3 / 4 of the high-pressure pipeline during actual operation of the high-pressure fuel system. Construct a support vector machine (SVM) return flow prediction model with injection conditions as input and return flow as output. Train the model based on the return flow dataset.

[0009] (3) Establish a high-pressure pipeline flow model based on the pressure fluctuation transmission relationship at 1 / 4 and 3 / 4 of the high-pressure pipeline. The pressure signal at 1 / 4 of the high-pressure pipeline measured in actual measurement and the pressure at 3 / 4 predicted in real time by the ARIMA pressure fluctuation prediction model are used as inputs to the high-pressure pipeline flow model. The flow rate of the high-pressure pipeline is calculated, and the amount of fuel flowing out of the high-pressure pipeline is obtained by integration. This amount is used as the sum of the injector injection amount and the return flow.

[0010] (4) The return flow rate is calculated based on the injection conditions in each cycle. The actual injection quantity of the injector is obtained by subtracting the fuel quantity from the outflow high-pressure pipeline. Based on the deviation between the actual injection quantity and the target injection quantity, the injection pulse width of the next cycle is corrected by dual-mode PID to achieve closed-loop control of the injection quantity.

[0011] The present invention may also include:

[0012] 1. The operating conditions in step (1) include rail pressure conditions and injection pulse width conditions. The rail pressure conditions include all rail pressure conditions with an interval of 10MPa 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 0.1ms between the minimum injection pulse width and the rated pulse width.

[0013] 2. The specific method for constructing the ARIMA pressure fluctuation prediction model in step (2) is as follows: the autoregressive part, the differencing part, and the moving average part of the ARIMA model are constructed sequentially:

[0014] (21) Constructing the autoregressive component:

[0015] φ(B)=1-φ1B-φ2B 2 -…-φ p B p

[0016] In the formula, φ i B is the autoregressive coefficient in the autoregressive part; B is the lag operator, defined as... p is the order of the autoregressive term;

[0017] (22) Construct the differential part and use the second-order difference to process the pressure fluctuation:

[0018]

[0019] In the formula, P 1 / 4 (t) and P 3 / 4 (t) represents the time series data of the pressure fluctuation at 1 / 4 and the pressure fluctuation at 1 / 4, respectively;

[0020] (23) Constructing the moving average component:

[0021] θ(B)=1+θ1B+θ2B2 +…+θ p B q

[0022] In the formula, θ i is the moving average coefficient in the autoregressive part, and q is the order of the moving average term;

[0023] (24) Couple the various parts of the model to construct the ARIMA model:

[0024]

[0025] In the formula, ε t This is the white noise error term; β i The effect of the pressure fluctuation time series at the 1 / 4 position on the pressure fluctuation at the 3 / 4 position is specifically represented by β. i = (β1,β2,…β) m ), where m is the maximum order of lag in the input sequence under consideration;

[0026] (25) Model coefficients φ are calculated based on the maximum likelihood estimation method. i θ i and β i The identification of these features enables the model to predict pressure fluctuations at 3 / 4 of the distance.

[0027]

[0028] 3. The specific method for constructing the high-pressure pipeline flow model in step (3) is as follows:

[0029] Establish the momentum balance equation within the high-pressure pipeline:

[0030]

[0031] In the formula, ρ is the fuel density, u is the flow rate, P is the pressure, D is the pipe diameter, and γ is the wall shear stress.

[0032] Integrating the distance L between the 1 / 4 and 3 / 4 points, and then multiplying by the pipe cross-sectional area A, yields the mass flow rate out of the high-pressure pipe:

[0033]

[0034] In the formula, ξ is a constant related to the speed of sound, and t is time;

[0035] The fuel mass of high-pressure pipelines is expressed as follows:

[0036] M pipe-out =∫Q pipe-out dt.

[0037] 4. The method for real-time correction of injection quantity by dual-mode PID in step (4) is as follows:

[0038] Based on the current deviation between the actual injection volume and the target injection volume, the dual-mode PID switches between coarse-tuning mode and fine-tuning mode to calculate the injection pulse width correction:

[0039]

[0040] In the formula, Δu(k) is the pulse width correction for the k-th injection, e(k) is the deviation between the actual injection amount and the target injection amount for the k-th injection, and e # It is the error threshold. These are the correction coefficients in coarse adjustment mode. It is the correction factor in fine-tuning mode;

[0041] The dual-mode PID controller outputs the control signal for the k-th injection based on the calculated injection pulse width correction.

[0042] u(k)=u(k-1)+Δu(k).

[0043] The advantages of this invention are:

[0044] (1) The present invention only requires the installation of a pressure sensor in the high-pressure pipeline, and can virtually predict the pressure fluctuation at the other end based on the measured pressure fluctuation, thus avoiding the complexity and cost of adding extra sensors in actual working conditions.

[0045] (2) The present invention calculates the injection quantity in real time by the difference between the predicted total fuel quantity and the return flow rate. This dual-model prediction method improves the prediction accuracy of the injection quantity under complex working conditions.

[0046] (3) The dual-mode PID of the present invention can automatically adjust the control correction amount of the injection pulse width according to the injector error threshold, quickly respond to complex dynamic working condition changes, and improve the follow-up response speed of the system control. Attached Figure Description

[0047] Figure 1 This is a flowchart of the present invention;

[0048] Figure 2 A diagram of the experimental setup used to obtain the dataset;

[0049] Figure 3 This is a block diagram of a dual-mode PID control system. Detailed Implementation

[0050] The invention will now be described in more detail with reference to the accompanying drawings:

[0051] Combination Figure 1-3 The present invention discloses a dual-mode PID real-time correction method for injector injection quantity based on virtual prediction of pressure fluctuations, comprising the following steps:

[0052] Step S1, the experimental setup is arranged as follows: Figure 2 As shown, pressure sensors are installed at 1 / 4 and 3 / 4 of the high-pressure line between the common rail and the injector. Under different injection conditions, the fuel pressure fluctuations at these two locations are measured, and the return flow rate of the injector is measured simultaneously using a flow meter. After obtaining the pressure fluctuation data set and the return flow rate data set, the pressure sensor at 3 / 4 of the high-pressure line is removed.

[0053] Step S2: Construct an Automatic Regression Integral Moving Average (ARIMA) pressure fluctuation prediction model with pressure fluctuation at 1 / 4 as input and pressure fluctuation at 3 / 4 as output. Parameter identification is performed based on the pressure fluctuation dataset. The ARIMA pressure fluctuation prediction model is used for virtual prediction of pressure fluctuation at 3 / 4 of the high-pressure pipeline during actual operation of the high-pressure fuel system. Construct a support vector machine return flow prediction model with injection conditions as input and return flow as output, and train it based on the return flow dataset.

[0054] Step S3: Based on the Euler partial differential equations of generalized mass and momentum, establish a high-pressure pipeline flow model based on the pressure fluctuation transmission relationship at 1 / 4 and 3 / 4 of the high-pressure pipeline. Use the actual measured pressure signal at 1 / 4 of the high-pressure pipeline and the pressure at 3 / 4 predicted in real time by the ARIMA pressure fluctuation prediction model as inputs to the high-pressure pipeline flow model to calculate the flow rate of the high-pressure pipeline. Then, obtain the amount of fuel flowing out of the high-pressure pipeline through integration, and use it as the sum of the injector injection rate and return flow rate.

[0055] Step S4: Based on the support vector machine return flow prediction model, the return flow is calculated according to the injection conditions in each cycle. The actual injection quantity of the injector is obtained by subtracting the fuel quantity flowing out of the high-pressure pipeline. Based on the deviation between the actual injection quantity and the target injection quantity, the injection pulse width for the next cycle is corrected using a dual-mode PID controller to achieve closed-loop control of the injection quantity. Figure 3 As shown.

[0056] The specific working conditions of the dataset in step S1 are as follows:

[0057] Operating conditions include rail pressure and injection pulse width. Rail pressure conditions include all rail pressure conditions with an interval of 10 MPa between idle rail pressure and rated rail pressure. Injection pulse width conditions include all injection pulse width conditions with an interval of 0.1 ms between minimum injection pulse width and rated pulse width.

[0058] The specific steps in step S2 for constructing the ARIMA pressure fluctuation prediction model are as follows:

[0059] The three main components of the ARIMA model—autoregressive, differencing, and moving average—are constructed sequentially:

[0060] Step (a) constructs the autoregressive component, represented as:

[0061] φ(B)=1-φ1B-φ2B 2 -…-φ p B p (1)

[0062] In the formula, φ i B is the autoregressive coefficient in the autoregressive part, describing the relationship between the current pressure fluctuation value and the pressure fluctuation values ​​at the previous i time points; B is the lag operator, defined as... p is the order of the autoregressive term.

[0063] Step (b) involves constructing the difference component to eliminate non-stationarity in the time series. Second-order differencing is used to process pressure fluctuations.

[0064]

[0065] In the formula, P 1 / 4 (t) and P 3 / 4 (t) represents the time series data of the pressure fluctuations at 1 / 4 and 1 / 4, respectively.

[0066] Step (c) constructs the moving average portion, represented as:

[0067] θ(B)=1+θ1B+θ2B 2 +…+θ p B q (3)

[0068] In the formula, θ i is the moving average coefficient in the autoregressive part, describing the relationship between the current pressure fluctuation value and the pressure fluctuation error at the previous i time points, and q is the order of the moving average term;

[0069] Step (d): Couple the various parts of the model to construct the ARIMA model:

[0070]

[0071] In the formula, ε t This is the white noise error term; β i The effect of the pressure fluctuation time series at the 1 / 4 position on the pressure fluctuation at the 3 / 4 position is specifically represented by β. i = (β1,β2,…β) m ), where m is the maximum order of lag in the input sequence under consideration.

[0072] Step (e) involves performing model coefficient φ based on the maximum likelihood estimation method. i θ i and β iThe identification of these features enables the model to predict pressure fluctuations at 3 / 4 of the distance.

[0073]

[0074] The specific steps in step S3 for constructing the high-pressure pipeline flow model are as follows:

[0075] Establish the momentum balance equation within the high-pressure pipeline:

[0076]

[0077] In the formula, ρ is the fuel density, u is the flow rate, P is the pressure, D is the pipe diameter, and γ is the wall shear stress.

[0078] Integrating the distance L between the 1 / 4 and 3 / 4 points, and then multiplying by the pipe cross-sectional area A, yields the mass flow rate out of the high-pressure pipe:

[0079]

[0080] In the formula, ξ is a constant related to the speed of sound, and t is time.

[0081] The fuel mass of high-pressure pipelines is expressed as follows:

[0082] M pipe-out =∫Q pipe-out dt (8)

[0083] The real-time correction of the injection quantity by the dual-mode PID in step S4 is as follows:

[0084] Based on the current deviation between the actual injection quantity and the target injection quantity, the dual-mode PID switches between coarse-tuning mode and fine-tuning mode to calculate the injection pulse width correction amount. The specific formula is as follows:

[0085]

[0086] In the formula, Δu(k) is the pulse width correction for the k-th injection, e(k) is the deviation between the actual injection amount and the target injection amount for the k-th injection, and e # It is the error threshold. These are the correction coefficients in coarse adjustment mode. It is the correction factor in fine-tuning mode.

[0087] The dual-mode PID controller outputs the control signal for the k-th injection based on the calculated injection pulse width correction.

[0088] u(k)=u(k-1)+Δu(k) (10).

Claims

1. A dual-mode PID real-time correction method for injector injection quantity based on virtual prediction of pressure fluctuations, characterized in that: Includes the following steps: (1) Connect the common rail and the injector through a high-pressure pipeline. Install pressure sensors at 1 / 4 and 3 / 4 of the high-pressure pipeline respectively. Under different injection conditions, measure the fuel pressure fluctuation at the two points. At the same time, use a flow meter to measure the backflow of the injector. After obtaining the pressure fluctuation data set and the backflow data set, remove the pressure sensor at 3 / 4 of the high-pressure pipeline. (2) Construct an automatic regression integral moving average (ARIMA) pressure fluctuation prediction model with pressure fluctuation at 1 / 4 as input and pressure fluctuation at 3 / 4 as output. Based on the pressure fluctuation dataset, the parameters are identified. The ARIMA pressure fluctuation prediction model performs virtual prediction of pressure fluctuation at 3 / 4 of the high-pressure pipeline during actual operation of the high-pressure fuel system. A support vector machine backflow prediction model is constructed with injection conditions as input and backflow as output, and trained based on the backflow dataset; (3) Establish a high-pressure pipeline flow model based on the pressure fluctuation transmission relationship at 1 / 4 and 3 / 4 of the high-pressure pipeline. The pressure signal at 1 / 4 of the high-pressure pipeline measured in actual measurement and the pressure at 3 / 4 predicted in real time by the ARIMA pressure fluctuation prediction model are used as inputs to the high-pressure pipeline flow model. The flow rate of the high-pressure pipeline is calculated, and the amount of fuel flowing out of the high-pressure pipeline is obtained by integration. This amount is used as the sum of the injector injection amount and the return flow. (4) The return flow rate is calculated based on the injection conditions in each cycle. The actual injection quantity of the injector is obtained by subtracting the fuel quantity from the outflow high-pressure pipeline. Based on the deviation between the actual injection quantity and the target injection quantity, the injection pulse width of the next cycle is corrected by dual-mode PID to achieve closed-loop control of the injection quantity.

2. The dual-mode PID real-time correction method for injector injection quantity based on virtual prediction of pressure fluctuations according to claim 1, characterized in that: The operating conditions in step (1) 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 pulse width and the rated pulse width.

3. The dual-mode PID real-time correction method for injector injection quantity based on virtual prediction of pressure fluctuations according to claim 1, characterized in that: The specific method for constructing the ARIMA pressure fluctuation prediction model in step (2) is as follows: the autoregressive part, the differencing part, and the moving average part of the ARIMA model are constructed sequentially: (21) Constructing the autoregressive component: φ(B)=1-φ1B-φ2B 2 -…-f p B p In the formula, φ i B is the autoregressive coefficient in the autoregressive part; B is the lag operator, defined as... p is the order of the autoregressive term; (22) Construct the differential part and use the second-order difference to process the pressure fluctuation: In the formula, P 1 / 4 (t) and P 3 / 4 (t) represents the time series data of the pressure fluctuation at 1 / 4 and the pressure fluctuation at 1 / 4, respectively; (23) Constructing the moving average component: θ(B)=1+θ1B+θ2B 2 +…+θ p B q In the formula, θ i is the moving average coefficient in the autoregressive part, and q is the order of the moving average term; (24) Couple the various parts of the model to construct the ARIMA model: In the formula, ε t This is the white noise error term; β i The effect of the pressure fluctuation time series at the 1 / 4 position on the pressure fluctuation at the 3 / 4 position is specifically represented by β. i = (β1,β2,…β) m ), where m is the maximum order of lag in the input sequence under consideration; (25) Model coefficients φ are calculated based on the maximum likelihood estimation method. i θ i and β i The identification of these features enables the model to predict pressure fluctuations at 3 / 4 of the distance.

4. The dual-mode PID real-time correction method for injector injection quantity based on virtual prediction of pressure fluctuations according to claim 1, characterized in that: The specific method for constructing the high-pressure pipeline flow model in step (3) is as follows: Establish the momentum balance equation within the high-pressure pipeline: In the formula, ρ is the fuel density, u is the flow rate, P is the pressure, D is the pipe diameter, and γ is the wall shear stress. Integrating the distance L between the 1 / 4 and 3 / 4 points, and then multiplying by the pipe cross-sectional area A, yields the mass flow rate out of the high-pressure pipe: In the formula, ξ is a constant related to the speed of sound, and t is time; The fuel mass of high-pressure pipelines is expressed as follows: M pipe-out =∫Q pipe-out dt。 5. The dual-mode PID real-time correction method for injector injection quantity based on virtual prediction of pressure fluctuations according to claim 1, characterized in that: The method for real-time correction of injection quantity by dual-mode PID in step (4) is as follows: Based on the current deviation between the actual injection volume and the target injection volume, the dual-mode PID switches between coarse-tuning mode and fine-tuning mode to calculate the injection pulse width correction: In the formula, Δu(k) is the pulse width correction for the k-th injection, e(k) is the deviation between the actual injection amount and the target injection amount for the k-th injection, and e # It is the error threshold. These are the correction coefficients in coarse adjustment mode. It is the correction factor in fine-tuning mode; The dual-mode PID controller outputs the control signal for the k-th injection based on the calculated injection pulse width correction. u(k)=u(k-1)+Δu(k).

Images