JP5321606B2 - Fuel injection control device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To highly accurately control an injection state by using an injection ratio parameter corresponding to the current environmental condition, while preventing an increase in learning processing load of the injection ratio parameter. <P>SOLUTION: This fuel injection control device includes a calculating means 31 for calculating an injection ratio parameter based on a detecting value of a fuel pressure sensor, a leaning means 32 for learning the injection ratio parameter, and a setting means 33 for setting an injection command signal based on the learnt injection ratio parameter. Correlation models MTh, MInt and MP(&theta;) expressing a correlation with an environmental value such as the fuel temperature Th, a fuel interval Int and cylinder internal pressure P(&theta;) and the injection ratio parameter, are stored in a memory. The injection ratio parameter (a detecting parameter) calculated by the calculating means 31 is converted into an injection ratio parameter (a reference parameter) corresponding to a reference environmental value, based on the correlation model and the current environmental value, and is learnt by the learning means 32. <P>COPYRIGHT: (C)2012,JPO&amp;INPIT

Description

  The present invention relates to a fuel injection control device that controls an injection state of fuel used for combustion of an internal combustion engine.

  A conventional fuel injection control apparatus controls a fuel injection start timing and an injection amount by outputting an injection command signal for instructing a valve opening timing and an injection period of the fuel injection valve. However, there is a delay time from when the start of injection is commanded to when the injection actually starts, and there is a difference between the commanded injection amount and the actual injection amount. Therefore, eigenvalues (injection rate parameters) such as these delay times and deviations are acquired and stored in advance by a test, and the desired injection start timing and injection amount are referenced with reference to the stored injection rate parameters. An injection command signal is set so that

  However, the injection rate parameter changes due to deterioration over time. Therefore, the present applicant is equipped with a fuel pressure sensor that detects the fuel pressure in the downstream portion of the common rail, and obtains the injection rate change (injection rate waveform) by detecting the pressure change (fuel pressure waveform) caused by fuel injection. A technique for detecting the injection rate parameter described above from the acquired injection rate waveform has been proposed (see Patent Documents 1, 2, 3, etc.). According to these techniques, since it is possible to detect and learn the injection rate parameter that changes due to aging, the injection state can be controlled with high accuracy so that the desired injection start timing and injection amount are obtained. Incidentally, specific examples of the injection rate parameter include an injection start delay time Td, an injection end delay time Te, an injection rate increase gradient Rα, an injection rate decrease gradient Rβ, a maximum injection rate Rmax, and the like illustrated in FIG.

JP 2008-144749 JP 2009-74535 A JP 2010-223185 A

  However, the injection rate parameter varies depending on the environmental conditions at that time, such as the fuel temperature at the time of injection, the in-cylinder pressure, the supercharging pressure, the EGR amount, and the injection interval at the time of multistage injection. Therefore, if the injection rate parameter is learned by ignoring these environmental conditions, when the environmental condition suddenly changes, the injection rate is changed during the transition period until learning of the injection rate parameter according to the environmental condition after the sudden change is completed. The state cannot be controlled with high accuracy.

  However, on the other hand, if the injection rate parameter is learned in association with all these environmental conditions, the storage capacity of the memory required for learning becomes enormous and the learning processing load increases.

  The present invention has been made to solve the above-described problems, and its purpose is to meet the current environmental conditions while suppressing an increase in storage capacity and learning processing load required for learning the injection rate parameter. An object of the present invention is to provide a fuel injection control device that can control an injection state with high accuracy using an injection rate parameter.

  Hereinafter, means for solving the above-described problems and the operation and effects thereof will be described.

In the first invention, the fuel injection valve for injecting the fuel accumulated in the pressure accumulating vessel, and the fuel passage from the discharge port of the pressure accumulating vessel to the injection hole of the fuel injection valve, the fuel in the fuel passage A fuel pressure sensor for detecting pressure, and a fuel pressure waveform detecting means for detecting a change in fuel pressure caused by injection as a fuel pressure waveform based on a detection value of the fuel pressure sensor; Based on the fuel pressure waveform, an injection rate parameter calculating means for calculating an injection rate parameter required for specifying an injection rate waveform corresponding to the fuel pressure waveform, an injection rate parameter learning means for learning the calculated injection rate parameter, An injection that sets an injection command signal corresponding to a requested injection state based on the learned injection rate parameter and outputs the set injection command signal to the fuel injection valve It assumes that comprise a decree signal setting means.

  Then, a correlation model storage unit that stores a correlation model representing a correlation between the environmental value that changes the value of the injection rate parameter and the injection rate parameter when the value changes, and the injection rate parameter calculation unit Reference environment conversion means for converting the calculated injection rate parameter into an injection rate parameter corresponding to a reference environment value based on the current environment value and the correlation model, and the injection rate parameter learning means includes the reference The injection rate parameter converted by the environment conversion means is learned.

  Here, it is clear from the test conducted by the inventors that the correlation between the injection rate parameter and the environmental value can be estimated. For example, the higher the fuel temperature (environment value), the longer the injection start delay time Td (injection rate parameter) due to the lower viscosity of the fuel (see FIG. 7A). Further, the injection start delay time Td (injection rate parameter) periodically changes according to a predetermined rule in accordance with the change in the injection interval (environmental value) at the time of multi-stage injection (see FIGS. 8A1 and 8A2).

  In the above invention in view of this point, a correlation model representing the correlation between the injection rate parameter and the environmental value is stored in advance. Then, the injection rate parameter (detection parameter) calculated based on the detected fuel pressure waveform is converted into an injection rate parameter (reference parameter) corresponding to the reference environment value based on the current environment value and correlation model, and learning is performed.

  According to this, since the injection rate parameter corresponding to the reference environmental value is converted and learned, the increase in the storage capacity required for learning is suppressed compared to the case where the injection rate parameter is learned in association with the environmental value each time. And increase in learning processing load can be suppressed.

  Further, in view of the difference between the current environmental value and the reference environmental value, if the injection command signal is set based on the learned injection rate parameter, the injection command signal is set (expected setting) according to the current environmental value. be able to. Therefore, when the environmental value suddenly changes, the injection command signal suitable for the environmental value after the sudden change can be set without waiting for the completion of learning of the injection rate parameter corresponding to the environmental value after the sudden change. . Therefore, the injection state can be controlled with high accuracy even during a transition period in which the environmental value changes suddenly.

According to a second aspect of the invention, there is provided current environment conversion means for converting the injection rate parameter learned by the injection rate parameter learning means into an injection rate parameter corresponding to the current environment value based on the current environment value and the correlation model. The injection command signal setting means sets an injection command signal corresponding to the required injection state based on the injection rate parameter converted by the current environment conversion means.

  According to this, the injection rate parameter (reference parameter) learned by conversion so as to correspond to the reference environmental value is converted into the injection rate parameter (current parameter) corresponding to the current environmental value, Since the injection command signal is set based on this, the injection command signal can be set according to the current environmental value.

  Moreover, since the correlation model used in the current environment conversion means and the correlation model used in the reference environment conversion means are made common, the conversion accuracy from the reference parameter to the current parameter can be improved, and the correlation model used in both conversion means As compared with the case of using different models, the storage capacity required for the correlation model can be reduced.

According to a third aspect of the present invention, a fuel injection valve that injects fuel accumulated in the pressure accumulating vessel and a fuel passage from the discharge port of the pressure accumulating vessel to the injection hole of the fuel injection valve, the fuel in the fuel passage A fuel pressure sensor for detecting pressure, and a fuel pressure waveform detecting means for detecting a change in fuel pressure caused by injection as a fuel pressure waveform based on a detection value of the fuel pressure sensor; Based on the fuel pressure waveform, an injection rate parameter calculating means for calculating an injection rate parameter required for specifying an injection rate waveform corresponding to the fuel pressure waveform, an injection rate parameter learning means for learning the calculated injection rate parameter, An injection that sets an injection command signal corresponding to a requested injection state based on the learned injection rate parameter and outputs the set injection command signal to the fuel injection valve It assumes that comprise a decree signal setting means.

  Then, a correlation model storage unit that stores a correlation model representing a correlation between the environmental value that changes the value of the injection rate parameter and the injection rate parameter when the value changes, and the injection rate parameter learning unit A current environment conversion means for converting the learned injection rate parameter into an injection rate parameter corresponding to the current environment value based on the current environment value and the correlation model, the injection command signal setting means, An injection command signal corresponding to the required injection state is set based on the injection rate parameter converted by the current environment conversion means.

  Here, as described above, it is possible to estimate the correlation between the injection rate parameter and the environmental value. In the above-mentioned invention in view of this point, a correlation model that represents the correlation between the injection rate parameter and the environmental value is previously set. Remember. Then, the learned injection rate parameter is converted into an injection rate parameter (current parameter) corresponding to the current environmental value based on the current environmental value and the correlation model, and the required injection state based on the injection rate parameter thus converted The injection command signal corresponding to is set. Therefore, when the environmental value suddenly changes, the injection command signal suitable for the environmental value after the sudden change can be set without waiting for the completion of learning of the injection rate parameter corresponding to the environmental value after the sudden change. . Therefore, the injection state can be controlled with high accuracy even during a transition period in which the environmental value changes suddenly.

  In addition, it is unnecessary to learn the injection rate parameter in association with the environmental value in each case, and if the injection rate parameter corresponding to the reference environmental value is learned, the injection command signal is set according to the current environmental value. Therefore, it is possible to suppress an increase in storage capacity required for learning and to suppress an increase in learning processing load as compared with the case where the injection rate parameter is learned in association with the environmental value.

In the fourth aspect of the invention, the fuel generated after the end of the injection from the detected fuel pressure waveform when the interval between the injections is the environmental value when performing the multistage injection in which the fuel injection is performed a plurality of times per one combustion cycle. A pulsation waveform extraction means for extracting a pulsation waveform representing a pressure pulsation, a correlation learning value calculation means for calculating a learning value of the correlation model based on the extracted pulsation waveform, and the correlation learning value calculation means calculated by the correlation learning value calculation means Correlation model learning means for learning the correlation model based on a learning value.

  Here, when performing multi-stage injection, the value of the injection rate parameter fluctuates due to the influence of fuel pressure fluctuation (particularly fuel pressure pulsation that occurs after the end of injection) caused by the previous stage of injection. And because the fluctuation in fuel pressure applied to the pre-stage injection is a pulsation that decays while repeating rise and fall, if the interval between injections changes, the value of the injection rate parameter also decays while repeating rise and fall. It became clear by the test conducted by the present inventor that the pulsation occurred. For example, the injection start delay time Td (injection rate parameter) and the injection end delay time Te (injection rate parameter) pulsate according to the interval as shown in FIG. The inventor found that there is a correlation between the pulsation waveform of the injection rate parameter corresponding to the interval and the fuel pressure pulsation waveform generated after the end of injection. This means that if a pulsation waveform is extracted from the detected fuel pressure waveform, the pulsation waveform of the injection rate parameter can be calculated from the extracted pulsation waveform, and thus the learning value of the correlation model can be calculated.

  In the above invention in view of this point, the pulsation waveform is extracted from the detected fuel pressure waveform, the learning value of the correlation model is calculated based on the extracted pulsation waveform, and the correlation model is learned based on the calculated learning value. Even if the actual correlation (correlation model) between the environmental value and the injection rate parameter changes due to the above, the actual correlation can be learned. Therefore, since the correlation model can be made highly accurate, the conversion accuracy of the conversion by the reference environment conversion means or the conversion by the current environment conversion means can be improved, and as a result, the injection state can be controlled with higher accuracy.

In a fifth aspect of the invention, the correlation model storage means stores a correlation between the environmental value and the injection rate parameter in association with a supply pressure that is a pressure of fuel supplied from the pressure accumulating container to the fuel injection valve. The correlation model learning means learns the correlation model in association with the supply pressure.

  By the way, as described above, the correlation between the injection rate parameter and the environmental value can be estimated, but the supply pressure has a different correlation with the injection rate parameter depending on the state of deterioration of the fuel injection valve. Therefore, the correlation between the injection rate parameter and the supply pressure is difficult to estimate, and it is difficult to create and store a correlation model by setting the supply pressure as an environmental value. For example, the injection rate parameter and the supply pressure are different depending on whether the nozzle hole area of the fuel injection valve is worn and the nozzle hole area is large, or when the nozzle hole area is small due to foreign matter adhering to the nozzle hole. This is because the correlation with is different.

  In the above-described invention focusing on this point, the correlation model representing the correlation between the environmental value and the injection rate parameter is used as a model associated with the supply pressure, and the correlation model is learned in association with the supply pressure. It is possible to learn from a correlation model that takes into account the correlation between the injection rate parameter corresponding to the state and the supply pressure. Therefore, the accuracy of the correlation model can be improved.

In a sixth aspect of the invention, the injection rate parameter learning means learns the injection rate parameter in association with a supply pressure that is a pressure of fuel supplied from the pressure accumulating container to the fuel injection valve.

  As described above, the correlation between the injection rate parameter and the supply pressure is difficult to estimate, and it is difficult to create and store a correlation model by setting the supply pressure as an environmental value. That is, it is difficult to store the supply pressure as a correlation model and to convert the supply pressure by the reference environment conversion unit or the current environment conversion unit.

  In the above-described invention focusing on this point, when the injection rate parameter learning unit learns the injection rate parameter, the injection rate parameter is learned in association with the supply pressure, so that the correlation with the supply pressure corresponding to the aging deterioration state is taken into account. The learned injection rate parameter can be learned. Therefore, the accuracy of the injection rate parameter can be improved.

It is a figure showing the outline of the fuel injection system to which the fuel injection control device concerning a 1st embodiment of the present invention is applied. It is a figure which shows the change of the injection rate, fuel pressure, and differential value corresponding to an injection command signal. It is a block diagram which shows the outline | summary of the learning of the injection rate parameter concerning 1st Embodiment, the setting of an injection command signal, etc. FIG. It is a flowchart which shows the calculation procedure of the injection rate parameter concerning 1st Embodiment. It is a figure which shows the fuel pressure waveform Wa at the time of injection, the fuel pressure waveform Wu at the time of non-injection, and the injection waveform Wb. 5 is a flowchart illustrating a procedure for learning by converting a detection parameter into a reference parameter in the first embodiment. FIG. 4 is a correlation map MTh used for the conversion means of FIG. 3 between a fuel temperature (environmental value) and an injection rate parameter. It is a test result which this inventor implemented, and is a figure which shows the correlation with the injection interval Int (environmental value) and the injection rate parameter. It is a test result which this inventor implemented, and is a figure which shows the effect of expectation correction by the conversion means of FIG. In 1st Embodiment, it is a flowchart which shows the procedure which converts a reference parameter into a present parameter, and sets an injection command signal. It is a flowchart which shows the procedure which learns the pulsation parameter Uf and the correlation parameter Uint in 2nd Embodiment of this invention.

  Hereinafter, each embodiment which actualized the fuel-injection control apparatus which concerns on this invention is described based on drawing. The fuel injection system of the embodiment described below is mounted on a vehicle engine (internal combustion engine), and high pressure fuel is injected into a plurality of cylinders # 1 to # 4 into the engine. A diesel engine that uses compression auto-ignition combustion is assumed.

(First embodiment)
FIG. 1 is a schematic diagram showing a fuel injection valve 10 mounted on each cylinder of the engine, a fuel pressure sensor 20 mounted on each fuel injection valve 10, an ECU 30 that is an electronic control device mounted on a vehicle, and the like. is there.

  First, an engine fuel injection system including the fuel injection valve 10 will be described. The fuel in the fuel tank 40 is pumped and stored in the common rail 42 (pressure accumulating container) by the fuel pump 41, and distributed and supplied to the fuel injection valves 10 (# 1 to # 4) of each cylinder. The plurality of fuel injection valves 10 (# 1 to # 4) sequentially inject fuel in a preset order. In addition, since the plunger pump is used for the fuel pump 41, fuel is pumped in synchronism with the reciprocating motion of the plunger.

  The fuel injection valve 10 includes a body 11, a needle-shaped valve body 12, an actuator 13, and the like described below. The body 11 forms a high-pressure passage 11a inside and a nozzle hole 11b for injecting fuel. The valve body 12 is accommodated in the body 11 and opens and closes the nozzle hole 11b.

  A back pressure chamber 11c for applying a back pressure to the valve body 12 is formed in the body 11, and the high pressure passage 11a and the low pressure passage 11d are connected to the back pressure chamber 11c. The communication state between the high pressure passage 11a and the low pressure passage 11d and the back pressure chamber 11c is switched by the control valve 14, and the actuator 13 such as an electromagnetic coil or a piezoelectric element is energized to push the control valve 14 downward in FIG. As a result, the back pressure chamber 11c communicates with the low pressure passage 11d and the fuel pressure in the back pressure chamber 11c decreases. As a result, the back pressure applied to the valve body 12 is lowered and the valve body 12 is lifted up (opening operation). On the other hand, when the power supply to the actuator 13 is turned off and the control valve 14 is operated upward in FIG. 1, the back pressure chamber 11c communicates with the high pressure passage 11a and the fuel pressure in the back pressure chamber 11c increases. As a result, the back pressure applied to the valve body 12 increases and the valve body 12 is lifted down (closed valve operation).

  Therefore, the ECU 30 controls the energization of the actuator 13 so that the opening / closing operation of the valve body 12 is controlled. Thereby, the high-pressure fuel supplied from the common rail 42 to the high-pressure passage 11 a is injected from the injection hole 11 b according to the opening / closing operation of the valve body 12.

  The fuel pressure sensor 20 includes a stem 21 (distortion body), a pressure sensor element 22, a mold IC 23, and the like described below. The stem 21 is attached to the body 11, and the diaphragm portion 21a formed on the stem 21 is elastically deformed by receiving the pressure of the high-pressure fuel flowing through the high-pressure passage 11a. The pressure sensor element 22 is attached to the diaphragm portion 21a, and outputs a pressure detection signal in accordance with the amount of elastic deformation generated in the diaphragm portion 21a.

  A temperature sensor element 22a (fuel temperature sensor) is attached to the diaphragm portion 21a. The temperature detected by the temperature sensor element 22a can be regarded as the temperature of the high-pressure fuel, and is used as an environmental value described later.

  The mold IC 23 is formed by resin molding electronic components such as an amplification circuit that amplifies the pressure detection signal output from the pressure sensor element 22 and a transmission circuit that transmits the pressure detection signal. 10 is installed. A connector 15 is provided on the upper portion of the body 11, and the mold IC 23, the actuator 13, and the ECU 30 are electrically connected by a harness 16 (signal line) connected to the connector 15. The amplified pressure detection signal is transmitted to the ECU 30 and received by a receiving circuit included in the ECU 30. This communication process for transmission / reception is performed for each fuel pressure sensor 20 of each cylinder.

  The ECU 30 calculates a target injection state (for example, the number of injection stages, the injection start timing, the injection end timing, the injection amount, etc.) based on the operation amount of the accelerator pedal, the engine load, the engine rotational speed NE, and the like. For example, the optimal injection state corresponding to the engine load and the engine speed is stored as an injection state map. Based on the current engine load and engine speed, the target injection state is calculated with reference to the injection state map. Then, the injection command signals t1, t2, and Tq (see FIG. 2A) corresponding to the calculated target injection state are set based on the injection rate parameters td, te, Rα, Rβ, and Rmax described in detail later, and the fuel By outputting to the injection valve 10, the operation of the fuel injection valve 10 is controlled.

  Here, the actual injection state with respect to the injection command signal changes due to the deterioration of the fuel injection valve 10 over time, such as wear and clogging of the injection hole 11b. Therefore, based on the detection value of the fuel pressure sensor 20, a change in the fuel pressure caused by the injection is detected as a fuel pressure waveform (see FIG. 2C), and an injection representing a change in the fuel injection rate based on the detected fuel pressure waveform. The rate waveform (see FIG. 2B) is calculated to detect the injection state. Then, while learning the injection rate parameters Rα, Rβ, and Rmax that specify the detected injection rate waveform (injection state), the correlation between the injection command signals (pulse-on timing t1, pulse-off timing t2, and pulse-on period Tq) and the injection state. The injection rate parameters td and te for specifying Specifically, the injection start delay time td, the injection end delay time te, the injection rate increase gradient Rα, the injection rate decrease gradient Rβ, the maximum injection rate Rmax, and the like illustrated in FIG.

  FIG. 3 is a block diagram showing an overview of learning of the injection rate parameter, setting of the injection command signal, and the like. Each means 31, 32, 33, 34 functioning by the ECU 30 will be described below. The injection rate parameter calculation means 31 (injection rate parameter calculation means) calculates injection rate parameters td, te, Rα, Rβ, Rmax based on the fuel pressure waveform detected by the fuel pressure sensor 20. The learning means 32 (injection rate parameter learning means) learns by updating the injection rate parameter converted by the conversion means 34 (reference environment conversion means) described in detail below in the memory 30m of the ECU 30.

  Here, the injection rate parameter has a different value depending on the environmental conditions at that time, such as the fuel temperature at the time of injection, the in-cylinder pressure, the supercharging pressure, the EGR amount, and the injection interval at the time of multistage injection. Therefore, the injection rate parameter calculated by the injection rate parameter calculation unit 31 (hereinafter referred to as a detection parameter) is converted by the conversion unit 34 into an injection rate parameter (hereinafter referred to as a reference parameter) corresponding to a reference environmental condition. To do. Then, the learning means 32 learns by storing and updating the converted reference parameter in the memory 30m.

  The injection rate parameter has a different value depending on the supply pressure at that time (pressure in the common rail 42). Therefore, it is desirable to learn the reference parameter in association with the supply pressure or a reference pressure Pbase described later. Further, it is desirable to learn other injection rate parameters other than the maximum injection rate Rmax in association with the injection amount. In the example of FIG. 3, the reference parameter is stored in the reference parameter map Mn in association with the fuel pressure (supply pressure or reference pressure Pbase). The reference parameter map Mn is provided for each injection rate parameter (td, te, Rα, Rβ, Rmax).

  Further, the converting means 34 (current environment converting means) has a function of converting the reference parameter stored in the reference parameter map Mn into an injection rate parameter (hereinafter referred to as current parameter) corresponding to the current environmental condition. . The conversion method to the reference parameter and the conversion method to the current parameter by the conversion means 34 will be described in detail later.

  The setting means 33 (injection command signal setting means) acquires a reference parameter corresponding to the current fuel pressure from the reference parameter map Mn, and based on the current parameter converted by the conversion means 34, an injection command signal corresponding to the target injection state. t1, t2, and Tq are set. The fuel pressure sensor 20 detects the fuel pressure waveform when the fuel injection valve 10 is operated in accordance with the injection command signal set in this way, and the injection rate parameter calculation means 31 based on the detected fuel pressure waveform, the injection rate parameter td, te, Rα, Rβ, Rmax are calculated.

  In short, an actual injection state (that is, injection rate parameters td, te, Rα, Rβ, Rmax) with respect to the injection command signal is detected and learned, and an injection command signal corresponding to the target injection state is set based on the learned value. . Therefore, the injection command signal is feedback-controlled based on the actual injection state, and the fuel injection state can be controlled with high accuracy so that the actual injection state coincides with the target injection state even when the above-described aging deterioration proceeds.

  Next, the procedure for calculating the injection rate parameters td, te, Rα, Rβ, and Rmax (see FIG. 2B) from the detected fuel pressure waveform (see FIG. 2C) will be described using the flowchart of FIG. To do. Note that the process shown in FIG. 4 is executed each time fuel is injected by the microcomputer of the ECU 30. The fuel pressure waveform is a set of a plurality of detection values obtained by the fuel pressure sensor 20 acquired at a predetermined sampling period.

  First, in step S10 (fuel pressure waveform detecting means) shown in FIG. 4, a fuel pressure waveform used for calculation of the injection rate parameter, and an injection waveform Wb (corrected fuel pressure waveform) described below is calculated. In the following description, a cylinder that is injecting fuel from the fuel injection valve 10 is an injection cylinder (front cylinder), and a cylinder that is not injecting fuel when the injection cylinder is injecting fuel is a non-injection cylinder ( The fuel pressure sensor 20 corresponding to the injection cylinder and the fuel pressure sensor 20 corresponding to the non-injection cylinder is referred to as the non-injection fuel pressure sensor.

  The fuel pressure waveform Wa during injection, which is the fuel pressure waveform detected by the fuel pressure sensor during injection (see FIG. 5A), does not represent only the influence due to the injection, but is caused by the influence other than the injection exemplified below. It also includes waveform components. That is, when the fuel pump 41 that pumps the fuel in the fuel tank 40 to the common rail 42 pumps the fuel intermittently like a plunger pump, if pump pumping is performed during fuel injection, the pump pumping period The fuel pressure waveform Wa during the injection is a waveform in which the pressure is increased as a whole. That is, the injection fuel pressure waveform Wa (see FIG. 5 (a)) represents the injection waveform Wb (see FIG. 5 (c)), which is a fuel pressure waveform representing the change in fuel pressure due to injection, and the increase in fuel pressure due to pumping. It can be said that the fuel pressure waveform (see the solid line Wu in FIG. 5B) is included.

  Even if such pump pumping is not performed during fuel injection, immediately after the fuel is injected, the fuel pressure in the entire injection system is reduced by that amount. Therefore, the fuel pressure waveform Wa at the time of injection becomes a waveform in which the pressure is lowered as a whole. That is, the injection fuel pressure waveform Wa includes a component of the injection waveform Wb that represents a change in fuel pressure due to injection and a fuel pressure waveform that represents a decrease in the fuel pressure in the entire injection system (see the dotted line Wu ′ in FIG. 5B). It can be said that the ingredients are included.

  Therefore, in step S10 of FIG. 4, paying attention to the non-injection fuel pressure waveform Wu (Wu ′) detected by the non-injection cylinder sensor represents a change in the fuel pressure in the common rail (the fuel pressure in the entire injection system), The injection waveform Wb is calculated by subtracting the non-injection fuel pressure waveform Wu (Wu ′) from the non-injection cylinder sensor from the injection fuel pressure waveform Wa detected by the injection cylinder sensor. The fuel pressure waveform shown in FIG. 2C is the injection waveform Wb.

  In the subsequent step S11, based on a reference waveform that is a waveform corresponding to a period until the fuel pressure starts to drop with the start of injection in the injection waveform Wb, the average fuel pressure of the reference waveform is calculated as the reference pressure Pbase. . For example, a portion corresponding to a period TA until a predetermined time elapses from the injection start command timing t1 may be set as the reference waveform. Alternatively, the inflection point P1 is calculated based on the differential value of the descending waveform (see FIG. 2D), and the portion corresponding to the period from the injection start command timing t1 to the predetermined time before the inflection point P1 is used as the reference waveform. You only have to set it.

  In the subsequent step S12, an approximate straight line Lα of the descending waveform is calculated based on the descending waveform that is the waveform corresponding to the period in which the fuel pressure decreases as the injection rate increases in the injection waveform Wb. For example, what is necessary is just to set the part corresponding to predetermined period TB from the time of predetermined time having passed since injection start instruction | command time t1 as a fall waveform. Alternatively, the inflection points P1 and P2 may be calculated based on the differential value of the descending waveform (see FIG. 2D), and a portion corresponding to the inflection points P1 and P2 may be set as the descending waveform. Then, an approximate straight line Lα may be calculated by a least square method from a plurality of detected fuel pressure values (sampling values) constituting the descending waveform. Alternatively, the tangent at the time when the differential value (see FIG. 2D) of the descending waveform is minimum may be calculated as the approximate straight line Lα.

  In the subsequent step S13, an approximate straight line Lβ of the rising waveform is calculated based on the rising waveform that is the waveform corresponding to the period in which the fuel pressure increases as the injection rate decreases in the injection waveform Wb. For example, what is necessary is just to set the part corresponding to the predetermined period TC from the time of predetermined time having passed since the injection end instruction | command time t2 as a rising waveform. Alternatively, the inflection points P3 and P5 may be calculated based on the differential value of the rising waveform (see FIG. 2D), and the portion corresponding to the inflection points P3 and P5 may be set as the rising waveform. Then, the approximate straight line Lβ may be calculated from the plurality of detected fuel pressure values (sampling values) constituting the rising waveform by the least square method. Alternatively, the tangent at the time when the differential value (see FIG. 2D) of the rising waveform becomes maximum may be calculated as the approximate straight line Lβ.

  In subsequent step S14, reference values Bα and Bβ are calculated based on the reference pressure Pbase. For example, values lower than the reference pressure Pbase by a predetermined amount may be calculated as the reference values Bα and Bβ. It is not necessary to set both reference values Bα and Bβ to the same value. The predetermined amount may be variably set according to the value of the reference pressure Pbase, the fuel temperature, and the like.

  In the subsequent step S15, a time (intersection time LBα between Lα and Bα) at which the approximate value Lα becomes the reference value Bα is calculated. Focusing on the fact that the intersection time LBα and the injection start time R1 are highly correlated, the injection start time R1 is calculated based on the intersection time LBα. For example, a timing that is a predetermined delay time Cα before the intersection timing LBα may be calculated as the injection start timing R1.

  In the subsequent step S16, a time (intersection time LBβ between Lβ and Bβ) that is the reference value Bβ in the approximate straight line Lβ is calculated. Focusing on the fact that the intersection timing LBβ and the injection end timing R4 are highly correlated, the injection end timing R4 is calculated based on the intersection timing LBβ. For example, a timing that is a predetermined delay time Cβ before the intersection timing LBβ may be calculated as the injection end timing R4. The delay times Cα and Cβ may be variably set according to the value of the reference pressure Pbase, the fuel temperature, and the like.

  In subsequent step S17, focusing on the fact that the slope of the approximate line Lα and the slope of the injection rate increase are highly correlated, the slope of the straight line Rα indicating the increase in injection in the injection rate waveform shown in FIG. Calculation is based on the slope of Lα. For example, the slope of Rα may be calculated by multiplying the slope of Lα by a predetermined coefficient. Note that, based on the injection start timing R1 calculated in step S15 and the slope of Rα calculated in step S17, a straight line Rα representing the rising portion of the injection rate waveform with respect to the injection command signal can be specified.

  Further, in step S17, paying attention to the fact that the slope of the approximate straight line Lβ and the slope of the injection rate decrease are highly correlated, the slope of the straight line Rβ indicating the decrease in the injection rate waveform is calculated based on the slope of the approximate straight line Lβ. . For example, the slope of Rβ may be calculated by multiplying the slope of Lβ by a predetermined coefficient. Note that, based on the injection end timing R4 calculated in step S16 and the slope of Rβ calculated in step S17, a straight line Rβ representing the descending portion of the injection rate waveform with respect to the injection command signal can be specified. The predetermined coefficient may be variably set according to the value of the reference pressure Pbase, the fuel temperature, and the like.

  In the subsequent step S18, based on the injection rate waveform straight lines Rα and Rβ calculated in step S17, a timing (valve closing operation start timing R23) at which the valve body 12 starts lift-down in response to the command to end the injection is calculated. . Specifically, the intersection of both straight lines Rα and Rβ is calculated, and the intersection timing is calculated as the valve closing operation start timing R23.

  In the subsequent step S19, a delay time (injection start delay time td) of the injection start timing R1 calculated in step S15 with respect to the injection start command timing t1 is calculated. Further, a delay time (injection end delay time te) with respect to the injection end command timing t2 of the valve closing operation start timing R23 calculated in step S18 is calculated.

  In subsequent step S20, paying attention to the fact that the maximum drop amount ΔP of the injection waveform Wb is highly correlated with the maximum injection rate Rmax, the maximum drop amount ΔP is calculated from the injection waveform Wb, and the maximum injection is based on the calculated maximum drop amount ΔP. The rate Rmax is calculated. For example, Rmax may be calculated by multiplying ΔP by a predetermined coefficient. The predetermined coefficient may be variably set according to the value of the reference pressure Pbase, the fuel temperature, and the like.

  As described above, according to the process of FIG. 4, the injection rate parameters td, te, Rα, Rβ, and Rmax can be calculated from the injection waveform Wb. Based on these injection rate parameters td, te, Rα, Rβ, Rmax, an injection rate waveform (see FIG. 2B) corresponding to the injection command signal (see FIG. 2A) can be calculated. . Since the area of the injection rate waveform calculated in this way (see halftone dot hatching in FIG. 2B) corresponds to the injection amount, the injection amount can also be calculated based on the injection rate parameter. Incidentally, when the injection command period Tq is sufficiently long and the valve opening state is continued even after reaching the maximum injection rate, the injection rate waveform is trapezoidal as shown in FIG. On the other hand, in the case of small injection that starts the valve closing operation before reaching the maximum injection rate, the injection rate waveform is a triangle.

  Next, the procedure for learning by converting the detection parameter into the reference parameter as described above will be described with reference to the flowchart of FIG. Note that the process shown in FIG. 6 is executed each time fuel is injected by the microcomputer of the ECU 30.

  First, in step S30 (injection rate parameter calculation means) shown in FIG. 6, the injection rate parameters td, te, Rα, Rβ, and Rmax calculated from the injection waveform Wb by the processing of FIG. 4 described above are acquired as detection parameters. In the subsequent step S31, an environmental value exemplified below and an environmental value (current environmental value) when the fuel injection of the injection waveform Wb used for calculation of the detection parameter is performed is acquired. Specific examples of the environmental value include the fuel temperature Th, the interval Int between fuel injections (see FIG. 2A), the in-cylinder pressure P (θ) at the time of fuel injection, the number of injection stages, and the intake pressure (or supercharging pressure). , EGR amount and the like.

  If these environmental values are different, even if the injection command signal is the same, the injection state (injection rate waveform) will be different, and the detection parameters will also be different. Further, the correlation between these environmental values and detection parameters can be estimated. Therefore, in the present embodiment, the correlation between the detection parameter and the environmental value is acquired by testing in advance, and the correlation map MTh, MInt, MP (θ) representing the acquired correlation is stored in the memory 30m (correlation model storage unit). Remember.

  These correlation maps MTh, MInt, and MP (θ) correspond to “correlation models that represent the correlation between the injection rate parameter and the environmental value that changes the value of the injection rate parameter by changing the value”. Instead of this, a model expression representing the relationship between the detection parameter and the environmental value may be stored in the memory 30m as a correlation model. Such a correlation model (correlation map or model formula) represents the correlation between the deviation of the detection parameter with respect to the injection rate parameter (reference parameter) corresponding to the reference environment value and the environment value. The correlation model is created for each of the injection rate parameters td, te, Rα, Rβ, and Rmax.

  FIG. 7 is a correlation map MTh between the fuel temperature (environmental value) and the injection rate parameter. The injection start delay time td and the injection end delay time te are longer as the temperature is higher. Therefore, in the correlation map MTh shown in FIGS. 7A and 7B, the deviations td−tdn and te−ten with respect to the reference parameters tdn and ten of the delay times td and te are set to be longer as the fuel temperature is higher. ing.

  Further, the injection rate increase slope Rα and the injection rate decrease slope Rβ become gentler as the temperature increases. Therefore, in the correlation map MTh shown in FIG. 7C, the deviation Rα−Rαn of the injection rate increasing slope Rα with respect to the reference parameter Rαn is set to be smaller as the fuel temperature is higher. Further, in the correlation map MTh shown in FIG. 7D, the deviation Rβ−Rβn of the injection rate decreasing slope Rβ with respect to the reference parameter Rβn is set to increase as the fuel temperature increases.

  Further, the maximum injection rate Rmax decreases as the temperature increases. Therefore, in the correlation map MTh shown in FIG. 7 (e), the deviation Rmax−Rmaxn of the maximum injection rate Rmax with respect to the reference parameter Rmaxn is set to be smaller as the fuel temperature is higher.

FIG. 8 is a diagram showing the correlation between the injection interval Int (environment value) and the injection rate parameter. The + mark in the figure indicates the value (actual value) of the injection rate parameter measured by the test described below. On the other hand, the solid line without the + mark in the figure indicates the current parameter (model value) calculated by the conversion means 34 in FIG. In the above test, the injection rate parameter for the second-stage injection when the second-stage injection is performed at the supply pressure of 80 MPa is measured. 8 (a1) to (d1) are test results in which the first and second stage injection amounts are both 2 mm ³ , and FIGS. 8 (a2) to (d2) are the first stage injection. This is a test result when the amount is 2 mm ³ and the second stage injection amount is 10 mm ³ .

  The test results in FIG. 8 indicate that in any injection rate parameter, pulsation repeats ascending and descending according to the change in the interval. Further, the current parameter (model value) calculated by the conversion means 34 in FIG. 3 is a value close to the actual measurement value, which indicates that the model value calculation accuracy by the conversion means 34 is sufficiently secured.

  FIG. 9 is a graph showing the results of a test of measuring the injection amount when the injection command signal and the supply pressure (80 MPa) are the same while actually injecting at different intervals. Indicates the amount of deviation between the measured value of the injection amount and the target injection amount, and the horizontal axis indicates the interval. In the figure, the solid line to which the + mark has not been assigned is based on the model value obtained by converting the reference parameter into the current parameter (correction correction) by the converting unit 34, and the setting unit 33 sets the injection command signal and performs the injection control. The deviation amount in the case is shown. On the other hand, the + mark in the figure indicates the shift amount when the prospective correction is not performed.

The test results in FIG. 9 indicate that if the prospective correction is performed, the deviation of the actual injection amount with respect to the target injection amount becomes small, and the injection control can be performed with high accuracy. FIG. 9 (a) shows the test results in which the first and second stage injection amounts are both 2 mm ^3. FIG. 9 (b) shows the first stage injection amount of 2 mm ³ and the second stage. It is a test result which made the injection quantity of 10 mm < ³ >.

  Returning to the description of FIG. 6, in the subsequent step S <b> 32, it is determined whether or not a learning condition is satisfied. For example, when the fuel temperature exceeds a predetermined upper limit and becomes high, the liquid fuel boils and enters a gas-liquid two-phase state. Further, when the fuel temperature exceeds a predetermined lower limit value and becomes a low temperature, the liquid fuel is waxed. Therefore, when the fuel temperature exceeds the upper limit value and is high, or when the fuel temperature exceeds the lower limit value and is low, it is determined that the learning condition is not satisfied and learning of the reference parameter is prohibited.

  On the other hand, if it is determined that the learning condition is satisfied, the process proceeds to the next step S33 (reference environment conversion means), and the current environment value acquired in step S31 and the correlation map MTh, MInt, MP (θ). Based on this, all detection parameters are converted into reference parameters. For example, when the reference fuel temperature Thn is 70 ° C. and the current fuel temperature Th is 100 ° C., the deviation td of the injection start delay time td corresponding to 100 ° C. based on the correlation map MTh illustrated in FIG. -Tdn (+2 μsec in the example of FIG. 7A) is calculated. Then, by subtracting the deviation td-tdn (2 μsec) from the detected injection start delay time td, the reference injection start delay time tdn can be calculated. Thereby, the detected injection start delay time td (detection parameter) can be converted into a reference injection start delay time tdn (reference parameter).

  In subsequent step S34 (injection rate parameter learning means), the converted reference parameters td, te, Rα, Rβ, Rmax calculated in step S33 are stored and updated in the reference parameter map Mn for learning. In the reference parameter map Mn illustrated in FIG. 3, the reference parameter is learned in association with the fuel pressure (supply pressure or reference pressure Pbase). Therefore, it is desirable to store the deviation of the injection rate parameter with respect to the environmental value in association with the fuel pressure (supply pressure or reference pressure Pbase) for the correlation maps MTh, MInt, and MP (θ).

  Next, the procedure for converting the reference parameter into the current parameter and setting the injection command signal as described above will be described with reference to the flowchart of FIG. Note that the process shown in FIG. 10 is repeatedly executed by a microcomputer included in the ECU 30.

  First, in step S40 shown in FIG. 10, the current environmental value (current environmental value) is acquired. The current value of the interval Int may be calculated based on the injection start command timing t1 (scheduled timing) based on the current injection command signal and the previous injection start command timing t1. Further, since the in-cylinder pressure P (θ) can be predicted based on the injection start timing, the current value of the in-cylinder pressure P (θ) can be calculated based on the injection start command timing t1 (scheduled timing) based on the current injection command signal. Good. Further, as the current value of the fuel temperature Th, the fuel temperature acquired in step S31 of FIG. 6 at the time of the previous injection may be used.

  In subsequent step S41 (current environment converting means), all reference parameters are converted into current parameters based on the current environment values acquired in step S40, the correlation map MTh, MInt, MP (θ), and the reference parameter map Mn. To do. For example, when the reference fuel temperature Thn is 70 ° C. and the current fuel temperature Th is 100 ° C., the deviation td of the injection start delay time td corresponding to 100 ° C. based on the correlation map MTh illustrated in FIG. -Tdn (+2 μsec in the example of FIG. 7A) is calculated. The current injection start delay time td can be calculated by adding the deviation td-tdn (2 μsec) to the reference injection start delay time tdn stored in the reference parameter map Mn. Thereby, the reference injection start delay time tdn (reference parameter) can be converted into the current injection start delay time td (current parameter).

  As described above, in the reference parameter map Mn, the reference parameter is learned in association with the fuel pressure (supply pressure or reference pressure Pbase). Therefore, in calculating the current parameter in step S41, the current parameter may be calculated by calculating the reference parameter corresponding to the fuel pressure from the reference parameter map Mn.

  In the subsequent step S42, the target injection state (for example, the number of injection stages, the injection start timing, the injection end timing, the injection amount, etc.) is calculated based on the operation amount of the accelerator pedal, the engine load, the engine speed NE, and the like. In subsequent step S43 (injection command signal setting means), an injection command signal corresponding to the target injection state calculated in step S42 is set based on the current parameter calculated in step S41.

  According to the embodiment described in detail above, the following effects can be obtained.

  (1) A correlation map MTh, MInt, MP (θ) representing the correlation between the injection rate parameters td, te, Rα, Rβ, Rmax and the environmental values Th, Int, P (θ) is stored in the memory 30m in advance. deep. Then, the injection rate parameter (detection parameter) calculated based on the detected injection waveform Wb is converted into the injection rate parameter (reference parameter) corresponding to the reference environment value based on the current environment value and the correlation map, and the reference parameter Learn to map Mn. For this reason, since only the reference parameter corresponding to the reference environment value needs to be learned in the reference parameter map Mn, the map used by the learning means 32 is compared with the case where the detection parameter is learned in association with the current environment value each time. The storage capacity required for (reference parameter map Mn) can be reduced, and an increase in learning processing load can be suppressed.

  (2) Here, when the conversion means 34 is abolished against the present embodiment and the detection parameters are directly learned in the map used in the learning means 32, the following problems are concerned. That is, the optimal injection rate parameter (current parameter) used for setting the injection command signal changes as the environmental value changes, but if the above learning is performed, the injection command signal is set with the optimal injection rate parameter. It is possible to set. However, since the injection command signal cannot be set with the optimal injection rate parameter until the learning is completed, the injection state cannot be controlled with high accuracy during the transient period in which the environmental value has suddenly changed.

  In contrast, in the present embodiment, based on the current environmental value and the correlation map, the reference parameter is converted into an injection rate parameter (current parameter) corresponding to the current environmental value, and the injection command is based on the converted current parameter. Set the signal. Therefore, when the environmental value suddenly changes, the injection command signal suitable for the environmental value after the sudden change can be set without waiting for the completion of learning of the injection rate parameter corresponding to the environmental value after the sudden change. . Therefore, it is possible to control the injection state with high accuracy even during a transition period in which the environmental value changes suddenly.

  In short, in the present embodiment, feedback control is performed by learning the reference parameter by the learning unit 32, and feedforward control is performed by converting (reference correction) the reference parameter to the current parameter by the conversion unit 34. I can say that.

  (3) The correlation map of the conversion means 34 (reference environment conversion means) used in the reference parameter learning process of FIG. 6 and the correlation map of the conversion means 34 (current environment conversion means) used in the injection command signal setting process of FIG. Therefore, the conversion accuracy from the reference parameter to the current parameter can be improved, and the storage capacity of the memory 30m required for the correlation map can be increased as compared with the case where the correlation maps used in both conversion means are different. Less.

  (4) Here, the correlation between the environmental values Th, Int, P (θ) and the injection rate parameters td, te, Rα, Rβ, Rmax should be estimated before shipping the fuel injection valve 10 to the market. Therefore, the correlation map MTh, MInt, and MP (θ) can be created by testing and obtaining the correlation before shipment to the market and stored in the memory 30m. On the other hand, the correlation between the supply pressure such as the reference pressure Pbase and the injection rate parameter varies greatly depending on the degree of deterioration of the fuel injection valve 10, so that it is difficult to estimate and create a correlation map before market shipment. It is.

  On the other hand, in this embodiment, when learning the injection rate parameter (reference parameter) with the reference parameter map Mn of the learning means 32, the reference parameter is learned in association with the supply pressure. It is possible to learn from reference parameters that take into account the correlation with pressure. Therefore, the learning accuracy of the reference parameter can be improved. Similarly, since the reference parameter corresponding to the current supply pressure is acquired from the reference parameter map Mn when setting the injection command signal by the setting means 33, the correlation with the supply pressure corresponding to the aged deterioration state is obtained. An added injection command signal can be set. Therefore, the injection state can be controlled with high accuracy.

  In short, in the present embodiment, a correlation map is created for the environmental values Th, Int, P (θ) whose correlation with the injection rate parameter can be estimated before market shipment, and the detected parameter is converted into the reference parameter and the reference parameter To current parameters. On the other hand, the environmental value (supply pressure) that is difficult to estimate is learned in association with the supply pressure when learning the reference parameter in the reference parameter map Mn without creating a correlation map.

(Second Embodiment)
In the present embodiment, a pulsation waveform Wm described below is learned, and a correlation model (correlation map MInt) shown in FIG. 3 is learned based on the learned pulsation waveform Wm. First, the definition of the pulsation waveform Wm and the technical significance of learning the pulsation waveform Wm will be described below, and then the details of the technique for learning the correlation model based on the pulsation waveform Wm will be described.

  When executing multi-stage injection control in which fuel is injected a plurality of times per combustion cycle, it is necessary to pay attention to the following points. That is, the fuel pressure waveform Wa generated with the n-th injection after the first injection has a pulsation waveform corresponding to the portion after the end of the fuel pressure waveform Wa generated with the m-th injection (pre-stage injection) before the n-th injection. Wm (see FIG. 2C and FIG. 5C) is superimposed (interfered). Then, it becomes difficult to accurately detect the injection rate parameter from the injection waveform Wb applied to the n-th injection.

  Therefore, in the present embodiment, in calculating the injection waveform Wb used in step S10 of FIG. 4 and step S30 of FIG. 6, the non-injection fuel pressure waveform Wu is subtracted from the injection fuel pressure waveform Wa and the pulsation waveform Wm described above is subtracted. To calculate the injection waveform Wb. According to this, the component of the pulsation waveform Wm of the pre-stage injection superimposed on the fuel pressure waveform Wa during injection can be removed, and the injection rate parameter can be detected with high accuracy.

  Next, a method for acquiring the pulsation waveform Wm used for subtraction in this way will be described.

  In the memory 30m of the ECU 30, a model formula (pulsation model formula) in which the pulsation waveform Wm is expressed by a mathematical formula is stored in advance. And the model waveform represented by this pulsation model formula is acquired as the pulsation waveform Wm. In the present embodiment, the following formula 1 obtained by superposing a plurality of damped oscillation equations is adopted as the model formula.

数式１中のｐは脈動モデル式により表されるモデル波形の値（燃圧センサ２０による検出圧力推定値）を示す。なお、この脈動モデル式により表されるモデル波形は、単調増加と単調減少を繰り返しながら減衰する減衰波形となっている。

P in Formula 1 indicates a value of a model waveform (estimated pressure value detected by the fuel pressure sensor 20) represented by a pulsation model formula. Note that the model waveform represented by this pulsation model equation is an attenuation waveform that attenuates while repeating monotonous increase and monotonous decrease.

  Here, p0 in Equation 1 represents an offset deviation amount of the model waveform with respect to the pulsation waveform included in the fuel pressure waveform Wa on which the pulsation waveform Wm of the pre-stage injection is not superimposed. N in Formula 1 indicates the number of damped oscillation equations superimposed. A, k, ω, and θ in Equation 1 represent the amplitude, the damping coefficient, the frequency, and the phase in the damped vibration, respectively. That is, the pulsation model equation shown in Equation 1 determines the parameters of the model waveform by determining the parameters of p0, n, A, k, ω, θ (hereinafter, these parameters are collectively referred to as the pulsation parameter Uf). The value p can be output.

  The ECU 30 calculates the pulsation parameter Uf based on the detected pulsation waveform Wm, and stores and updates the calculated pulsation parameter Uf for learning. Specifically, the values of pulsation parameters Uf such as p0, A, k, ω, θ are learned for each in association with the injection amount and the supply pressure. Then, the pulsation waveform Wm is calculated from the pulsation model equation based on the learned pulsation parameter Uf, the correction is performed by subtracting the calculated pulsation waveform Wm from the fuel pressure waveform Wa, and the injection waveform Wb used in steps S10 and S30 is calculated.

  By the way, a correlation model representing the correlation between the injection rate parameters td, te, Rα, Rβ, Rmax and the interval Int can be expressed by the following equation 2 (interval correlation model equation). The correlation map MInt shown in FIG. 3 can be used instead.

数式２中のｐｉｎｔは、基準パラメータに対する噴射率パラメータ（検出パラメータ）の偏差を示す。つまり、図３に例示する相関マップＭＩｎｔの縦軸の値に相当し、具体的には、先述したｔｄ−ｔｄｎ，ｔｅ−ｔｅｎ，Ｒα−Ｒαｎ，Ｒβ−Ｒβｎ，Ｒｍａｘ−Ｒｍａｘｎのいずれかを示す。このインターバル相関モデル式により表されるモデル波形は、単調増加と単調減少を繰り返しながら減衰する減衰波形となっている。つまり、インターバルＩｎｔの変化に応じて検出パラメータは増加と減少を周期的に繰り返す。

“Pint” in Equation 2 represents the deviation of the injection rate parameter (detection parameter) from the reference parameter. That is, it corresponds to the value on the vertical axis of the correlation map MInt illustrated in FIG. 3, and specifically indicates any of the above-described td-tdn, te-ten, Rα-Rαn, Rβ-Rβn, Rmax-Rmaxn. . The model waveform represented by the interval correlation model equation is an attenuation waveform that attenuates while repeating monotonous increase and monotonic decrease. That is, the detection parameter periodically increases and decreases according to the change in the interval Int.

  In Equation 2, p0td, Atd, ktd, ωtd, and θtd indicate an offset deviation amount, an amplitude in a damped oscillation, a damping coefficient, a frequency, and a phase, respectively. In other words, the interval correlation model expression shown in Equation 2 is obtained by determining the parameters of p0td, n, Atd, ktd, ωtd, and θtd (hereinafter these parameters are collectively referred to as interval correlation parameter Uint). A deviation value pint of the detected parameter with respect to the parameter can be output.

  Here, the interval correlation model formula of Formula 2 and the pulsation model formula of Formula 1 are attenuation waveforms having the same shape. The present inventors have found that there is a correlation between both model formulas. For example, the following relationships hold: Atd = G1 × A, ktd = G2 × k, ωtd = ω, θtd = G3 × θ (G1, G2, and G3 are proportional constants). In this embodiment in view of this point, the interval correlation parameter Uint is calculated from the learned pulsation parameter Uf, and the interval correlation parameter Uint is stored and updated for learning. It is desirable to learn the values of interval correlation parameters Uint such as p0td, Atd, ktd, ωtd, and θtd in association with the injection amount and the supply pressure.

  Next, the procedure for learning the pulsation parameter Uf and the correlation parameter Uint as described above will be described with reference to the flowchart of FIG. Note that the processing shown in FIG. 11 is repeatedly executed by the microcomputer included in the ECU 30.

  First, in step S50 shown in FIG. 11, it is determined whether or not a learning condition is satisfied. For example, in the same manner as in step S32 of FIG. 10, when the fuel temperature exceeds the upper limit value and is high, or when the fuel temperature exceeds the lower limit value and is low, it is determined that the learning condition is not satisfied and both Learning of the parameters Uf and Uint is prohibited. On the other hand, if it is determined that the learning condition is satisfied, the process proceeds to the next step S51 (pulsation waveform extracting means), where the pulsation waveform Wm is extracted from the injection waveform Wb, and the value of the pulsation parameter Uf is extracted from the extracted pulsation waveform Wm. Is detected.

  In the subsequent step S52, the pulsation parameter Uf detected in step S51 is stored and updated for learning. In the subsequent step S53 (correlation learning value calculation means), the value of the interval correlation parameter Uint is calculated based on the value of the pulsation parameter Uf learned in step S52 and the preset proportional constants G1, G2, G3, etc. To do. In the subsequent step S54 (correlation model learning means), the value of the interval correlation parameter Uint calculated in step S53 is stored and updated for learning.

  As described above, according to the present embodiment, when calculating the injection waveform Wb used in step S10 of FIG. 4 and step S30 of FIG. 6, the injection waveform Wb is obtained by subtracting the pulsation waveform Wm estimated from the pulsation model equation of Equation 1. Therefore, the component of the pulsation waveform Wm of the preceding injection superimposed on the fuel pressure waveform Wa during injection can be removed, and the injection rate parameter can be accurately detected.

  Furthermore, according to the present embodiment, focusing on the fact that the interval correlation parameter Uint has a correlation with the pulsation parameter Uf, the interval correlation parameter Uint is calculated and learned based on the learned pulsation parameter Uf. The model formula can be high. Therefore, using the interval correlation model formula (correlation model), when converting the detection parameter to the reference parameter and converting the reference parameter to the current parameter, the conversion accuracy can be improved. As a result, the injection state can be improved with higher accuracy. You will be able to control.

(Other embodiments)
The present invention is not limited to the description of the above embodiment, and may be modified as follows. Moreover, you may make it combine the characteristic structure of each embodiment arbitrarily, respectively.

  In the above-described embodiment, the injection start delay time td, the injection end delay time te, the injection rate increase slope Rα, the injection rate decrease slope Rβ, and the maximum injection rate Rmax are given as specific examples of the injection rate parameter. The delay time from the injection end command timing t2 to the injection end timing R4, the ratio of the injection amount with respect to the injection command period Tq, and the like.

  In the above embodiment shown in FIG. 1, the fuel pressure sensor 20 is mounted on the fuel injection valve 10, but the fuel pressure sensor according to the present invention is in the fuel supply path from the discharge port 42a of the common rail 42 to the injection hole 11b. Any fuel pressure sensor may be used so long as it detects the fuel pressure. Therefore, for example, a fuel pressure sensor may be mounted on the high-pressure pipe 42 b that connects the common rail 42 and the fuel injection valve 10. That is, the high-pressure pipe 42b connecting the common rail 42 and the fuel injection valve 10 and the high-pressure passage 11a in the body 11 correspond to the “fuel passage”.

  DESCRIPTION OF SYMBOLS 10 ... Fuel injection valve, 20 ... Fuel pressure sensor, 30m ... Memory (correlation model storage means), S10 ... Fuel pressure waveform detection means, 31, S30 ... Injection rate parameter calculation means, 32, S34 ... Injection rate parameter learning means, 33, S43 ... Injection command signal setting means, S33 ... Reference environment conversion means, S41 ... Current environment conversion means, S51 ... Pulsation waveform extraction means, S53 ... Correlation learning value calculation means, S54 ... Correlation model learning means.

Claims (5)

A fuel injection valve for injecting fuel accumulated in a pressure accumulating vessel;
A fuel pressure sensor that is disposed in a fuel passage from a discharge port of the pressure accumulating container to a nozzle hole of the fuel injection valve, and detects a fuel pressure in the fuel passage;
Applied to the fuel injection system with
A fuel pressure waveform detecting means for detecting a change in fuel pressure caused by injection as a fuel pressure waveform based on a detection value of the fuel pressure sensor;
An injection rate parameter calculation means for calculating an injection rate parameter required to specify an injection rate waveform corresponding to the detected fuel pressure waveform based on the detected fuel pressure waveform ;
In a fuel injection control device comprising:
Correlation model storage means for storing a correlation model representing a correlation between an environmental value that changes the value of the injection rate parameter and the injection rate parameter when the value changes;
Reference environment conversion means for converting the injection rate parameter calculated by the injection rate parameter calculation means into an injection rate parameter corresponding to a reference environment value based on the current environment value and the correlation model ;
And the injection rate parameter learning means for learning the injection rate parameter corresponding to the environmental value of the reference converted by the pre-Symbol reference environment conversion means,
An injection command signal setting means for setting an injection command signal corresponding to a required injection state based on the injection rate parameter learned by the injection rate parameter learning means, and outputting the set injection command signal to the fuel injection valve;
The fuel injection control apparatus comprising: a. A current environment conversion means for converting the injection rate parameter learned by the injection rate parameter learning means into an injection rate parameter corresponding to the current environment value based on the current environment value and the correlation model;
2. The fuel injection control apparatus according to claim 1, wherein the injection command signal setting means sets an injection command signal corresponding to a requested injection state based on the injection rate parameter converted by the current environment conversion means. In the case where the interval between injections when the multistage injection in which fuel injection is performed a plurality of times per one combustion cycle is performed as the environmental value,
A pulsation waveform extracting means for extracting a pulsation waveform representing a pulsation of fuel pressure generated after the end of injection from the detected fuel pressure waveform;
Correlation learning value calculation means for calculating a learning value of the correlation model based on the extracted pulsation waveform;
Correlation model learning means for learning the correlation model based on the learning value calculated by the correlation learning value calculating means;
The fuel injection control device according to claim 1 or 2, characterized in that it comprises a. The correlation model storage means stores a correlation between the environmental value and the injection rate parameter in association with a supply pressure which is a pressure of fuel supplied from the pressure accumulating container to the fuel injection valve.
4. The fuel injection control apparatus according to claim 3 , wherein the correlation model learning unit learns the correlation model in association with the supply pressure. The injection rate parameter learning unit are all from the pressure accumulator in association with the supply pressure is the pressure of the fuel supplied to the fuel injection valve, according to claim 1-4, characterized in that to learn the injection rate parameter The fuel-injection control apparatus as described in any one.

Images