Internal combustion engine control device and internal combustion engine control method

Abstract

The purpose of the present invention is to appropriately control the heat balance of an ignition device and suppress an increase in size and cost of the ignition device. This internal combustion engine control device controls an internal combustion engine in which a current flowing through an ignition coil of an ignition device is interrupted in accordance with a predetermined ignition timing. The internal combustion engine control device includes a request setting unit, an adjusting unit, and an ignition control unit. The request setting unit determines a requested energization amount of an ignition coil on the basis of the rotational speed of an internal combustion engine. The adjustment unit adjusts the amount of energization of the ignition coil in accordance with the temperature related to the ignition device and the required amount of energization. The ignition control unit controls the interruption state of the ignition coil in accordance with the energization amount of the ignition coil adjusted by the adjustment unit.

Description

Technical Field

[0001] The present invention relates to an internal combustion engine control device and an internal combustion engine control method. Background Art

[0002] In recent years, in order to improve the fuel efficiency of vehicles, lean burn technology has been developed to operate the internal combustion engine by burning a mixture with a larger air-fuel ratio (thinner fuel) than the theoretical air-fuel ratio, and exhaust gas recirculation technology to introduce part of the burned exhaust gas and re-intake it.

[0003] In such an internal combustion engine, since a fuel-lean mixture is used or exhaust gas recirculation is implemented, it is difficult for sparks to fly out from the spark plug. Therefore, the ignition capacity (i.e., ignition energy) of the ignition device required to form a flame in the combustion chamber is greater than the case of ignition in a mixture with a theoretical air-fuel ratio. Therefore, the heat generated by the ignition coil per unit time increases.

[0004] For example, Patent Document 1 discloses an engine ignition device that corrects ignition energy based on pressure changes in an intake pipe. In the engine ignition device disclosed in Patent Document 1, ignition energy is increased by extending the energization time of the ignition coil based on the intake pipe pressure Pm to prevent misfires during supercharging. Thus, even in a situation where sparks on the spark plug are difficult to fly out due to supercharging, a stable combustion state is ensured. Prior art literature Patent Literature

[0005] Patent Document 1: Japanese Patent Application Publication No. 2000-054941 Summary of the invention Technical problem to be solved by the invention

[0006] However, the ignition device of the engine disclosed in Patent Document 1 does not take into account the thermal balance of the ignition coil. For example, if the internal combustion engine is continuously operated at a high load while the pressure Pm of the intake pipe is increased due to supercharging, the power supply time to the ignition coil will be extended. As a result, the ignition energy of the ignition device increases, that is, the state of high heat generation per unit time will continue. As a result, the temperature of the ignition device may exceed the preset rated temperature.

[0007] As a countermeasure to this problem, the heat dissipation of the ignition coil can be designed in consideration of the maximum heat generation per unit time of the ignition coil under the conditions of continuous high-load operation and severe environmental conditions such as high outside temperature in summer. However, this countermeasure brings new problems such as the enlargement of the ignition device and the increase in cost.

[0008] In view of the above problems, an object of the present invention is to provide an internal combustion engine control device and an internal combustion engine control method which appropriately control the heat balance of an ignition device and suppress the increase in size and cost of the ignition device. Technical means for solving technical problems

[0009] In order to solve the above problems and achieve the purpose of the present invention, an internal combustion engine control device involved in one aspect of the present invention controls an internal combustion engine, in which the current flowing through the ignition coil of the ignition device is intermittent according to a predetermined ignition timing. The internal combustion engine control device includes a requirement setting unit, an adjustment unit and an ignition control unit. The requirement setting unit determines the required energization amount of the ignition coil based on the rotational speed of the internal combustion engine. The adjustment unit adjusts the energization amount of the ignition coil according to the temperature related to the ignition device and the required energization amount. The ignition control unit controls the intermittent state of the ignition coil according to the energization amount of the ignition coil adjusted by the adjustment unit.

[0010] An internal combustion engine control method as one aspect of the present invention is a method for controlling an internal combustion engine in which a current flowing through an ignition coil of an ignition device is intermittent according to a predetermined ignition timing. In the internal combustion engine control method, a requirement setting unit determines a required energization amount of the ignition coil based on the rotation speed of the internal combustion engine. Next, an adjustment unit adjusts the energization amount of the ignition coil according to a temperature related to the ignition device and the required energization amount. Then, an ignition control unit controls the intermittent state of the ignition coil according to the energization amount of the ignition coil adjusted by the adjustment unit. Effects of the Invention

[0011] According to one aspect of the present invention, the heat balance of an ignition device in an internal combustion engine can be appropriately controlled, thereby suppressing an increase in size and cost of the ignition device. In addition, problems, structures, and effects other than those described above will become more apparent through the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is an overall configuration diagram showing a basic configuration example of an internal combustion engine according to one embodiment. Figure 2 It is a partially enlarged view illustrating a spark plug according to an embodiment. Figure 3 This is a functional block diagram illustrating the functional structure of an internal combustion engine control device according to an embodiment. Figure 4 is a circuit diagram showing one example of a circuit including an ignition coil. Figure 5 is a graph illustrating the relationship between electrode temperature, minimum ignition energy, and air-fuel ratio. Figure 6 is an example of a discharge waveform for multiple ignitions. Figure 7 This is a conceptual diagram showing the relationship between the supplyable discharge energy, the required discharge energy, and the difference between them with respect to the temperature of the ignition coil. Figure 8 This is a conceptual diagram showing the relationship between the temperature and discharge energy of a conventional ignition coil. Fig. 9 This is a conceptual diagram showing the relationship between the temperature of the ignition coil and the discharge energy when the present invention is applied. Fig.10 This is a flowchart showing the ignition and fuel injection control process according to the first embodiment. Fig.11 A conceptual diagram showing the weights and biases of each neuron that makes up a neural network model. Fig.12 This is a diagram illustrating a method for realizing calculations of target variables using a neural network model according to the first embodiment. Fig.13 1 is a conceptual diagram showing a neural network model used for ignition and fuel injection control processing in the first embodiment. Fig.14 This is a correspondence table showing the relationship between the target variable and the explanatory variable when the neural network model of embodiment 1 is used. Fig.15 This is a selection table of influencing factors when selecting explanatory variables for estimating the ignition coil temperature in the first embodiment. Fig.16 This is a diagram for explaining the restricted residency mapping according to the second implementation mode. Fig.17 This is a diagram for explaining the request-residence mapping according to the second embodiment. Fig.18 This is a diagram for explaining the voltage correction coefficient map according to the second embodiment. Fig.19 This is a flowchart showing the ignition and fuel injection control process according to the second embodiment. Fig. 20 This is a diagram for explaining the temperature correction coefficient map according to the third embodiment. Fig.21 This is a flowchart showing the ignition and fuel injection control process according to the third embodiment. Fig. 22 This is a diagram for explaining the low-temperature request residence map according to the fourth embodiment. Fig.23 This is a diagram for explaining the high-temperature demand residence map according to the fourth embodiment. Fig.24 This is a flowchart showing the ignition and fuel injection control process according to the fourth embodiment. Fig.25This is a circuit diagram showing an example of a circuit including an ignition coil according to the fifth embodiment. DETAILED DESCRIPTION

[0013] <Implementation Method 1> Hereinafter, the internal combustion engine control device according to the first embodiment will be described. In the drawings, the same reference numerals are used to denote common parts.

[0014] [Internal combustion engine system] First, the configuration of an internal combustion engine system according to an embodiment will be described. Figure 1 This is an overall configuration diagram showing a basic configuration example of an internal combustion engine according to an embodiment of the present invention.

[0015] Figure 1 The internal combustion engine 100 shown may have a single cylinder or multiple cylinders, but in the embodiment, an internal combustion engine 100 having four cylinders will be described as an example.

[0016] like Figure 1 As shown, in the internal combustion engine 100, air (intake air) sucked from the outside flows through the air filter 110, the intake pipe 111 and the intake manifold 112. When the intake valve 151 is opened, the air passing through the intake manifold 112 flows into each cylinder 150. The amount of air flowing into each cylinder 150 is adjusted by the throttle valve 113. The amount of air adjusted by the throttle valve 113 is measured by the flow sensor 114.

[0017] The throttle valve 113 is provided with a throttle valve opening sensor 113a for detecting the opening of the throttle valve. The opening information of the throttle valve 113 detected by the throttle valve opening sensor 113a is output to a control device (electronic control unit: ECU) 1.

[0018] In the present embodiment, an electronic throttle valve driven by an electric motor is used as the throttle valve 113. However, as the throttle valve of the present invention, other types of throttle valves may be applied as long as the air flow rate can be appropriately adjusted.

[0019] The temperature of the air flowing into each cylinder 150 is detected by the intake air temperature sensor 115 .

[0020] The crank angle sensor 121 is provided radially outside the ring gear 120 mounted on the crankshaft 123. The crank angle sensor 121 detects the rotation angle of the crankshaft 123. In the present embodiment, the crank angle sensor 121 detects the rotation angle of the crankshaft 123 every 10° and every combustion cycle.

[0021] The water temperature sensor 122 is provided in a water jacket (not shown) of the cylinder head. The water temperature sensor 122 detects the temperature of cooling water of the internal combustion engine 100.

[0022] In addition, an accelerator position sensor 126 is provided on the vehicle to detect the displacement (depression amount) of the accelerator pedal 125. The accelerator position sensor 126 detects the driver's required torque. The driver's required torque detected by the accelerator position sensor 126 is output to the internal combustion engine control device 1 described later. The internal combustion engine control device 1 controls the throttle valve 113 based on the required torque.

[0023] The fuel stored in the fuel tank 130 is sucked and pressurized by the fuel pump 131. The fuel sucked and pressurized by the fuel pump 131 is adjusted to a predetermined pressure in the fuel tank 130 by a pressure regulator 132 provided in parallel with the fuel pump 131. Then, the fuel adjusted to the predetermined pressure is supplied to the fuel injection device (injector) 134 via the fuel piping 133, and is injected into each cylinder 150. In addition, the excess fuel generated by the pressure adjustment of the pressure regulator 132 is discharged from the pressure regulator 132 to the fuel tank 130.

[0024] The fuel injection control unit 82 (see Figure 3 )'s fuel injection pulse (control signal) is used to control the fuel injection device 134.

[0025] The cylinder pressure sensor (also called combustion pressure sensor) 140 is provided in a cylinder head (not shown) facing the combustion chamber of the internal combustion engine 100. The cylinder pressure sensor 140 is provided in the cylinder 150, and detects the pressure (combustion pressure) in the cylinder 150. For example, a piezoelectric or strain gauge pressure sensor is applied to the cylinder pressure sensor 140. Thus, the cylinder pressure in the cylinder 150 can be detected.

[0026] Each cylinder 150 is equipped with an exhaust valve 152 and an exhaust manifold 160. When the exhaust valve 152 is opened, exhaust gas is discharged from the cylinder 150 to the exhaust manifold 160. The exhaust manifold 160 discharges the combusted gas (exhaust gas) to the outside of the cylinder 150. A three-way catalyst 161 is provided on the exhaust side of the exhaust manifold 160. The three-way catalyst 161 purifies the exhaust gas. The exhaust gas purified by the three-way catalyst 161 is discharged into the atmosphere.

[0027] The upstream air-fuel ratio sensor 162 is provided on the upstream side of the three-way catalyst 161. The upstream air-fuel ratio sensor 162 outputs a signal corresponding to the oxygen concentration associated with the air-fuel ratio of the exhaust gas exhausted from each cylinder 150. The upstream air-fuel ratio sensor 162 of the present embodiment is a so-called linear air-fuel ratio sensor, which detects the air-fuel ratio (oxygen concentration) of the exhaust gas exhausted from each cylinder 150 as a voltage that changes in proportion (linearly) to the air-fuel ratio.

[0028] In addition, a downstream air-fuel ratio sensor 163 is provided on the downstream side of the three-way catalyst 161. The downstream air-fuel ratio sensor 163 outputs a signal corresponding to the oxygen concentration associated with the air-fuel ratio of the exhaust gas purified by the three-way catalyst 161. The downstream air-fuel ratio sensor 163 of the present embodiment is a so-called O2 sensor, which outputs a detection signal that changes in a binary manner corresponding to richer (rich) and thinner (lean) than the theoretical air-fuel ratio.

[0029] Spark plugs 200 are respectively provided at the positions facing the respective combustion chambers of the respective cylinders 150. Spark plugs 200 generate sparks by discharge (ignition), and the sparks ignite the mixed gas of air and fuel in cylinder 150. As a result, explosive combustion occurs in cylinder 150, and piston 170 is pushed downward. As piston 170 is pushed downward, crankshaft 123 rotates. Ignition coil 300 that generates (boosts) the discharge voltage to be supplied to spark plug 200 is connected to spark plug 200.

[0030] Output signals from various sensors such as the throttle valve opening sensor 113a, the flow sensor 114, the crank angle sensor 121, the accelerator position sensor 126, the water temperature sensor 122, and the cylinder pressure sensor 140 are input to the internal combustion engine control device 1 (hereinafter referred to as "control device 1"). The control device 1 controls various items such as the amount of air passing through the throttle valve 113, the amount of fuel injected by the fuel pump 131 and the fuel injection device 134, and the ignition timing of the ignition coil 300 to the spark plug 200 based on the signals from the various sensors.

[0031] [spark plug] Next, we will refer to Figure 2 Spark plug 200 will be described. Figure 2 It is a partially enlarged view for explaining the spark plug 200 .

[0032] like Figure 2 As shown, spark plug 200 includes a center electrode 210 and an outer electrode 220. Center electrode 210 is supported on a spark plug base (not shown) via an insulator 230. Thus, center electrode 210 is insulated. Outer electrode 220 is grounded.

[0033] When the ignition coil 300 (refer to Figure 1 ) generates a voltage, a predetermined voltage (e.g., 20,000 V to 40,000 V) is applied to the center electrode 210. When the predetermined voltage is applied to the center electrode 210, discharge (ignition) occurs between the center electrode 210 and the outer electrode 220. Then, the spark generated by the discharge ignites the mixed gas (gas component) of air and fuel in the cylinder 150.

[0034] In addition, the voltage at which discharge (ignition) is generated due to insulation breakdown of the gas components in the cylinder 150 varies depending on the state of the gas (mixed gas in the cylinder) between the center electrode 210 and the outer electrode 220 and the cylinder pressure of the cylinder 150. The voltage generated by such discharge is called insulation breakdown voltage.

[0035] The discharge control (ignition control) of the spark plug 200 is performed by an ignition control unit 83 (see Figure 3 )implement.

[0036] [Hardware structure of the control device] Next, the overall configuration of the hardware of the control device 1 will be described.

[0037] like Figure 1 As shown, the control device 1 has an analog input unit 10, a digital input unit 20, an A / D (analog / digital) conversion unit 30, a RAM (Random Access Memory) 40, an MPU (Micro-Processing Unit) 50, a ROM (Read Only Memory) 60, an I / O (Input / Output) port 70 and an output circuit 80.

[0038] Analog output signals from various sensors such as the throttle opening sensor 113a, the flow sensor 114, the accelerator position sensor 126, the upstream air-fuel ratio sensor 162, the downstream air-fuel ratio sensor 163, the cylinder pressure sensor 140 and the water temperature sensor 122 are input to the analog input unit 10.

[0039] The analog input unit 10 is connected to an A / D converter 30. The analog output signals from various sensors input to the analog input unit 10 are converted into digital signals by the A / D converter 30 after performing signal processing such as noise removal. Then, the digital signals converted by the A / D converter 30 are stored in the RAM 40.

[0040] The digital output signal from the crank angle sensor 121 is input to the digital input section 20. The digital input section 20 is connected to the I / O port 70. The digital output signal input to the digital input section 20 is stored in the RAM 40 via the I / O port 70.

[0041] Each output signal stored in the RAM 40 is subjected to calculation processing by the MPU 50 .

[0042] The MPU 50 processes the output signals stored in the RAM 40 according to the control program by executing the control program (not shown) stored in the ROM 60. The MPU 50 calculates control values ​​for specifying the operation amounts of the various actuators (e.g., the throttle valve 113, the fuel injection device 134, the fuel pump 131, the ignition coil 300, etc.) driving the internal combustion engine 100 according to the control program, and temporarily stores the control values ​​in the RAM 40.

[0043] The control values ​​for defining the operation amounts of the respective actuators stored in the RAM 40 are output to the output circuit 80 via the I / O port 70 .

[0044] The driving device of the throttle valve 113 , the fuel pump 131 , the fuel injection device 134 , and the ignition coil 300 are electrically connected to the output circuit 80 .

[0045] [Functional blocks of control device] Next, we will refer to Figure 3 The functional structure of the control device 1 will be described. Figure 3 It is a functional block diagram for explaining the functional structure of the control device 1 .

[0046] like Figure 3 As shown, the control device 1 is provided with the above-mentioned output circuit 80. In the present embodiment, the output circuit 80 includes an overall control unit 81, a fuel injection control unit 82, and an ignition control unit 83. In addition, the control device 1 is provided with a cylinder discrimination unit 84, an angle information generation unit 85, a rotation speed information generation unit 86, an intake air amount measurement unit 87, a load information generation unit 88, a water temperature measurement unit 89, and a voltage measurement unit 90.

[0047] The angle information generating unit 85 measures the crank angle of the crankshaft 123 based on the digital output signal of the crank angle sensor 121. The cylinder discriminating unit 84 discriminates whether the current crank angle measured by the angle information generating unit 85 corresponds to the stroke of each cylinder 150 of the internal combustion engine 100 (for example, Figure 6 The speed information generating unit 86 measures the engine speed.

[0048] The intake air amount measuring unit 87 measures the intake air amount of the air sucked into the cylinder 150 based on the output signal of the flow sensor 114. The load information generating unit 88 calculates the driver's required torque based on the output signal of the accelerator position sensor 126. The water temperature measuring unit 89 measures the temperature of the engine cooling water. The voltage measuring unit 90 measures Figure 4 The voltage of DC power supply 330 (battery of internal combustion engine 100) is shown.

[0049] [Overall Control Department] The overall control unit 81 includes an ignition timing setting unit 811 , a request setting unit 812 , an adjustment unit 813 , an ignition device temperature estimating unit 814 , a fuel injection amount setting unit 815 , and a fuel injection timing setting unit 816 .

[0050] The ignition timing setting unit 811 optimally calculates the ignition timing IGADV, which is a main operation variable of the internal combustion engine 100, based on the operating state of the internal combustion engine 100 obtained from the outputs of various sensors such as the output signal S2 of the cylinder pressure sensor 140.

[0051] The required setting unit 812 calculates the required energization time (required energization amount) based on the operating state of the internal combustion engine 100 obtained from the outputs of various sensors such as the rotation speed NE and the power supply voltage VB of the internal combustion engine 100. The required energization time is the required energization time for the primary side coil 310 (see Figure 5 )The time when the power is on.

[0052] The adjustment unit 813 calculates the current to be supplied to the primary side coil 310 (see FIG. 1 ) of the ignition coil 300 based on the temperature value (ignition coil temperature) TC related to the ignition device obtained from the ignition device temperature estimation unit 814 and the required energization time (required energization amount) obtained from the required setting unit. Figure 5 )The power-on time of power-on.

[0053] The ignition device temperature estimation unit 814 calculates a temperature value (ignition coil temperature) TC related to the ignition device using a neural network model that uses a preselected explanatory variable as an input.

[0054] Fuel injection amount setting unit 815 optimally calculates the fuel injection amount as a main operation amount of internal combustion engine 100 based on the operating state of internal combustion engine 100 obtained from outputs of various sensors such as rotation speed NE and power supply voltage VB of internal combustion engine 100 .

[0055] The fuel injection timing setting unit 816 optimally calculates the opening and closing timing of the fuel injection valve in the fuel injection device 134 based on the operating state of the internal combustion engine 100 obtained from the outputs of various sensors such as the rotational speed NE of the internal combustion engine 100 and the fuel injection amount obtained from the fuel injection amount setting unit 815.

[0056] [Fuel injection control unit] The fuel injection control unit 82 controls the timing and duration of energization to the fuel injection valve. The fuel injection control unit 82 generates a fuel injection pulse based on the fuel control information input from the overall control unit 81. The fuel injection control unit 82 provides the generated fuel injection pulse to the fuel injection control unit 82. The fuel injection device 134 is driven according to the fuel injection pulse.

[0057] The fuel control information includes, for example, the value of the fuel injection amount obtained from the fuel injection amount setting unit 815 , the number of fuel injection executions per combustion cycle of the internal combustion engine 100 , the opening and closing operation timing of the fuel injection valve obtained from the fuel injection timing setting unit 816 , and the like.

[0058] [Ignition control unit] The ignition control unit 83 controls the energization timing and energization time of the ignition coil 300. The ignition control unit 83 calculates the energization start timing (energization start crank angle) of the primary side coil 310 based on the ignition control information input from the overall control unit 81. The energization start timing of the primary side coil 310 is the timing after tracing back the energization time in the time series from the ignition timing when the current supplied to the primary side coil 310 is cut off.

[0059] The ignition control information includes, for example, engine speed information S5, the value of ignition timing (crank angle from spark generation timing to compression top dead center of the internal combustion engine), and the value of energization time obtained from the adjustment unit 813.

[0060] The ignition control unit 83 starts to energize the primary coil 310 based on the calculated energization start time, and outputs an ignition signal SA (see FIG. 1 ) for cutting off the energization to the primary coil 310 based on the ignition time. Figure 4 ). Thus, the spark plug 200 ignites the air-fuel mixture.

[0061] [Circuit including ignition coil] Next, we will refer to Figure 4 The circuit including the ignition coil is described. Figure 4 is a diagram showing a circuit including an ignition coil.

[0062] Figure 4 The illustrated circuit 500 includes an ignition coil 300. The ignition coil 300 includes a primary side coil 310 wound with a prescribed number of turns and a secondary side coil 320 wound with a greater number of turns than the primary side coil 310.

[0063] One end of the primary coil 310 is connected to a DC power supply 330. Thus, a predetermined voltage (e.g., 12V) is applied to the primary coil 310. The other end of the primary coil 310 is connected to a drain (D) terminal of an igniter (power-on control circuit) 340 and is grounded via the igniter 340. The igniter 340 uses a transistor, a field effect transistor (FET), or the like.

[0064] The gate (G) terminal of the igniter 340 is connected to the ignition control unit 83 via the temperature switch unit 350. The purpose of providing the temperature switch unit 350 is to prevent the ignition coil 300 from being damaged due to overheating. When the temperature of the ignition coil 300 reaches a predetermined threshold value A (first temperature) or above, the temperature switch unit 350 cuts off the ignition signal SA output from the ignition control unit 83 to the igniter 340.

[0065] When the temperature switch unit 350 cuts off the ignition signal SA, the primary coil 310 is deenergized, thereby preventing the igniter 340 from overheating. When the temperature detected by the temperature detection unit 351 is lower than the first temperature, the ignition signal SA output from the ignition control unit 83 is input to the gate (G) terminal of the igniter 340.

[0066] When the ignition signal SA is input to the gate (G) terminal of the igniter 340, the drain (D) terminal and the source (S) terminal of the igniter 340 are in a power-on state, and current flows between the drain (D) terminal and the source (S) terminal. Thus, the ignition signal SA is output from the ignition control unit 83 to the primary side coil 310 of the ignition coil 300 via the igniter 340. As a result, current flows through the primary side coil 310 to accumulate power (electric energy).

[0067] When the output of the ignition signal SA from the ignition control unit 83 stops, the current flowing through the primary coil 310 is cut off. As a result, a high voltage corresponding to the coil turn ratio with respect to the primary coil 310 is generated in the secondary coil 320.

[0068] The high voltage generated in the secondary coil 320 is applied to the center electrode 210 of the spark plug 200 (see Figure 2 ). As a result, a potential difference is generated between the center electrode 210 and the outer electrode 220 of the spark plug 200. When the potential difference generated between the center electrode 210 and the outer electrode 220 is greater than the insulation breakdown voltage Vm of the surrounding gas (the mixed gas in the cylinder 150), the gas components are broken down by insulation, and discharge is generated between the center electrode 210 and the outer electrode 220. As a result, the fuel (mixed gas) is ignited (burned). The circuit 500 having the spark plug 200 and the ignition coil 300 corresponds to the ignition device involved in the present invention.

[0069] The discharge path generated between the center electrode 210 and the outer electrode 220 reaches a high temperature of several thousand degrees C. Since the discharge path is in contact with the surrounding gas and the electrodes 210, 220, the heat energy generated by the discharge is distributed to the surrounding gas and the electrodes 210, 220. Then, the heat energy distributed to the surrounding gas heats (preheats) the surrounding gas and the electrodes 210, 220, thereby promoting ignition.

[0070] [Electrode temperature, minimum ignition energy and air-fuel ratio] Next, we will refer to Figure 5 The relationship among the temperature of the electrode of the spark plug 200, the minimum ignition energy, and the air-fuel ratio will be described. Figure 5 is a graph illustrating the relationship between electrode temperature, minimum ignition energy, and air-fuel ratio.

[0071] Figure 5 The value of the air-fuel ratio corresponding to the value of the minimum ignition energy is shown. Figure 5 In the figure, the up and down directions represent the voltage scale values ​​corresponding to the minimum ignition energy of the mixed gas. Figure 5 In the figure, the left and right directions represent the air-fuel ratio scale values ​​corresponding to the air-fuel ratio of the mixed gas. Figure 5 The air-fuel ratio P1 shown in is a value of the air-fuel ratio corresponding to a prescribed value of the minimum ignition energy that can ignite the mixed gas when the electrode temperature of the spark plug is relatively low (e.g., -25 degrees C). On the other hand, the air-fuel ratio P2 is a value of the air-fuel ratio corresponding to a prescribed value of the minimum ignition energy that can ignite the mixed gas when the electrode temperature of the spark plug is relatively high (e.g., -7 degrees C).

[0072] like Figure 5 As shown, in the internal combustion engine 100, the greater the air-fuel ratio (the leaner the fuel), the higher the value of the minimum ignition energy of the mixed gas, and thus it is difficult to ignite the mixed gas by the discharge (ignition) from the spark plug. In addition, the lower the electrode temperature of the spark plug, the higher the minimum ignition energy value of the mixed gas, and thus it becomes more difficult to ignite the mixed gas by the discharge (ignition) from the spark plug.

[0073] For example, it is assumed that when the electrode temperature of the spark plug is low, the same value as the minimum ignition energy corresponding to the air-fuel ratio P2 when the electrode temperature of the spark plug is high is obtained. In this case, if the air-fuel ratio is not set to a value less than the air-fuel ratio P2 (richer fuel), that is, the air-fuel ratio P1, the discharge (ignition) from the spark plug 200 cannot exceed the minimum ignition energy. Therefore, in the past, a rich air-fuel ratio (P1) was set in the fuel injection control unit 82 on the premise that the temperature of the electrode of the spark plug 200 is always low, as a setting with a safety margin that does not cause misfires and other defects in the internal combustion engine 100. As a result, in the internal combustion engine 100, the generation of hydrocarbons (HC) during combustion increases as the proportion of fuel in the mixed gas increases.

[0074] On the other hand, the higher the temperature of the electrode of the spark plug 200 during cold start (see Figure 5 The lower the minimum ignition energy for igniting the mixed gas, the lower the minimum ignition energy for igniting the mixed gas. Therefore, even if the air-fuel ratio is increased (the fuel becomes leaner), the discharge (ignition) from the spark plug can exceed the minimum ignition energy, thereby igniting the mixed gas. As a result, the generation of hydrocarbons (HC) in the internal combustion engine 100 can be reduced. Therefore, in the internal combustion engine 100, as described below, the temperature of the electrode of the spark plug 200 during cold start is increased before the discharge (ignition). As a result, the air-fuel ratio during cold start can be increased, thereby suppressing the generation of hydrocarbons (HC).

[0075] [Multiple ignitions] Next, refer to Figure 6 Indicates multiple fires. Figure 6 is an example of a discharge waveform for multiple ignitions.

[0076] It is known that in an internal combustion engine, a large amount of hydrocarbons (HC) are generated during a cold start when the temperature of each part is the same as the outside air temperature. One of the reasons why hydrocarbons are generated during a cold start is that the temperature in the cylinder is low, resulting in a decrease in the fuel vaporized by the ignition timing, and the air-fuel ratio of the mixed gas in the cylinder becomes larger (the fuel becomes leaner). In this case, the required ignition energy increases, and ignition failure and flameout (misfire) increase, and hydrocarbons increase. In other words, the main cause of hydrocarbon generation is misfire.

[0077] Misfire occurs when the flame core generated by ignition fails to grow and extinguishes. In order to grow the flame core and suppress misfire, it is necessary to suppress the flow of light from between the electrodes 210 and 220 facing the spark plug 200 (see Figure 2) of the discharge path and the flame core to the electrodes 210 and 220. For example, when multiple ignitions are performed in the ignition device and the electrodes 210 and 220 of the spark plug 200 are preheated, the temperature difference between the discharge path and the flame core and the electrodes 210 and 220 is reduced. As a result, the amount of heat transferred from the discharge path and the flame core to the electrodes 210 and 220 can be suppressed.

[0078] like Figure 6 As shown, by repeatedly turning on and off the ignition signal, multiple discharges are added and multiple ignitions are performed. As a result, the temperature of the electrodes 210 and 220 of the spark plug 200 can be increased before the ignition of the main ignition of the spark plug 200 (discharge at the ignition timing). The multiple ignitions performed by the additional discharges can be performed at a timing that does not overlap with the ignition timing of the main ignition. For example, at least during the period from the ignition of the main ignition to the start of fuel injection (at the Figure 6 In an embodiment of the present invention, multiple ignitions are performed by additional discharge during the period from the expansion stroke to the intake stroke.

[0079] [Ignition coil temperature and discharge energy] Next, we will refer to Figure 7 The temperature and discharge energy of the ignition coil 300 are described. Figure 7 This is a conceptual diagram showing the relationship between the supplyable discharge energy, the required discharge energy, and the difference between them with respect to the temperature of the ignition coil.

[0080] Figure 7 The horizontal axis of the graph shown in FIG. 1 is the ignition coil 300 (refer to Figure 4 ) temperature TC (hereinafter referred to as "ignition coil temperature TC"), and the vertical axis is the ignition performance expressed in megajoules (mJ) of the unit of discharge energy. The ignition performance includes the required discharge energy set based on the above-mentioned minimum ignition energy required to ignite the mixed gas, for example, according to the operating state of the internal combustion engine 100, and the supplyable discharge energy which is the upper limit value for making the ignition coil temperature TC below the rated temperature. As described above, the required discharge energy is affected by the air-fuel ratio of the mixed gas, the exhaust gas recirculation amount, etc. In addition, the supplyable discharge energy shows a tendency that the farther the ignition coil temperature TC is from the rated temperature, for example, Figure 7 When the rated temperature is set to 120 degrees C, when the ignition coil temperature TC decreases to 80 degrees C or 40 degrees C below the rated temperature, the value of the discharge energy that can be supplied increases as the temperature decreases.

[0081] Since a high current of, for example, about 15A flows through the primary side coil 310 and the igniter 340 of the ignition coil 300, instantaneous heating is repeated each time ignition is performed. Therefore, the discharge energy A that can be supplied is set based on the ignition coil temperature TC, and the energization of the ignition coil 300 is controlled based on the discharge energy A that can be supplied, so that the temperature of the primary side coil 310 and the igniter 340 of the ignition coil 300 does not exceed the preset rated temperature (the heat resistance temperature of each component in design). When the ignition coil temperature TC rises and approaches the rated temperature, the discharge energy A that can be supplied by the ignition coil 300 decreases.

[0082] The required discharge energy B is mainly affected by the state of the mixed gas near the spark plug electrode, that is, the air-fuel ratio and the intake air flow. When the air-fuel ratio of the mixed gas is close to the theoretical air-fuel ratio (stoichiometric ratio), the required discharge energy B is almost the minimum value. On the other hand, as the air-fuel ratio moves away from the theoretical air-fuel ratio, the required discharge energy B becomes higher.

[0083] Usually, in Figure 7 In FIG. 1 , the slopes of the temperature axis of the ignition coil temperature TC shown in the left and right directions are different for the supplyable discharge energy A and the required discharge energy B. Figure 7 As shown, the supplyable discharge energy A and the required discharge energy B intersect. At this time, for example, when the temperature of the point where the two discharge energies A and B intersect is higher than the rated temperature (designed operating temperature range) of the ignition coil 300, the discharge energy A that is higher than the required discharge energy B can be output from the ignition coil 300 without ever exceeding the rated temperature. In this case, the ignition performance of the internal combustion engine 100 is always satisfied without being limited by the temperature of the ignition coil 300.

[0084] On the other hand, in order to improve the fuel efficiency of the vehicle, for example, in the case of implementing a lean burn technology for operating the internal combustion engine by burning a mixed gas having a greater than theoretical air-fuel ratio (fuel is leaner), since the required discharge energy B increases as the air-fuel ratio of the mixed gas moves away from the theoretical air-fuel ratio, the temperature at the point where the two discharge energies A and B intersect may be lower than the rated temperature (within the operating temperature range) of the ignition coil 300. In this case, it is difficult to continuously supply the required discharge energy B exceeding the supplyable discharge energy A to the ignition coil 300 on the high temperature side higher than the temperature at the intersection point. Therefore, since the supplyable discharge energy A is insufficient on the high temperature side higher than the temperature at the point where the two discharge energies A and B intersect, the feasibility of the so-called fuel efficiency improvement technology of the internal combustion engine 100, such as lean burn and exhaust gas recirculation, is limited.

[0085] Hereinafter, a difference value between the available discharge energy A and the required discharge energy B when the available discharge energy A is smaller than the required discharge energy B is defined as an ignition performance deficiency amount C.

[0086] [Relationship between conventional ignition coil temperature and discharge energy] Next, we will refer to Figure 8 The relationship between the temperature and discharge energy of a conventional ignition coil will be described. Figure 8 This is a conceptual diagram showing the relationship between the temperature and discharge energy of a conventional ignition coil.

[0087] Figure 8 The horizontal axis of the graph shown in FIG. 1 is the ignition coil temperature TC, and the vertical axis is the ignition performance. Figure 8 The thick line in the figure is the discharge energy output from the ignition coil in the past. Figure 8 As shown, in the conventional ignition device (for example, refer to Japanese Patent Laid-Open No. 2000-054941), the value of the ignition coil temperature TC is unclear. Therefore, for example, when Figure 8 When 120degC is set as the rated temperature, the discharge energy A2 that can be supplied at this 120degC is always applied as the output limit value of the discharge energy of the ignition coil. That is, in the conventional ignition device, the discharge energy A2 that can be supplied does not change substantially with respect to the change of the ignition coil temperature TC. In other words, the conventional ignition device is designed so that when ignition is performed in a state where the air-fuel ratio is close to the theoretical air-fuel ratio, the temperature of the point where the discharge energy A2 that can be supplied and the required discharge energy B intersect is higher than the rated temperature of the ignition coil. Therefore, at least under the condition of ignition in a state where the air-fuel ratio is close to the theoretical air-fuel ratio, the ignition performance of the internal combustion engine 100 to which the conventional ignition device is applied is always satisfied without being limited by the temperature of the ignition coil 300.

[0088] However, when implementing lean burn and exhaust gas recirculation in which part of the exhaust gas after combustion is introduced and re-intaken, as described above, the required discharge energy B is higher than when the mixed gas is ignited in a state close to the theoretical air-fuel ratio, so the temperature of the point where the two discharge energies A and B intersect is lower than the rated temperature. In this case, the ignition performance deficiency C increases as the ignition coil temperature TC rises on the high temperature side higher than the temperature of the point where the supplyable discharge energy A and the required discharge energy B intersect, so misfire may occur. Due to this situation, in an internal combustion engine using a conventional ignition device, there is a limitation that lean burn and exhaust gas recirculation are implemented only under low load conditions where the amount of air flowing into the cylinder is reduced and the required discharge energy B is reduced.

[0089] [Relationship between the temperature and discharge energy of the ignition coil involved in the present invention] Next, we will refer to Fig. 9 The relationship between the temperature and discharge energy of the ignition coil according to the present invention will be described. Fig. 9This is a conceptual diagram showing the relationship between the temperature of the ignition coil and the discharge energy when the present invention is applied.

[0090] Fig. 9 The horizontal axis of the graph shown in FIG. 1 is the ignition coil temperature TC, and the vertical axis is the ignition performance. Fig. 9 The thick line in FIG. 1 is the discharge energy output from the ignition coil 300. Fig. 9 As shown, in this embodiment, when the temperature of the ignition coil 300 is higher than the temperature of the point where the suppliable discharge energy A and the required discharge energy B intersect, the suppliable discharge energy A is prioritized over the required discharge energy B.

[0091] That is, in the present embodiment, when the ignition coil temperature TC is higher than the temperature at the point where the supplyable discharge energy A and the required discharge energy B intersect, the discharge energy of the ignition coil 300 is set to the supplyable discharge energy A. Thus, when the temperature becomes higher than the temperature at the point where the supplyable discharge energy A and the required discharge energy B intersect, the discharge energy of the ignition coil 300 gradually decreases as the ignition coil temperature TC rises.

[0092] In addition, in the present embodiment, on the high temperature side higher than the temperature at the point where the supplyable discharge energy A and the required discharge energy B intersect, the fuel injection amount can be increased so that ignition is performed in a state where the air-fuel ratio is close to the theoretical air-fuel ratio, thereby substantially reducing the value of the required discharge energy B. That is, in the present embodiment, the insufficient ignition performance due to the reduction of the discharge energy is compensated by improving the combustibility of the mixed gas. Thus, by reducing the value of the required discharge energy B, the required ignition performance can be satisfied while preventing the ignition coil 300 from overheating. As a result, misfires can be suppressed. In addition, in the present embodiment, on the low temperature side lower than the temperature at the point where the supplyable discharge energy A and the required discharge energy B intersect, the value of the required discharge energy B can be increased to a value higher than that of the conventional ignition device to implement lean combustion and exhaust gas recirculation. Thus, even in a high load condition where the required discharge energy B is the highest due to an increase in the amount of air flowing into the cylinder, etc., lean combustion and exhaust gas recirculation can be implemented more than the conventional ignition device while taking into account both preventing misfires and preventing overheating of the ignition coil 300. As a result, the fuel efficiency of the vehicle can be improved.

[0093] As described above, in this embodiment, the discharge energy of the ignition coil 300 is changed according to the temperature of the ignition coil 300. Therefore, it is necessary to grasp the temperature of the ignition coil 300 (the temperature of the ignition device). For example, the temperature of the ignition coil 300 can be detected by providing a temperature sensor.

[0094] However, when the temperature sensor is provided in the ignition coil 300, the cost increases and the housing becomes larger as the number of detection elements and wiring increases. Therefore, in the present embodiment, the temperature of the ignition coil 300 is estimated without providing a temperature sensor. Thus, it is possible to suppress misfires while suppressing the increase in cost and the enlargement of the housing.

[0095] [Ignition and fuel injection control processing] Next, we will refer to Fig.10 The ignition and fuel injection control process according to the first embodiment will be described. Fig.10 This is a flowchart showing the ignition and fuel injection control process according to the first embodiment.

[0096] The ignition and fuel injection control process starts with the start of the internal combustion engine 100 (engine start). First, the overall control unit 81 obtains the power supply voltage VB (S1). Next, the overall control unit 81 obtains the speed NE of the internal combustion engine 100 (S2). Next, the ignition timing setting unit 811 of the overall control unit 81 sets the ignition timing of the internal combustion engine 100 according to the speed NE (S3).

[0097] Next, the overall control unit 81 sets the explanatory variables of the neural network model (S4). In the present embodiment, a plurality of explanatory variables pre-selected from various parameter groups including the operating state of the internal combustion engine 100 associated with parameters related to the temperature of the ignition coil 300 and the thermal balance inside and outside the ignition device are set by detection, estimation or calculation.

[0098] Next, the ignition device temperature estimation unit 814 of the overall control unit 81 inputs the explanatory variables to the first neural network model and estimates the temperature value (ignition coil temperature) TC related to the ignition device (S5). The explanatory variables input to the first neural network model include at least the power supply voltage VB and the rotation speed NE.

[0099] Next, the adjustment unit 813 of the overall control unit 81 inputs the explanatory variables to the second neural network model and outputs the limited energization time corresponding to the ignition coil temperature TC (S6). The explanatory variables input to the second neural network model include at least the power supply voltage VB, the rotation speed NE, and the ignition coil temperature TC.

[0100] The limited energization time is the upper limit of the time during which current is supplied to the ignition coil 300 (primary coil 310 ), and corresponds to the above-mentioned supplyable discharge energy A. Therefore, the limited energization time may also be referred to as a limited energization amount.

[0101] Next, the requirement setting unit 812 of the overall control unit 81 inputs the explanatory variables to the third neural network model and outputs the required energization time corresponding to the operating state of the internal combustion engine 100 (S7). The explanatory variables input to the third neural network model include at least the power supply voltage VB and the rotation speed NE.

[0102] The required energization time is the time for energizing the current to the ignition coil 300 (primary coil 310 ) in order to satisfy the required discharge energy B. Therefore, the required energization time may also be referred to as the required energization amount.

[0103] Next, the adjustment unit 813 of the overall control unit 81 determines whether the required power-on time is greater than the limited power-on time (S8). When it is determined in step S8 that the required power-on time is not greater than the limited power-on time (if S8 is determined to be "No"), the adjustment unit 813 sets the required power-on time for the power-on time of the ignition coil 300 (hereinafter referred to as "ignition coil power-on time") (S9).

[0104] On the other hand, when it is determined in step S8 that the requested energization time is greater than the limited energization time (if S8 is determined to be YES), the adjustment unit 813 sets the limited energization time to the ignition coil energization time ( S10 ).

[0105] After the processing of step S9 or step S10, the fuel injection amount setting unit 815 of the overall control unit 81 sets the target air-fuel ratio of the fuel injection control unit 82 to the stoichiometric ratio according to the ignition coil temperature TC (S11). In the processing of step S11, for example, when the ignition performance is reduced due to the setting of the limited energization time for the ignition coil energization time, the value of the target air-fuel ratio associated with the determination of the fuel injection amount Tinj in the fuel injection control unit 82 is set to the theoretical air-fuel ratio or a value close to the theoretical air-fuel ratio at which the required discharge energy B becomes the minimum value according to the ignition coil temperature TC as described above. Thus, misfire can be suppressed by reducing the value of the minimum ignition energy of the mixed gas (reducing the required discharge energy B).

[0106] Next, the fuel injection control unit 82 causes the fuel injection device 134 to perform fuel injection (S12). Specifically, the fuel injection control unit 82 supplies a drive current (drive voltage) corresponding to the fuel injection amount Tinj based on the target air-fuel ratio set in step S11 and the fuel injection timing set by the fuel injection timing setting unit 816 to the fuel injection device 134.

[0107] Next, the ignition control unit 83 causes the ignition device to perform ignition (S13). Specifically, the ignition control unit 83 outputs an ignition signal SA corresponding to the ignition coil energization time set in steps S9 and S10, the ignition timing IGADV set in step S3, and the speed NE to the ignition coil 300. After the processing of step S13, the overall control unit 81 returns the processing to step S1.

[0108] [Neural network model] Next, we will refer to Fig.11 , Fig.12 , Fig.13 The neural network model of this embodiment is described. Fig.11 It is a conceptual diagram showing the weights and biases of each neuron that constitute each neural network model, including a first neural network model that uses the ignition coil temperature TC as a target variable, a second neural network model that uses the limited power-on time as a target variable, and a third neural network model that uses the required power-on time as a target variable. Fig.12 This is a diagram illustrating a method for realizing calculations of target variables using a neural network model according to the present embodiment. Fig.13 1 is a conceptual diagram showing a neural network model used for ignition and fuel injection control processing in the first embodiment.

[0109] The neural network model is a mathematical model that simulates the mechanism of the neural circuit of the human brain. In this embodiment, the neural network model is composed of a multi-layer neural network model having an input layer for inputting explanatory variables, an output layer for outputting target variables, and an intermediate layer connected between the input layer and the output layer. In so-called machine learning, neural network models are often used as a means of deep learning. For example, the error back propagation method can be applied to machine learning algorithms. In addition, although the neural network model is used in this embodiment, as long as the ignition coil temperature TC can be estimated by machine learning, or the limited power-on time and the required power-on time can be determined, it is not limited to this example.

[0110] like Fig.11 As shown, weights w and biases b are set for each neuron (unit) constituting the neural network model. Inputs a1 to an are input to n neurons respectively and multiplied by weights w1 to wn set for each neuron. Then, in the neurons of the next layer, the inputs a1 to an multiplied by weights w1 to wn are added (combined), and the output z is obtained after bias b is assigned to the addition result. The output of the neuron in the next layer is a represented by the function f(z).

[0111] In addition, a function called an activation function is defined for each neuron. In the activation function, a logistic function (sigmoid function) and a ramp function (ReLU (rectified linear unit: Rectified Linear Unit) function) are appropriately set. Fig.11 An example is shown in which the neuron is activated when the input x is greater than 0, and the output y (=f(x)) is closer to 1, and the neuron is deactivated when the input x is less than 0, and the output y is closer to 0. For example, when the input x is "5", the output y of the activation function is "1", and "1" is output from the neuron to the neuron in the next layer.

[0112] like Fig.12 As shown, the middle layer of the multi-layer neural network model is composed of a plurality of layers formed by a plurality of neurons stacked on top of each other. Although a large-scale neural network model configured with a large number of neurons and a large number of middle layers can learn complex input-output relationships and improve the approximate accuracy of the target variable, there is a trade-off between improving the approximate accuracy and the size of the neural network model. Therefore, the neural network model of the vehicle internal combustion engine control device involved in this embodiment is constructed and provided on the basis of a pre-study of a so-called cost-effective compromise point that balances the desired approximate accuracy and the model scale that takes into account the computing processing power, housing size, cost suppression, etc. of the control device 1.

[0113] Therefore, by setting the variable having a causal relationship with the target variable as the teacher data of the explanatory variable in the input layer, and setting the target variable as the teacher data in the output layer, on this basis, using a well-known algorithm such as the error back propagation method to perform machine learning (teacher learning) of weights w and bias b on multiple neurons in the middle layer, the input-output relationship of the neural network model can be approximated with high accuracy. When the explanatory variable used in machine learning is input to the input layer as the teacher data, the completed learning model that implements this learning performs the operation of the input-output relationship based on the learned content, and outputs the value of the target variable as the operation result based on the input explanatory variable.

[0114] Also refer to Fig.10 and Fig.13 The neural network model of the ignition and fuel injection control process according to the first embodiment of the present invention will be described. Fig.13 Shows Fig.10The input-output relationships between the explanatory variables and the target variables of the plurality of neural network models in the ignition and fuel injection control process according to the first embodiment of the present invention are shown. In addition, the ignition and fuel injection control process according to the present embodiment can be configured to use an estimation algorithm that uses a fourth neural network model in the fuel injection control of step S12 and a fifth neural network model in the ignition control of step S13, in addition to the first neural network model, the second neural network model and the third neural network model used in the processes of the above-mentioned steps S5, S6 and S7.

[0115] In the present embodiment, first, in the input layer of the first neural network model that has been learned with the ignition coil temperature TC as the target variable, a plurality of explanatory variables including the power supply voltage VB and the rotational speed NE that have a causal relationship with the ignition coil temperature TC are set, and the ignition coil temperature TC is output from the output layer through the calculation processing in the intermediate layer as described above (step S5). Next, in the input layer of the second neural network model that has been learned with the limited power-on time of the ignition coil 300 as the target variable, a plurality of explanatory variables including the power supply voltage VB and the rotational speed NE that have a causal relationship with the limited power-on time, and the ignition coil temperature TC output from the above-mentioned first neural network model are set, and the limited power-on time is output from the output layer through the calculation processing in the intermediate layer (step S6). In addition, in the input layer of the third neural network model that has been learned with the required power-on time as the target variable, a plurality of explanatory variables including the power supply voltage VB and the rotational speed NE that have a causal relationship with the required power-on time are set, and the required power-on time is output from the output layer through the calculation processing in the intermediate layer (step S7). Next, the limited power-on time output from the second neural network model and the required power-on time output from the third neural network model are set in the comparison operation of the requirement setting unit 812 (step S8), and the ignition coil power-on time is set based on the comparison result of the limited power-on time and the required power-on time (steps S8, S9, S10).

[0116] Next, in the input layer of the fourth neural network model that has been learned with the opening and closing action timing of the fuel injection valve as the target variable, a plurality of explanatory variables are set, including the power supply voltage VB, the rotational speed NE, and the fuel injection amount corresponding to the target air-fuel ratio set according to the ignition coil temperature TC (step S11), which have a causal relationship with the opening and closing action timing of the fuel injection valve. Through the calculation processing in the intermediate layer, the opening and closing action timing of the fuel injection valve corresponding to the crank angle measured by the angle information generating unit 85 is output from the output layer (step S12). Next, in the input layer of the fifth neural network model that has been learned with the power-on indication of the ignition coil, that is, the ignition signal SA output to the igniter 340 as the target variable, a plurality of explanatory variables are set, including the rotational speed NE, the ignition timing IGADV, and the ignition coil power-on time, which have a causal relationship with the ignition signal SA. Through the calculation processing in the intermediate layer, the ignition signal SA corresponding to the crank angle measured by the angle information generating unit 85 is output from the output layer (step S13). As shown in the figure Fig.13 As shown, the first to fifth neural network models can be used to form Fig.10 The ignition and fuel injection control process of the first embodiment is shown.

[0117] [Relationship between target variable and explanatory variables] Next, we will refer to Fig.14 The relationship between the target variable and the explanatory variables in this embodiment will be described. Fig.14 This is a correspondence table showing the relationship between the target variables and the explanatory variables of the first to fifth neural network models according to Embodiment 1. An example of the explanatory variables input for estimating (calculating) each target variable is shown.

[0118] like Fig.14 As shown, when the ignition coil temperature TC of the target variable is estimated in the first neural network model, in addition to the above-mentioned speed NE and power supply voltage VB, variables selected from intake flow, intake pressure, intake temperature, intake humidity, rainfall (rainfall detection), cooling water temperature, related values ​​of cooling wind speed, vehicle speed, ignition timing, ignition coil power-on time (executed value), number of power-ons / power-on cycles, elapsed time after the engine (internal combustion engine) is started, elapsed time after the engine (internal combustion engine) is stopped, and supplyable discharge energy (last calculated value) are input as explanatory variables into the first neural network model, and multiple neurons in the middle layer are caused to perform machine learning.

[0119] In addition to the above-mentioned explanatory variables, explanatory variables that can be further added to the first neural network model include, for example, the combustion pressure detected by the cylinder pressure sensor, the lubricating oil temperature, the value related to the crank angle of each open valve or the crank angle of each closed valve of the intake valve / exhaust valve of the internal combustion engine, the throttle opening, the ignition coil temperature TC (the previous value), the ignition coil power-on time, the air-fuel ratio feedback correction coefficient, the downstream air-fuel ratio sensor (O2 sensor) voltage, the upstream air-fuel ratio sensor (linear air-fuel ratio sensor) voltage, the value related to the properties of the fuel supplied to the internal combustion engine (octane number, etc.), the operating state of the radiator fan, the torque, the intake amount, the fuel injection amount, the air-fuel ratio or equivalence ratio, the value of the pressure in the exhaust pipe related to the exhaust gas recirculation, etc. Some or all of these variables can be selected based on the size of the causal relationship with the ignition coil temperature TC as the target variable, the size of the neural network model as described above, the ease of obtaining variables in the control device 1, etc., and the required variables can be set as the explanatory variables of the first neural network model.

[0120] [Explanatory variables] Next, we will refer to Fig.15 A method of selecting explanatory variables for estimating the ignition coil temperature TC will be described. Fig.15 This is a table showing an example of variables related to influencing factors to be examined when selecting explanatory variables for estimating the ignition coil temperature TC according to the first embodiment.

[0121] The factors affecting the change of the ignition coil temperature TC include factors related to the internal heating of the ignition coil and factors related to external heat conduction. Fig.15 The absolute value of the correlation coefficient between each variable shown in and the ignition coil temperature TC is examined. Then, for example, variables with larger correlation coefficients are selected in order as explanatory variables of the first neural network model.

[0122] The internal heating of the ignition coil includes the heating caused by the secondary current, the heating caused by the primary current and the heating caused by the igniter 340 (refer to Figure 4 ) in the ignition coil. This heat is generated by the power loss in the internal circuit of the ignition coil. Therefore, for each internal heat, a variable with a larger correlation coefficient is selected as the explanatory variable. As variables with a larger correlation coefficient with the heat caused by the secondary current, the speed NE, intake flow rate, intake pressure, mixture air-fuel ratio, ignition timing, ignition coil power-on time / number of power-on times / cycles can be listed. As variables with a larger correlation coefficient with the heat caused by the primary current and igniter, the speed NE, power supply voltage VB, ignition coil power-on time / number of power-on times / cycles can be listed.

[0123] External heat conduction of the ignition coil occurs at the contact portion outside the housing of the ignition coil 300. For an ignition coil configured in a form adjacent to a spark plug in each cylinder of the internal combustion engine 1, objects that are in direct contact with the ignition coil 300 are, for example, air (atmosphere), a spark plug, and a cylinder head. Therefore, for each object that is in direct contact with the ignition coil 300, a variable with a large correlation coefficient is selected as an explanatory variable. For example, variables with a large correlation coefficient with external heat conduction can be listed as: intake air temperature, intake air humidity, rainfall, cooling water temperature, lubricating oil temperature, cooling wind speed, vehicle speed, mixed gas air-fuel ratio, cylinder number, time elapsed after the engine (internal combustion engine) is started, and time elapsed after the engine (internal combustion engine) is stopped.

[0124] In the present embodiment, an example is described in which the required energization amount and the limited energization amount are determined and the energization amount of the ignition coil is adjusted when a spark is generated by discharge (ignition) and the mixture is ignited. The discharge (ignition) can be listed as: intermittent discharge for one combustion cycle of the internal combustion engine 100 (one ignition is performed at each compression top dead center for every two crank rotations), or discharge and ignition are performed at each compression top dead center and exhaust top dead center. In addition, the present invention can be applied to the case where multiple additional discharges are performed at the spark plug in addition to the ignition at the top dead center (the case where the above-mentioned multiple ignitions are performed). That is, based on the total amount of required energization amount and limited energization amount for one combustion cycle of the internal combustion engine 100, the energization amount of each ignition coil in the ignition at the compression top dead center, the ignition per rotation, or the multiple ignitions can be adjusted separately. For example, the energization time of the ignition coil at the compression top dead center may be set based on the required energization amount, and each energization time of the ignition coil for discharge at the exhaust top dead center or discharge at the multiple ignitions may be set by dividing the value obtained by subtracting the required energization amount from the total amount of limited energization amount for one combustion cycle of the internal combustion engine 100 according to the predetermined number of discharges at the exhaust top dead center or discharges at the multiple ignitions. Fig. 9 The discharge at the exhaust top dead center or the discharge at the multiple ignition is performed on the lower temperature side of the point where the supplyable discharge energy A and the required discharge energy B intersect, where the temperature is lower.

[0125] <Implementation Method 2> Hereinafter, an internal combustion engine control device according to Embodiment 2 will be described. The internal combustion engine control device according to Embodiment 2 differs from the internal combustion engine control device according to Embodiment 1 in ignition and fuel injection control processing. Therefore, the ignition and fuel injection control processing of the internal combustion engine control device according to Embodiment 2 will be described here, and the description of the common structure will be omitted.

[0126] The ROM 60 of the internal combustion engine control device according to the second embodiment stores a limit stay map used when calculating the limit energization amount (supplyable discharge energy A), a request stay map used when calculating the request energization amount (required discharge energy B), and a voltage correction coefficient map.

[0127] [Restrict resident mapping] Will refer to Fig.16 The restriction resident map stored in ROM 60 is described. Fig.16 is a diagram illustrating a restricted residency mapping.

[0128] Fig.16 The X-axis in the figure represents the rotational speed NE. Fig.16 The Y axis in represents the ignition coil temperature TC. Also, Fig.16 The Z axis in represents the limited energization time. The limited energization time is a variable that represents the limited energization amount (supplyable discharge energy A) by the time during which current is supplied to the ignition coil 300 (primary coil 310).

[0129] The limit stay map is mapping data in the form of a list that specifies a plurality of limit power-on times in correspondence with a plurality of index values ​​related to a plurality of ignition coil temperatures TC (e.g., 40, 80, 120 degrees C) and a plurality of index values ​​related to a plurality of speeds NE (e.g., idle speed IDLE, 3000, 7000 r / min). The adjustment unit 813 involved in the second embodiment calculates the limit power-on time corresponding to the value of the ignition coil temperature TC and the value of the speed NE based on the values ​​specified in the limit stay map. In addition, in the present embodiment, as Fig.16 As shown by the line connecting the points of multiple index values, when the value of the ignition coil temperature TC and the value of the speed NE correspond to values ​​located between the multiple index values, the limited energization time can be calculated by performing linear interpolation calculation connecting the points of multiple close index values.

[0130] [Requires resident mapping] Will refer to Fig.17 The requirement resident map stored in ROM 60 is described. Fig.17 is a diagram illustrating a requirement-resident mapping.

[0131] Fig.17 The horizontal axis of the graph shown in FIG. 1 represents the rotation speed NE. Fig.17 The vertical axis of the graph shown in represents the mapped energization time. The mapped energization time is a variable used when calculating the required energization time described later.

[0132] The request stay map is a table-like map data that specifies a plurality of map energization times in correspondence with a plurality of index values ​​related to a plurality of speeds NE (e.g., idle speed IDLE, 3000, 7000 r / min). The request setting unit 812 according to the second embodiment calculates the map energization time corresponding to the value of the speed NE based on the value specified in the request stay map.

[0133] [Voltage correction factor map] Will refer to Fig.18 The voltage correction coefficient map stored in the ROM 60 will be described. Fig.18 It is a diagram for explaining the voltage correction coefficient map.

[0134] Fig.18 The horizontal axis of the graph shown in FIG. 1 represents the power supply voltage VB, Fig.18 The vertical axis of the graph shown in represents a voltage correction coefficient. The voltage correction coefficient is a coefficient used when calculating a required energization time described later.

[0135] The voltage correction coefficient map is a table-like mapping data that specifies a plurality of voltage correction coefficients in correspondence with a plurality of index values ​​(e.g., 5, 12, 14V, 16V) related to a plurality of power supply voltages VB. In the second embodiment, the voltage correction coefficient corresponding to the value of the rotation speed NE is calculated based on the value specified in the voltage correction coefficient map.

[0136] The required setting unit 812 according to the second embodiment calculates the required energization time (required energization amount) by multiplying the mapped energization time by the voltage correction coefficient. The required energization time is a variable that represents the required energization amount (required discharge energy B) by the time for energizing the current to the ignition coil 300 (primary coil 310). That is, since the power consumption in the ignition coil 300 has a great influence on the internal heating of the ignition coil that affects the ignition coil temperature TC, the required energization time is adjusted according to the value of the power supply voltage VB related to the power consumption.

[0137] [Ignition and fuel injection control processing] Next, we will refer to Fig.19 The ignition and fuel injection control process according to the second embodiment will be described. Fig.19 This is a flowchart showing the ignition and fuel injection control process according to the second embodiment.

[0138] Steps S21 to S25 of the ignition and fuel injection control process according to Embodiment 2 are the same as Steps S1 to S5 of the ignition and fuel injection control process according to Embodiment 1. Therefore, the description of Steps S21 to S25 will be omitted.

[0139] After the process of step S25, the adjustment unit 813 of the overall control unit 81 uses the restricted residence map (see Fig.16 ), determine the limited energization time (limited energization amount) corresponding to the rotation speed NE and the ignition coil temperature TC (S26).

[0140] Next, the request setting unit 812 of the overall control unit 81 uses the request residency map (see Fig.17 ), determines the mapped energization time corresponding to the rotation speed NE (S27). Next, the requirement setting unit 812 determines the voltage correction coefficient corresponding to the power supply voltage VB using the voltage correction coefficient map (S28). Then, the requirement setting unit 812 calculates the required energization time (required energization amount) by multiplying the mapped energization time by the voltage correction coefficient (S29).

[0141] Next, the adjustment unit 813 of the overall control unit 81 determines whether the mapped energization time is greater than the limited energization time (S30). When it is determined in step S30 that the mapped energization time is not greater than the limited energization time (if S30 is determined as "No"), the adjustment unit 813 sets the required energization time (the value obtained by multiplying the mapped energization time by the voltage correction coefficient) as the ignition coil energization time (S31).

[0142] On the other hand, when it is determined in step S30 that the required energization time is greater than the limited energization time (if S30 is determined as "YES"), the adjustment unit 813 sets the ignition coil energization time to a value obtained by multiplying the limited energization time by the voltage correction coefficient (limited energization amount) (S32).

[0143] Steps S33 to S35 of the ignition and fuel injection control process according to Embodiment 2 are the same as Steps S11 to S13 of the ignition and fuel injection control process according to Embodiment 1. Therefore, the description of Steps S33 to S35 will be omitted.

[0144] <Implementation Method 3> Hereinafter, an internal combustion engine control device according to Embodiment 3 will be described. The internal combustion engine control device according to Embodiment 3 differs from the internal combustion engine control device according to Embodiment 1 or Embodiment 2 in ignition and fuel injection control processing. Therefore, the ignition and fuel injection control processing of the internal combustion engine control device according to Embodiment 3 will be described here, and the description of the common structure will be omitted.

[0145] In the ROM 60 of the internal combustion engine control device according to the third embodiment, a request residence map, a voltage correction coefficient map, and a temperature correction coefficient map used when executing the ignition and fuel injection control process are stored. The request residence map and the voltage correction coefficient map are the same as the request residence map of the second embodiment (see Fig.17 ) and voltage correction factor mapping (refer to Fig.18 )same.

[0146] [Temperature correction coefficient mapping] Will refer to Fig. 20 The temperature correction coefficient map stored in the ROM 60 will be described. Fig. 20 It is a diagram for explaining the temperature correction coefficient map.

[0147] Fig. 20 The horizontal axis of the graph shown in FIG. 1 represents the ignition coil temperature TC. Fig.18 The vertical axis of the graph shown in represents the temperature correction coefficient. The temperature correction coefficient is used when calculating the ignition coil energization time described later.

[0148] The temperature correction coefficient map is a table-like mapping data that specifies a plurality of temperature correction coefficients in a correspondence relationship with a plurality of index values ​​(e.g., -40, 0, 40, 80, 120 degrees C) related to a plurality of ignition coil temperatures TC. The adjustment unit 813 involved in the third embodiment calculates the temperature correction coefficient corresponding to the value of the ignition coil temperature TC based on the value specified in the temperature correction coefficient map.

[0149] In the third embodiment, the ignition coil energizing time is calculated by multiplying the required energizing time (required energizing amount) calculated by the required setting unit 812 by the temperature correction coefficient. That is, the ignition coil energizing time is adjusted by the temperature correction coefficient based on the ignition coil temperature TC.

[0150] [Ignition and fuel injection control processing] Next, we will refer to Fig.21 The ignition and fuel injection control process according to the third embodiment will be described. Fig.21 This is a flowchart showing the ignition and fuel injection control process according to the third embodiment.

[0151] Steps S41 to S45 of the ignition and fuel injection control process according to Embodiment 3 are the same as Steps S1 to S5 of the ignition and fuel injection control process according to Embodiment 1. Therefore, the description of Steps S41 to S45 will be omitted.

[0152] After the processing of step S45, the request setting unit 812 of the overall control unit 81 uses the request residency map (see Fig.17 ), determine the map energization time (map energization amount) corresponding to the rotation speed NE (S46).

[0153] Next, the adjustment unit 813 of the overall control unit 81 uses the temperature correction coefficient map (see Fig. 20 ), determine the temperature correction coefficient corresponding to the ignition coil temperature TC (S47). Next, the requirement setting unit 812 uses the voltage correction coefficient map to determine the voltage correction coefficient corresponding to the power supply voltage VB (S48). After the processing of step S48, proceed to step S49, and the requirement setting unit 812 multiplies the mapped power-on time by the voltage correction coefficient to calculate the required power-on time. The required power-on time is provided to the adjustment unit 813. The adjustment unit 813 calculates the ignition coil power-on time by multiplying the required power-on time by the temperature correction coefficient (S49).

[0154] Steps S50 to S52 of the ignition and fuel injection control process according to Embodiment 3 are the same as steps S11 to S13 of the ignition and fuel injection control process according to Embodiment 1. Therefore, the description of steps S50 to S52 will be omitted.

[0155] In the requirement setting unit 812 of the second and third embodiments, by using Fig.17 The required power-on time is determined by multiplying the mapped power-on time determined by the required residence map shown by the voltage correction coefficient to determine the required power-on time (S29, S49). However, the calculation of the required power-on time involved in the present invention is not limited to this. For example, the required residence map can use a map of a structure not shown in the figure that specifies multiple required power-on times (required power-on amounts) in a corresponding relationship with multiple index values ​​involved in multiple rotation speeds NE and multiple index values ​​involved in multiple power supply voltages VB. In this case, the above-mentioned voltage correction coefficient map ( Fig.18 ), and multiplying the voltage correction coefficient by the mapped energization amount.

[0156] <Implementation Method 4> Hereinafter, an internal combustion engine control device according to Embodiment 4 will be described. The internal combustion engine control device according to Embodiment 4 differs from the internal combustion engine control devices according to Embodiments 1 to 3 in ignition and fuel injection control processing. Therefore, the ignition and fuel injection control processing of the internal combustion engine control device according to Embodiment 4 will be described here, and the description of the common structure will be omitted.

[0157] In the ROM 60 of the internal combustion engine control device according to the fourth embodiment, a low temperature request residence map, a high temperature request residence map, and a voltage correction coefficient map are stored, which are used when executing the ignition and fuel injection control process. The voltage correction coefficient map is different from the voltage correction coefficient map of the second embodiment (see Fig.18 )same.

[0158] [Low temperature requires resident mapping] Will refer to Fig. 22 The low temperature request resident map stored in the ROM 60 will be described. Fig. 22 This is a diagram illustrating a low temperature demand retention map.

[0159] Fig. 22 The horizontal axis of the graph shown in FIG. 1 represents the rotation speed NE. Fig. 22 The vertical axis of the graph shown in represents the low temperature mapped power-on time. As described below, the low temperature mapped power-on time (low temperature mapped power-on amount) is used when calculating the low temperature ignition coil power-on time used when the ignition coil temperature TC is lower than a preset low temperature setting value. In addition, the low temperature ignition coil power-on time is also used when calculating the ignition coil power-on time when the ignition coil temperature TC is a value between the preset high temperature setting value and the low temperature setting value.

[0160] The low temperature request stay map specifies a plurality of low temperature map energization times (low temperature map energization amounts) in correspondence with a plurality of index values ​​associated with a plurality of speed NE values ​​(e.g., idle speed IDLE, 3000, 7000 r / min). The request setting unit 812 of the fourth embodiment calculates the low temperature map energization time corresponding to the speed NE value based on the value specified in the low temperature request stay map.

[0161] [High temperature requires resident mapping] Will refer to Fig.23 The high temperature request resident map stored in the ROM 60 will be described. Fig.23 This is a diagram illustrating a high temperature demand retention map.

[0162] Fig.23 The horizontal axis of the graph shown in FIG. 1 represents the rotation speed NE. Fig.23 The vertical axis of the graph shown in represents the high temperature mapped energization time. As described below, the high temperature mapped energization time (high temperature mapped energization amount) is used when calculating the high temperature ignition coil energization time when the ignition coil temperature TC is higher than a preset high temperature setting value. In addition, the high temperature ignition coil energization time is also used when calculating the ignition coil energization time when the ignition coil temperature TC is a value between the preset high temperature setting value and the low temperature setting value.

[0163] The high temperature request stay map specifies a plurality of high temperature map energization times in correspondence with a plurality of index values ​​associated with a plurality of speed NE values ​​(e.g., idle speed IDLE, 3000, 7000 r / min). The request setting unit 812 of the fourth embodiment calculates the high temperature map energization time corresponding to the speed NE value based on the value specified in the high temperature request stay map.

[0164] [Ignition and fuel injection control processing] Next, we will refer to Fig.24 The ignition and fuel injection control process according to the fourth embodiment will be described. Fig.24 This is a flowchart showing the ignition and fuel injection control process according to the fourth embodiment.

[0165] Steps S61 to S65 of the ignition and fuel injection control process according to Embodiment 4 are the same as Steps S1 to S5 of the ignition and fuel injection control process according to Embodiment 1. Therefore, the description of Steps S61 to S65 will be omitted.

[0166] After the processing of step S65, the requirement setting unit 812 of the overall control unit 81 determines the low temperature map energization time (low temperature map energization amount) corresponding to the rotation speed NE using the low temperature requirement residence map (S66). Next, the requirement setting unit 812 determines the high temperature map energization time (high temperature map energization amount) corresponding to the value of the rotation speed NE using the high temperature requirement residence map (S67).

[0167] Next, the adjustment unit 813 of the overall control unit 812 determines a voltage correction coefficient corresponding to the value of the power supply voltage VB using the voltage correction coefficient map (S68). Then, the adjustment unit 813 determines whether the ignition coil temperature TC is higher than a predetermined low temperature setting value (S69).

[0168] When it is determined in step S69 that the ignition coil temperature TC is not higher than the predetermined low temperature setting value (if S69 is determined as “NO”), the adjustment unit 813 sets the temperature change determination flag to “0” ( S70 ).

[0169] When it is determined in step S69 that the ignition coil temperature TC is higher than the predetermined low temperature setting value (if S69 is determined as YES), the adjustment unit 813 determines whether the ignition coil temperature TC is lower than the predetermined high temperature setting value ( S71 ).

[0170] If it is determined in step S71 that the ignition coil temperature TC is lower than the predetermined high temperature setting value (if S71 is determined as "YES"), the adjustment unit 813 determines whether the temperature change determination flag is "1" (S72). In addition, the high temperature setting value is higher than the low temperature setting value.

[0171] When it is determined in step S72 that the temperature change determination flag is not "1" (if the determination in S72 is "No"), the adjustment unit 813 executes the processing of step S73 described later.

[0172] When it is determined in step S72 that the temperature change determination flag is "1" (if the determination in S72 is "YES"), the adjustment unit 813 executes the processing of step S75 described later.

[0173] After the process of step S70 or when the determination of step S72 is “NO”, the adjustment unit 813 calculates the ignition coil energization time (ignition coil energization amount) by multiplying the low temperature map energization time by the voltage correction coefficient (S73).

[0174] On the other hand, when it is determined in step S71 that the ignition coil temperature TC is not lower than the predetermined high temperature set value (if S71 is determined as NO), the adjustment unit 813 sets the temperature change determination flag to "1" (S74).

[0175] After the process of step S74 or when it is determined to be YES in step S72, the adjustment unit 813 multiplies the high temperature map energization time by the voltage correction coefficient to calculate the ignition coil energization time (S75).

[0176] Steps S76 to S78 of the ignition and fuel injection control process according to the fourth embodiment are the same as steps S11 to S13 of the ignition and fuel injection control process according to the first embodiment. Therefore, the description of steps S76 to S78 will be omitted.

[0177] As described above, the low temperature request residence map of the fourth embodiment (see Fig. 22 ) and high temperature requires resident mapping (refer to Fig.23 ) specifies the low temperature map power-on time and the high temperature map power-on time (map power-on amount) corresponding to the value of the rotational speed NE. However, the low temperature required residence map and the high temperature required residence map involved in the fourth embodiment can specify the required power-on time (required power-on amount) corresponding to both the value of the rotational speed NE and the value of the power supply voltage VB.

[0178] In this case, the low temperature request dwell map is used to determine the low temperature ignition coil energization time (ignition coil energization amount) (equivalent to S73), or the high temperature request dwell map is used to determine the high temperature ignition coil energization time (ignition coil energization amount) (equivalent to S75). In this case, the calculation of the voltage correction coefficient (S68) and the multiplication of the voltage correction coefficient in steps S73 and S75 can be omitted.

[0179] In the above-mentioned fourth embodiment, the low temperature mapped power-on time and the high temperature mapped power-on time are switched by using the low temperature set value and the high temperature set value, so that the ignition coil power-on time is determined so as to change in a step-like manner in the temperature direction. However, when the ignition coil temperature TC is between the low temperature set value and the high temperature set value, the adjustment unit 813 involved in the present invention can determine the ignition coil power-on time by interpolating the value between the low temperature mapped power-on time and the high temperature mapped power-on time. That is, it can be set so that the ignition coil power-on time changes in a ramp-like manner from the low temperature set value to the high temperature set value by interpolating.

[0180] <Implementation method 5> Hereinafter, an internal combustion engine control device of Embodiment 5 will be described. The internal combustion engine control device of Embodiment 5 has the same structure as the internal combustion engine control device of Embodiment 1. The internal combustion engine control device of Embodiment 5 is different from the internal combustion engine control device of Embodiment 1 in that the circuit includes an ignition coil. Therefore, the circuit including the ignition coil of the internal combustion engine control device of Embodiment 5 will be described here, and the description of the common structure will be omitted.

[0181] [Circuit including ignition coil] Will refer to Fig.25 A circuit including an ignition coil according to the fifth embodiment will be described. Fig.25 This is a diagram for explaining an electric circuit including an ignition coil according to the fifth embodiment.

[0182] Fig.25 The circuit 501 shown includes an ignition coil 301. The ignition coil 301 is configured to include a primary coil 310 wound with a predetermined number of turns and a secondary coil 320 wound with a greater number of turns than the primary coil 310. The primary coil 310 and the secondary coil 320 are connected to Figure 5 The same as the embodiment 1 shown.

[0183] The other end of the primary coil 310 is connected to the drain (D) terminal of the igniter (power-on control circuit) 340 and grounded via the igniter 340. The gate (G) terminal of the igniter 340 is connected to the ignition control unit 83 via the temperature switch unit 360.

[0184] The purpose of providing the temperature switch unit 360 is to prevent the ignition coil 301 from being damaged due to overheating. The temperature switch unit 360 includes a temperature detection unit 361. The temperature detection unit 361 detects the temperature of the ignition coil 301 through the igniter 340. When the temperature detected by the temperature detection unit 361 is above a predetermined threshold value A (first temperature), the temperature switch unit 360 cuts off the ignition signal SA output from the ignition control unit 83 to the igniter 340.

[0185] The operating state of the temperature switch unit 360 corresponding to the threshold value A (first temperature) is input to the overall control unit 81 (not shown). Therefore, the overall control unit 81 involved in the fifth embodiment can read the ignition coil temperature TC as the first temperature based on the operating state of the temperature switch unit 360. As described above, the internal combustion engine control device involved in the present invention is not limited to a device for estimating the ignition coil temperature TC, and can also include a temperature detection unit for detecting the ignition coil temperature TC.

[0186] [Summarize] (1) The control device 1 (internal combustion engine control device) involved in the above-mentioned embodiment 1 controls the internal combustion engine 100, in which the current flowing through the ignition coil 300 of the ignition device is intermittent according to a predetermined ignition timing. The control device 1 includes a requirement setting unit 812, an adjustment unit 813 and an ignition control unit 83. The requirement setting unit 812 determines the required energization amount (required energization time) of the ignition coil 300 based on the rotation speed NE of the internal combustion engine 100. The adjustment unit 813 adjusts the ignition coil energization time (the energization amount of the ignition coil) according to the ignition coil temperature TC (temperature related to the ignition device) and the required energization amount. The ignition control unit 83 controls the intermittent state of the ignition coil 300 according to the ignition coil energization time adjusted by the adjustment unit 813. This makes it possible to appropriately control the thermal balance of the ignition device of the ignition coil 300. As a result, it is possible to suppress an increase in size and cost of the ignition device.

[0187] (2) The ROM 60 (storage unit) involved in the above-mentioned embodiment 2 stores a request residence map, a limit residence map, and a voltage correction coefficient map. The request residence map specifies the relationship between the rotation speed NE and the map energization amount. The limit residence map specifies the relationship between the rotation speed NE and the ignition coil temperature TC (temperature related to the ignition device) and the limit energization amount as the energization amount that can be provided to the ignition coil. The voltage correction coefficient map specifies the relationship between the power supply voltage VB of the ignition device and the voltage correction coefficient. The request setting unit 812 uses the request residence map to determine the map energization amount corresponding to the rotation speed NE, and uses the voltage correction coefficient map to determine the voltage correction coefficient corresponding to the power supply voltage. Then, the request setting unit 812 calculates the request energization amount by multiplying the map energization amount by the voltage correction coefficient. The adjustment unit 813 uses the limit residence map to determine the limit energization amount corresponding to the rotation speed NE and the ignition coil temperature TC. Then, when the request energization amount is less than the limit energization amount, the adjustment unit 813 sets the ignition coil energization time (the energization amount of the ignition coil) based on the request energization amount. On the other hand, when the required energization amount is greater than the limited energization amount, the ignition coil energization time is set based on the limited energization amount. Thus, the ignition coil energization time can be easily adjusted according to the ignition coil temperature TC and the required energization amount.

[0188] (3) The ROM 60 (storage unit) involved in the above-mentioned embodiment 3 stores a required residence map, a voltage correction coefficient map, and a temperature correction coefficient map. The required residence map specifies the relationship between the rotational speed NE and the map energization amount. The voltage correction coefficient map specifies the relationship between the power supply voltage VB of the ignition device and the voltage correction coefficient. The temperature correction coefficient map specifies the relationship between the ignition coil temperature TC (temperature related to the ignition device) and the temperature correction coefficient. The requirement setting unit 812 determines the map energization amount corresponding to the rotational speed NE by using the required residence map. The voltage correction coefficient map is used to determine the voltage correction coefficient corresponding to the power supply voltage VB, and the temperature correction coefficient map is used to determine the temperature correction coefficient corresponding to the ignition coil temperature TC. Then, the adjustment unit 813 calculates the ignition coil energization time (the energization amount of the ignition coil) by multiplying the map energization amount by the voltage correction coefficient and the temperature correction coefficient. Thus, the ignition coil energization time can be easily adjusted according to the ignition coil temperature TC and the required energization amount.

[0189] (4) The ROM 60 (storage unit) involved in the above-mentioned embodiment 4 stores a low temperature requirement residence map, a high temperature requirement residence map and a voltage correction coefficient map. The low temperature requirement residence map specifies the relationship between the rotational speed and the low temperature map energization amount. The high temperature requirement residence map specifies the relationship between the rotational speed and the high temperature map energization amount. The voltage correction coefficient map specifies the relationship between the power supply voltage VB of the ignition device and the voltage correction coefficient. The requirement setting unit 812 uses the low temperature requirement residence map to determine the low temperature map energization time corresponding to the rotational speed NE, and uses the high temperature requirement residence map to determine the high temperature map energization time corresponding to the rotational speed NE. The adjustment unit 813 sets the ignition coil energization time (the energization amount of the ignition coil) based on the low temperature map energization time and the high temperature map energization time according to the ignition coil temperature TC (temperature related to the ignition device). Thus, the ignition coil energization time can be easily adjusted according to the ignition coil temperature TC and the required energization amount.

[0190] (5) The adjustment unit 813 involved in the above-mentioned embodiment 4 sets the ignition coil power-on time (the power-on amount of the ignition coil) based on the low temperature mapped power-on time (the low temperature mapped power-on amount) when the ignition coil temperature TC (the temperature related to the ignition device) is less than a predetermined low temperature setting value. In addition, when the ignition coil temperature TC is greater than a predetermined high temperature setting value higher than the low temperature setting value, the adjustment unit 813 sets the ignition coil power-on time based on the high temperature mapped power-on time (the high temperature mapped power-on amount). In addition, when the ignition coil temperature TC is between the low temperature setting value and the high temperature setting value, if the ignition coil temperature TC is changing from a state below the low temperature setting value to the high temperature setting value, the adjustment unit 813 sets the ignition coil power-on time based on the low temperature mapped power-on time. In addition, if the ignition coil temperature TC is changing from a state above the high temperature setting value to the low temperature setting value, the ignition coil power-on time is set based on the high temperature mapped power-on time. Thus, when the ignition coil temperature TC is a value between the low temperature setting value and the high temperature setting value, the ignition coil energization time can be set by executing the hysteresis control.

[0191] (6) The ignition coil power-on time (the amount of power supplied to the ignition coil) involved in the above-mentioned embodiment is a value obtained by summing up the actual power-on time of the intermittent ignition coil 300 for performing a single ignition at each compression top dead center, double ignitions at compression and each exhaust top dead center, and even multiple discharges (multiple ignitions / discharges) other than the top dead center in order to perform one combustion cycle of the internal combustion engine 100. Thus, the ignition coil energization time (the energization amount of the ignition coil) adjusted based on the ignition coil temperature TC and the required energization amount can be easily adjusted to be applied to a variety of discharge (ignition) methods.

[0192] (7) The internal combustion engine according to the above embodiment includes the fuel injection device 134. Furthermore, the control device 1 (internal combustion engine control device) includes a fuel injection amount setting unit 815, which adjusts the fuel injection amount in the fuel injection device 134 based on the ignition coil temperature TC (temperature related to the ignition device). By adjusting the fuel injection amount, the combustibility of the mixed gas is improved, so that the required energization amount can be reduced. Thus, the ignition coil energization time can be easily adjusted according to the ignition coil temperature TC and the required energization amount. In addition, misfire can be suppressed.

[0193] (8) The ignition coil temperature TC (temperature related to the ignition device) in the above-described first to fourth embodiments is calculated using a neural network model that uses at least the rotation speed NE as an explanatory variable. Thus, the ignition coil temperature TC can be estimated with high accuracy without providing a temperature sensor for detecting the temperature of the ignition coil 300. As a result, the accuracy of the ignition coil energization time adjusted according to the ignition coil temperature TC can be improved, so that the thermal balance of the ignition device can be appropriately controlled. As a result, the cost of the ignition device can be suppressed.

[0194] (9) The explanatory variables input into the neural network model involved in the above-mentioned embodiments 1 to 4 include parameters related to the heat generation of the ignition coil 300 in the ignition device (rotation speed NE, power supply voltage VB, ignition coil current flow, etc.), and parameters related to the thermal balance inside and outside the ignition device (intake air temperature, intake air humidity, cooling water temperature, cooling wind speed, etc.). Thereby, the ignition coil temperature TC can be estimated with high accuracy.

[0195] (10) The internal combustion engine control method involved in the above-mentioned embodiment is a method for controlling an internal combustion engine 100 in which the current flowing through the ignition coil 300 of the ignition device is intermittent according to a predetermined ignition timing. In the internal combustion engine control method, the requirement setting unit 812 determines the required energization amount of the ignition coil 300 based on the rotation speed NE of the internal combustion engine 100. Then, the adjustment unit 813 adjusts the ignition coil energization time (the energization amount of the ignition coil) according to the ignition coil temperature TC (temperature related to the ignition device) and the required energization amount. Then, the ignition control unit 83 controls the intermittent state of the ignition coil 300 according to the ignition coil energization time adjusted by the adjustment unit 813. Thereby, the heat balance of the ignition device can be appropriately controlled, and as a result, the increase in size and cost of the ignition device can be suppressed.

[0196] (11) In the internal combustion engine control method according to the first embodiment, the ignition device temperature estimation unit 814 outputs the ignition coil temperature TC (temperature related to the ignition device) using the first neural network model with at least the rotation speed NE of the internal combustion engine 100 as an explanatory variable. The adjustment unit 813 outputs the limited energization time (limited energization amount) as the amount of energization that can be provided to the ignition coil 300 using the second neural network model with the ignition coil temperature TC, the power supply voltage VB and the rotation speed NE as explanatory variables. The requirement setting unit 812 outputs the required energization time (required energization amount) of the ignition coil 300 using the third neural network model with at least the rotation speed NE and the ignition coil temperature TC as explanatory variables. In addition, the adjustment unit 813 adjusts the ignition coil energization time (the energization amount of the ignition coil) based on the limited energization time and the required energization time. Then, the ignition control unit controls the intermittent state of the ignition coil 300 according to the ignition coil energization time adjusted by the adjustment unit 813. Thus, the ignition coil temperature TC can be grasped without providing a temperature sensor for detecting the temperature of the ignition coil 300. As a result, the cost of the ignition device can be suppressed. In addition, the accuracy of the ignition coil temperature TC, the limited power-on time, and the required power-on time can be improved, and the reliability of the adjusted ignition coil power-on time can be improved, so that the thermal balance of the ignition device can be appropriately controlled.

[0197] (12) The explanatory variables of the first neural network model or the explanatory variables of the third neural network model involved in the above-mentioned embodiment 1 include parameters related to the heat generation of the ignition coil 300 in the ignition device (rotation speed NE, power supply voltage VB, intake air flow rate, etc.), and parameters related to the thermal balance inside and outside the ignition device (intake air temperature, intake air humidity, cooling water temperature, cooling wind speed, etc.). Thereby, the ignition coil temperature TC can be estimated with high accuracy.

[0198] The present invention is not limited to the embodiments described above and shown in the drawings, and various modifications can be made without departing from the gist of the invention described in the claims.

[0199] The above-mentioned embodiments are detailed descriptions for the purpose of explaining the present invention in an understandable manner, and the present invention is not limited to including all the structures described. In addition, a part of the structure of a certain embodiment may be replaced with the structure of another embodiment, and the structure of another embodiment may be added to the structure of a certain embodiment. In addition, other structures may be added, deleted, or replaced with a part of the structure of each embodiment. Description of symbols

[0200] 1 internal combustion engine control device, 10 analog input unit, 20 digital input unit, 30 A / D conversion unit, 40 RAM, 50 MPU, 60 ROM, 70 I / O port, 80 output circuit, 81 overall control unit, 82 fuel injection control unit, 83 ignition control unit, 84 cylinder discrimination unit, 85 angle information generation unit, 86 speed information generation unit, 87 intake air amount measurement unit, 88 load information generation unit, 89 water temperature measurement unit, 90 voltage measurement unit, 100 internal combustion engine, 110 air filter, 111 intake pipe, 112 intake manifold, 113 throttle valve, 113a throttle valve opening sensor, 114 flow sensor, 115 intake air temperature sensor, 120 ring gear, 121 crank angle sensor, 122 water temperature sensor, 123 crankshaft, 125 accelerator pedal, 126 accelerator position sensor, 130 fuel tank, 131 fuel pump, 132 pressure regulator, 133 fuel pipe, 134 fuel injection device, 140 in-cylinder pressure sensor, 150 cylinder, 151 intake valve, 152 exhaust valve, 160 exhaust manifold, 161 three-way catalyst, 162 upstream air-fuel ratio sensor, 163 downstream air-fuel ratio sensor, 170 piston, 200 spark plug, 210 center electrode, 220 outer electrode, 230 insulator, 300, 301 ignition coil, 310 primary coil, 320 secondary coil, 330 DC power supply, 340 igniter, 350, 360 temperature switch unit, 361 temperature detection unit, 500, 501 electric circuit, 811 ignition timing setting unit, 812 requirement setting unit, 813 adjustment unit, 814 ignition device temperature estimation unit, 815 fuel injection amount setting unit, 816 fuel injection timing setting unit.

Claims

1. An internal combustion engine control device for controlling an internal combustion engine in which a current flowing through an ignition coil of an ignition device is intermittent according to a predetermined ignition timing, the internal combustion engine control device being characterized in that it comprises: a requirement setting unit that determines a required energization amount of the ignition coil based on a rotation speed of the internal combustion engine; an adjustment unit that adjusts the amount of energization of the ignition coil based on a temperature associated with the ignition device and the required amount of energization; and An ignition control unit controls an intermittent state of the ignition coil according to the amount of energization of the ignition coil adjusted by the adjustment unit.

2. The internal combustion engine control device according to claim 1, characterized in that: The invention comprises a storage unit, wherein the storage unit stores: a request-to-residence map that specifies a relationship between the rotational speed and a mapped energization amount; and a limit dwell map defining a relationship between the rotation speed and a temperature associated with the ignition device and a limit energization amount as an energization amount that can be supplied to the ignition coil, The requirement setting unit calculates the required energization amount corresponding to the rotation speed using the requirement retention map, The adjustment unit uses the limit residence map to determine the limit energization amount corresponding to the rotational speed and the temperature related to the ignition device, and when the required energization amount is less than the limit energization amount, the energization amount of the ignition coil is set based on the required energization amount; when the required energization amount is greater than the limit energization amount, the energization amount of the ignition coil is set based on the limit energization amount.

3. The internal combustion engine control device according to claim 1, characterized in that: The invention comprises a storage unit, wherein the storage unit stores: a request-to-residence map that specifies a relationship between the rotational speed and a mapped energization amount; a voltage correction factor map that specifies a relationship between a power supply voltage of the ignition device and a voltage correction factor; as well as a temperature correction factor map defining a relationship between a temperature associated with the ignition device and a temperature correction factor, The requirement setting unit determines a map energization amount corresponding to the rotation speed using the requirement retention map. using the voltage correction factor map to determine a voltage correction factor corresponding to the power supply voltage, and using the temperature correction factor map to determine a temperature correction factor corresponding to a temperature associated with the ignition device, The adjustment unit calculates the energization amount of the ignition coil by multiplying the mapped energization amount by the voltage correction coefficient and the temperature correction coefficient.

4. The internal combustion engine control device according to claim 1, characterized in that: The invention comprises a storage unit, wherein the storage unit stores: a low temperature request residence map, the low temperature request residence map defining a relationship between the rotation speed and the low temperature map power supply amount; a high temperature request residence map, the high temperature request residence map defining a relationship between the rotation speed and the high temperature map power supply amount; as well as a voltage correction factor map, the voltage correction factor map defining a relationship between a power supply voltage of the ignition device and a voltage correction factor, The requirement setting unit determines the low temperature map energization amount corresponding to the rotation speed using the low temperature requirement retention map, and determines the high temperature map energization amount corresponding to the rotation speed using the high temperature requirement retention map. The adjustment unit sets the energization amount of the ignition coil based on a temperature related to the ignition device, the low-temperature map energization amount, and the high-temperature map energization amount.

5. The internal combustion engine control device according to claim 4, characterized in that: The adjustment unit sets the energization amount of the ignition coil based on the low-temperature mapped energization amount when the temperature associated with the ignition device is below a predetermined low-temperature setting value, and sets the energization amount of the ignition coil based on the high-temperature mapped energization amount when the temperature associated with the ignition device is above a predetermined high-temperature setting value that is higher than the low-temperature setting value.

6. The internal combustion engine control device according to claim 1, characterized in that The amount of energization of the ignition coil is a value obtained by summing up the substantial energization time of the ignition coil which is intermittently energized once or a plurality of times during one combustion cycle of the internal combustion engine.

7. The internal combustion engine control device according to claim 1, characterized in that The internal combustion engine comprises a fuel injection device, The internal combustion engine control device includes a fuel injection amount setting portion that adjusts a fuel injection amount in the fuel injection device based on a temperature associated with the ignition device.

8. The internal combustion engine control device according to claim 1, characterized in that A temperature associated with the ignition device is output using a neural network model using at least the rotational speed as an explanatory variable.

9. The internal combustion engine control device according to claim 8, characterized in that: The explanatory variables input to the neural network model include parameters related to heat generation of the ignition coil in the ignition device and parameters related to heat balance inside and outside the ignition device.

10. An internal combustion engine control method for controlling an internal combustion engine in which a current flowing through an ignition coil of an ignition device is intermittent according to a predetermined ignition timing, the internal combustion engine control method being characterized in that: The requirement setting unit determines the required energization amount of the ignition coil based on the rotation speed of the internal combustion engine. The adjustment unit adjusts the energization amount of the ignition coil according to the temperature related to the ignition device and the required energization amount. The ignition control unit controls the intermittent state of the ignition coil according to the amount of energization of the ignition coil adjusted by the adjustment unit.

11. A method for controlling an internal combustion engine, wherein a current flowing through an ignition coil of an ignition device in the internal combustion engine is intermittent according to a predetermined ignition timing, the method for controlling the internal combustion engine being characterized in that: The ignition device temperature estimation unit outputs a temperature related to the ignition device using a first neural network model, the first neural network model using at least a power supply voltage of the ignition device and a rotation speed of the internal combustion engine as explanatory variables, The adjustment unit uses a second neural network model output as a limit energization amount that can be supplied to the ignition coil, the second neural network model using a temperature related to the ignition device, the power supply voltage, and the rotation speed as explanatory variables, The requirement setting unit outputs the required energization amount of the ignition coil using a third neural network model, the third neural network model using at least the rotation speed and a temperature related to the ignition device as explanatory variables, The adjustment unit adjusts the energization amount of the ignition coil based on the limited energization amount and the required energization amount. The ignition control unit controls the intermittent state of the ignition coil according to the amount of energization of the ignition coil adjusted by the adjustment unit.

12. The internal combustion engine control method according to claim 11, characterized in that: The explanatory variables of the first neural network model or the explanatory variables of the third neural network model include a parameter related to heat generation of the ignition coil in the ignition device and a parameter related to heat balance inside and outside the ignition device.

Images