Internal combustion engine control device and internal combustion engine control method

Abstract

The purpose of the present invention is to appropriately control heat balance of an ignition device and suppress upsizing or an increase in cost of the ignition device. This internal combustion engine control device controls an internal combustion engine in which a current flowing to an ignition coil of an ignition device is disconnected in accordance with an ignition period set in advance. The internal combustion engine is provided with a request setting unit, an adjustment unit, and an ignition control unit. The request setting unit determines a request energization amount of the ignition coil on the basis of the rotational speed of the internal combustion engine. The adjustment unit adjusts an energization amount of the ignition coil in accordance with a temperature and the request energization amount of the ignition device. The ignition control unit controls a disconnected 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 technology]

[0002] In recent years, in order to improve vehicle fuel efficiency, technologies such as lean burn, which operates internal combustion engines by burning a mixture with a higher than theoretical air-fuel ratio (lean fuel), and exhaust gas recirculation, which takes in some of the exhaust gas after combustion and inhales it again, have been developed.

[0003] In this type of internal combustion engine, the use of a lean fuel mixture and the implementation of exhaust gas recirculation make it difficult for the spark plug to produce a spark. Therefore, the ignition capacity (i.e., the amount of ignition energy) of the ignition device required to form a flame in the combustion chamber increases compared to when igniting a mixture with a stoichiometric air-fuel ratio. As a result, the amount of 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 in response to changes in the pressure in the intake pipe. The engine ignition device disclosed in Patent Document 1 increases ignition energy by extending the energization time of the ignition coil based on the intake pipe pressure Pm to prevent misfires during supercharging. This ensures stable combustion even when supercharging makes it difficult for the spark plug to produce a spark. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Laid-Open No. 2000-054941 Summary of the Invention [Problem to be solved by the invention]

[0006] However, the engine ignition device disclosed in Patent Document 1 does not take into consideration the heat balance of the ignition coil. For example, if an internal combustion engine is continuously operated under high load with the intake manifold pressure Pm increased by supercharging, the time that current is applied to the ignition coil is extended. This causes the ignition device to continue to operate in a state where the ignition energy is increased, i.e., where the amount of heat generated per unit time is large. As a result, there is a risk that the temperature of the ignition device will exceed the preset rated temperature.

[0007] One possible solution to this problem is to design the heat dissipation of the ignition coil by taking into account the maximum heat generation per unit time of the ignition coil during periods of continuous high-load operation, as well as harsh environmental conditions such as high outside temperatures in the summer. However, this solution creates new problems, such as an increase in the size and cost of the ignition device.

[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 that appropriately control the heat balance of an ignition device and suppress increases in the size and cost of the ignition device. [Means for solving the problem]

[0009] To solve the above problems and achieve the object, one aspect of the present invention provides an internal combustion engine control device that controls an internal combustion engine in which current flowing through an ignition coil of an ignition device is turned on and off in accordance with a predetermined ignition timing. This internal combustion engine control device includes a demand setting unit, an adjustment unit, and an ignition control unit. The demand setting unit determines a demanded amount of current flowing through the ignition coil based on the rotational speed of the internal combustion engine. The adjustment unit adjusts the amount of current flowing through the ignition coil in accordance with the temperature related to the ignition device and the demanded amount of current flowing through the ignition coil. The ignition control unit controls the on / off state of the ignition coil in accordance with the amount of current flowing through the ignition coil adjusted by the adjustment unit. The temperature related to the ignition device is output using a neural network model that uses at least the rotation speed as an explanatory variable.

[0010] One aspect of the present invention is a method for controlling an internal combustion engine in which current flowing through an ignition coil of an ignition device is turned on and off according to a predetermined ignition timing. In this internal combustion engine control method, a requirement setting unit determines a required current flow for the ignition coil based on the rotational speed of the internal combustion engine. Next, an adjustment unit adjusts the current flow for the ignition coil according to the temperature related to the ignition device and the required current flow. Then, an ignition control unit controls the on / off state of the ignition coil according to the current flow for the ignition coil adjusted by the adjustment unit. The temperature related to the ignition device is output using a neural network model that uses at least the rotation speed as an explanatory variable. [Effects of the Invention]

[0011] According to one aspect of the present invention, it is possible to appropriately control the heat balance of an ignition device in an internal combustion engine, and to suppress an increase in the size and cost of the ignition device. Problems, configurations, and effects other than those described above will become clear from the following description of the embodiments. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is an overall configuration diagram showing an example of the basic configuration of an internal combustion engine according to an embodiment; [Figure 2] FIG. 2 is a partially enlarged view illustrating the spark plug according to the embodiment. [Figure 3] 1 is a functional block diagram illustrating a functional configuration of an internal combustion engine control device according to an embodiment. [Figure 4] FIG. 2 is a circuit diagram showing an example of an electric circuit including an ignition coil. [Figure 5] FIG. 4 is a diagram illustrating the relationship between the electrode temperature, the minimum ignition energy, and the air-fuel ratio. [Figure 6] 10 is an example of a discharge waveform of multiple ignition. [Figure 7] FIG. 4 is a conceptual diagram showing the relationship between the temperature of the ignition coil and the supplyable discharge energy, the required discharge energy, and the difference therebetween. [Figure 8] FIG. 1 is a conceptual diagram showing the relationship between the temperature and discharge energy of a conventional ignition coil. [Figure 9]FIG. 4 is a conceptual diagram showing the relationship between the temperature of an ignition coil and discharge energy when the present invention is applied. [Figure 10] 4 is a flowchart showing an ignition and fuel injection control process according to the first embodiment. [Figure 11] FIG. 1 is a conceptual diagram showing the weights and biases of each neuron that constitutes a neural network model. [Figure 12] FIG. 2 is a diagram illustrating a method for implementing the calculation of each objective variable using a neural network model according to the first embodiment. [Figure 13] FIG. 2 is a conceptual diagram showing a neural network model used in the ignition and fuel injection control process according to the first embodiment. [Figure 14] 4 is a correspondence table showing the relationship between a response variable and an explanatory variable when using the neural network model according to the first embodiment. [Figure 15] 4 is a selection table of influencing factors when selecting explanatory variables for estimating an ignition coil temperature according to the first embodiment. [Figure 16] FIG. 10 is a diagram illustrating a limit dwell map according to the second embodiment. [Figure 17] FIG. 10 is a diagram illustrating a required dwell map according to the second embodiment. [Figure 18] FIG. 10 is a diagram illustrating a voltage correction coefficient map according to the second embodiment. [Figure 19] 10 is a flowchart showing an ignition and fuel injection control process according to a second embodiment. [Figure 20] FIG. 11 is a diagram illustrating a temperature correction coefficient map according to the third embodiment. [Figure 21] 10 is a flowchart showing an ignition and fuel injection control process according to a third embodiment. [Figure 22] FIG. 10 is a diagram illustrating a low-temperature required dwell map according to the fourth embodiment. [Figure 23] FIG. 10 is a diagram illustrating a high-temperature required dwell map according to the fourth embodiment. [Figure 24] 10 is a flowchart showing an ignition and fuel injection control process according to a fourth embodiment. [Figure 25] FIG. 10 is a circuit diagram showing an example of an electric circuit including a ignition coil according to a fifth embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0013] First Embodiment The internal combustion engine control device according to the first embodiment will be described below. Note that common parts in each drawing are given the same reference numerals.

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

[0015] The internal combustion engine 100 shown in FIG. 1 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] As shown in Fig. 1, in an internal combustion engine 100, air drawn in from the outside (intake air) flows through an air cleaner 110, an intake pipe 111, and an intake manifold 112. The air that passes through the intake manifold 112 flows into each cylinder 150 when an intake valve 151 opens. The amount of air flowing into each cylinder 150 is adjusted by a throttle valve 113. The amount of air adjusted by the throttle valve 113 is measured by a flow rate sensor 114.

[0017] A throttle opening sensor 113a that detects the opening of the throttle is provided to the throttle valve 113. Information about the opening of the throttle valve 113 detected by the throttle opening sensor 113a is output to a control device (Electronic Control Unit: ECU) 1.

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

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

[0020] A crank angle sensor 121 is provided radially outward of the ring gear 120 attached to the crankshaft 123. The crank angle sensor 121 detects the rotation angle of the crankshaft 123. In this embodiment, the crank angle sensor 121 detects the rotation angle of the crankshaft 123 every 10° and every combustion cycle.

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

[0022] The vehicle is also provided with an accelerator position sensor 126 that detects the displacement (depression amount) of an accelerator pedal 125. The accelerator position sensor 126 detects the torque required by the driver. The torque required by the driver detected by the accelerator position sensor 126 is output to the internal combustion engine control device 1, which will be described later. The internal combustion engine control device 1 controls the throttle valve 113 based on this required torque.

[0023] Fuel stored in a fuel tank 130 is sucked in and pressurized by a fuel pump 131. The fuel sucked in and pressurized by the fuel pump 131 is adjusted to a predetermined pressure in the fuel tank 130 by a pressure regulator 132 attached to the fuel pump 131. The fuel adjusted to the predetermined pressure is then supplied to a fuel injection device (injector) 134 via a fuel pipe 133 and injected into each cylinder 150. Note that excess fuel generated by the pressure adjustment by the pressure regulator 132 is discharged from the pressure regulator 132 to the fuel tank 130.

[0024] The fuel injection device 134 is controlled based on a fuel injection pulse (control signal) from a fuel injection control section 82 (see FIG. 3) of the internal combustion engine control device 1, which will be described later.

[0025] An in-cylinder pressure sensor (also called a combustion pressure sensor) 140 is provided in a cylinder head (not shown) facing the combustion chamber of the internal combustion engine 100. The in-cylinder pressure sensor 140 is provided in a cylinder 150 and detects the pressure (combustion pressure) inside the cylinder 150. For example, a piezoelectric or gauge type pressure sensor is used as the in-cylinder pressure sensor 140. This makes it possible to detect the in-cylinder pressure inside the cylinder 150.

[0026] Each cylinder 150 is equipped with an exhaust valve 152 and an exhaust manifold 160. When the exhaust valve 152 opens, exhaust gas is discharged from the cylinder 150 to the exhaust manifold 160. The exhaust manifold 160 discharges the post-combustion 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] An upstream air-fuel ratio sensor 162 is provided upstream of the three-way catalyst 161. The upstream air-fuel ratio sensor 162 outputs a signal corresponding to the oxygen concentration related to the air-fuel ratio of the exhaust gas discharged from each cylinder 150. The upstream air-fuel ratio sensor 162 of this embodiment is a so-called linear air-fuel ratio sensor that detects the air-fuel ratio (oxygen concentration) of the exhaust gas discharged from each cylinder 150 as a voltage that changes proportionally (linearly) to the air-fuel ratio.

[0028] Further, a downstream air-fuel ratio sensor 163 is provided downstream of the three-way catalyst 161. The downstream air-fuel ratio sensor 163 outputs a signal corresponding to the oxygen concentration related to the air-fuel ratio of the exhaust gas purified by the three-way catalyst 161. The downstream air-fuel ratio sensor 163 of this embodiment is a so-called O2 sensor that outputs a detection signal that changes between two values ​​corresponding to whether the air-fuel ratio is richer (rich) or leaner (lean) than the stoichiometric air-fuel ratio.

[0029] An ignition plug 200 is provided at a location facing each combustion chamber of each cylinder 150. The spark plug 200 generates a spark by discharge (ignition), and the spark ignites the air-fuel mixture in the cylinder 150. This causes explosive combustion in the cylinder 150, pushing down the piston 170. Pushing down the piston 170 rotates the crankshaft 123. An ignition coil 300 is connected to the spark plug 200, which generates (boosts) a discharge voltage to be supplied to the spark plug 200.

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

[0031] [Spark plug] Next, the spark plug 200 will be described with reference to FIG. FIG. 2 is a partially enlarged view illustrating the spark plug 200. As shown in FIG.

[0032] As shown in Fig. 2, the spark plug 200 has a center electrode 210 and an outer electrode 220. The center electrode 210 is supported on a plug base (not shown) via an insulator 230, thereby insulating the center electrode 210. The outer electrode 220 is grounded.

[0033] When a voltage is generated in the ignition coil 300 (see FIG. 1), a predetermined voltage (for example, 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, a discharge (ignition) occurs between the center electrode 210 and the outer electrode 220. A spark generated by the discharge ignites the mixture of air and fuel (gas components) in the cylinder 150.

[0034] The voltage at which a discharge (ignition) occurs due to dielectric breakdown of the gas components in the cylinder 150 varies depending on the state of the gas (air-fuel mixture in the cylinder) present between the center electrode 210 and the outer electrode 220 and the internal pressure of the cylinder 150. The voltage at which this discharge occurs is called the dielectric breakdown voltage.

[0035] Discharge control (ignition control) of the spark plug 200 is performed by an ignition control section 83 (see FIG. 3) of the control device 1, which will be described later.

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

[0037] As shown in FIG. 1, 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] The analog input unit 10 receives analog output signals from various sensors such as a throttle opening sensor 113a, a flow rate sensor 114, an accelerator position sensor 126, an upstream air-fuel ratio sensor 162, a downstream air-fuel ratio sensor 163, an in-cylinder pressure sensor 140, and a water temperature sensor 122.

[0039] An A / D conversion unit 30 is connected to the analog input unit 10. Analog output signals from various sensors input to the analog input unit 10 are subjected to signal processing such as noise removal, and then converted into digital signals by the A / D conversion unit 30. The digital signals converted by the A / D conversion unit 30 are then stored in a RAM 40.

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

[0041] The output signals stored in the RAM 40 are processed by the MPU 50.

[0042] The MPU 50 executes a control program (not shown) stored in the ROM 60, thereby processing the output signals stored in the RAM 40 in accordance with the control program. In accordance with the control program, the MPU 50 calculates control values ​​that define the operating amounts of the actuators that drive the internal combustion engine 100 (for example, the throttle valve 113, the fuel injector 134, the fuel pump 131, the ignition coil 300, etc.), and temporarily stores the control values ​​in the RAM 40.

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

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

[0045] [Controller function block] Next, the functional configuration of the control device 1 will be described with reference to FIG. FIG. 3 is a functional block diagram illustrating the functional configuration of the control device 1. As shown in FIG.

[0046] 3, the control device 1 is provided with the above-mentioned output circuit 80. In this embodiment, the output circuit 80 has an overall control unit 81, a fuel injection control unit 82, and an ignition control unit 83. The control device 1 further includes a cylinder discrimination unit 84, an angle information generation unit 85, a rotation speed information generation unit 86, an intake 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 determining unit 84 determines which stroke (for example, expansion, compression, intake or compression stroke as shown in FIG. 6) of each cylinder 150 of the internal combustion engine 100 the current crank angle measured by the angle information generating unit 85 corresponds to. The rotational speed information generating unit 86 measures the engine rotational speed.

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

[0049] [Overall Control Unit] The overall control unit 81 has an ignition timing setting unit 811 , a requirement 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 operating 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 in-cylinder pressure sensor 140.

[0051] The requirement setting unit 812 calculates the required current supply time (required current supply amount) based on the operating state of the internal combustion engine 100 obtained from outputs of various sensors such as the rotation speed NE and power supply voltage VB of the internal combustion engine 100. The required current supply time is the time required to supply current to the primary coil 310 (see FIG. 5) of the ignition coil 300 at the time of ignition.

[0052] The adjustment unit 813 calculates the current flow time for passing current through the primary coil 310 (see Figure 5) 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 current flow time (required current amount) obtained from the requirement setting unit.

[0053] The ignition device temperature estimation unit 814 calculates a temperature value (ignition coil temperature) TC relating to the ignition device using a neural network model with preselected explanatory variables as input.

[0054] The fuel injection amount setting unit 815 optimally calculates the fuel injection amount, which is the main operating amount 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 rotation speed NE of the internal combustion engine 100 and the power supply voltage VB.

[0055] The fuel injection timing setting unit 816 optimally calculates the opening and closing operation 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 of the fuel injection valve. The fuel injection control unit 82 generates a fuel injection pulse based on fuel control information input from the overall control unit 81. The fuel injection control unit 82 supplies the generated fuel injection pulse to the fuel injection control unit 82. The fuel injector 134 is driven in response 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 injections performed per combustion cycle of the internal combustion engine 100, and the opening and closing operation timing of the fuel injection valve obtained from the fuel injection timing setting unit 816.

[0058] [Ignition control unit] The ignition control unit 83 controls the timing and duration of energization of the ignition coil 300. The ignition control unit 83 calculates the timing (energization start crank angle) to start energizing the primary coil 310 based on the ignition control information input from the overall control unit 81. The timing to start energizing the primary coil 310 is the timing going back in time from the ignition timing at which the current flowing through the primary coil 310 is cut off, by the energization time.

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

[0060] The ignition control unit 83 starts energizing the primary coil 310 based on the calculated energization start timing, and outputs an ignition signal SA (see FIG. 4) that cuts off energization to the primary coil 310 based on the ignition timing, thereby causing the ignition plug 200 to ignite the air-fuel mixture.

[0061] [Electrical circuit including ignition coil] Next, the electric circuit including the ignition coil will be described with reference to FIG. FIG. 4 is a diagram illustrating an electric circuit including an ignition coil.

[0062] 4 includes an ignition coil 300. The ignition coil 300 includes 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.

[0063] One end of the primary coil 310 is connected to a DC power supply 330. This allows a predetermined voltage (for example, 12 V) to be applied to the primary coil 310. The other end of the primary coil 310 is connected to a drain (D) terminal of an igniter (energization control circuit) 340, and is grounded via the igniter 340. The igniter 340 may be a transistor, a field effect transistor (FET), or the like.

[0064] A gate (G) terminal of the igniter 340 is connected to the ignition control unit 83 via a temperature switch unit 350. The temperature switch unit 350 is provided to prevent damage to the ignition coil 300 due to overheating. When the temperature of the ignition coil 300 reaches or exceeds a predetermined threshold value A (first temperature), 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 current to the primary coil 310 is stopped, thereby preventing overheating of the igniter 340. 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 an ignition signal SA is input to the gate (G) terminal of the igniter 340, a current is conducted between the drain (D) terminal and the source (S) terminal of the igniter 340, and a current flows between the drain (D) terminal and the source (S) terminal. This causes the ignition signal SA to be output from the ignition control unit 83 to the primary coil 310 of the ignition coil 300 via the igniter 340. As a result, a current flows in the primary coil 310, and power (electrical energy) is accumulated.

[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 interrupted. As a result, a high voltage corresponding to the ratio of the number of turns of the coil 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 (see FIG. 2) of the spark plug 200. This generates a potential difference between the center electrode 210 and the outer electrode 220 of the spark plug 200. When this potential difference generated between the center electrode 210 and the outer electrode 220 exceeds the breakdown voltage Vm of the surrounding gas (air-fuel mixture in the cylinder 150), dielectric breakdown occurs in the gas components, causing a discharge between the center electrode 210 and the outer electrode 220. As a result, the fuel (air-fuel mixture) is ignited. The spark plug 200 and an electric circuit 500 having the ignition coil 300 correspond to the ignition device according to 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 Celsius. Because the discharge path is in contact with the ambient gas and the electrodes 210, 220, the heat energy of the discharge is distributed to the ambient gas and the electrodes 210, 220. The heat energy distributed to the ambient gas heats (preheats) the ambient gas and the electrodes 210, 220, promoting ignition.

[0070] [Electrode temperature, minimum ignition energy, and air-fuel ratio] Next, the relationship between the electrode temperature of the spark plug 200, the minimum ignition energy, and the air-fuel ratio will be described with reference to FIG. FIG. 5 is a diagram illustrating the relationship between the electrode temperature, the minimum ignition energy, and the air-fuel ratio.

[0071] FIG. 5 shows air-fuel ratio values ​​corresponding to minimum ignition energy values. In FIG. 5, the vertical direction indicates voltage scale values ​​corresponding to the minimum ignition energy of the mixture, and the horizontal direction indicates air-fuel ratio scale values ​​corresponding to the air-fuel ratio of the mixture. Air-fuel ratio P1 shown in FIG. 5 is the air-fuel ratio value corresponding to the predetermined value of minimum ignition energy that can ignite the mixture when the electrode temperature of the ignition plug is low (for example, minus 25 degrees Celsius). On the other hand, air-fuel ratio P2 is the air-fuel ratio value corresponding to the predetermined value of minimum ignition energy that can ignite the mixture when the electrode temperature of the ignition plug is high (for example, minus 7 degrees Celsius).

[0072] 5, in internal combustion engine 100, the greater the air-fuel ratio (leaner the fuel), the higher the value of the minimum ignition energy of the mixture, making it more difficult to ignite the mixture by discharge (ignition) from the spark plug. Also, the lower the electrode temperature of the spark plug, the higher the value of the minimum ignition energy of the mixture, making it more difficult to ignite the mixture by discharge (ignition) from the spark plug.

[0073] For example, suppose that a value equivalent to the minimum ignition energy corresponding to an air-fuel ratio P2 when the electrode temperature of the spark plug is high is obtained when the electrode temperature of the spark plug is low. In this case, unless the air-fuel ratio is set to an air-fuel ratio P1 that is smaller (richer fuel) than the air-fuel ratio P2, 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 assumption that the electrode temperature of the spark plug 200 was always low, as a setting with a safety margin that would prevent problems such as misfires in the internal combustion engine 100. As a result, in the internal combustion engine 100, the proportion of fuel in the air-fuel mixture increased, resulting in increased generation of hydrocarbons (HC) during combustion.

[0074] On the other hand, the higher the electrode temperature of the spark plug 200 during cold start (see the thick arrow in FIG. 5), the lower the minimum ignition energy required to ignite the air-fuel mixture. Therefore, even if the air-fuel ratio is increased (the fuel is lean), the discharge (ignition) from the spark plug exceeds the minimum ignition energy, making it possible to ignite the air-fuel mixture. As a result, the generation of hydrocarbons (HC) in the internal combustion engine 100 can be reduced. Therefore, in the internal combustion engine 100, the electrode temperature of the spark plug 200 during cold start is increased before discharge (ignition), as will be described later. This increases the air-fuel ratio during cold start, thereby suppressing the generation of hydrocarbons (HC).

[0075] [Multiple ignition] Next, multiple ignition will be described with reference to FIG. Figure 6 shows an example of a discharge waveform for multiple ignition.

[0076] It is known that a large amount of hydrocarbons (HC) is generated during cold start-up of an internal combustion engine, when the temperature of each part is approximately the same as the outside air temperature. One of the factors that causes hydrocarbons to be generated during cold start-up is that the low in-cylinder temperature reduces the amount of fuel that is vaporized before the ignition timing, causing the air-fuel ratio of the in-cylinder mixture to increase (fuel becomes lean). In this case, the required ignition energy increases, which increases the incidence of poor ignition and flame out (misfire), resulting in an increase in hydrocarbons. In other words, the main cause of hydrocarbon generation is misfire.

[0077] Misfires occur when a flame kernel generated by ignition fails to grow and goes out. To prevent misfires by growing the flame kernel, it is necessary to suppress the amount of heat transferred from the ambient gas in the discharge path between the electrodes 210, 220 of the spark plug 200 (see FIG. 2) and from the flame kernel to the electrodes 210, 220. For example, if multiple ignition is performed in the ignition device to preheat the electrodes 210, 220 of the spark plug 200, the temperature difference between the discharge path and the flame kernel and the electrodes 210, 220 will be reduced. As a result, the amount of heat transferred from the discharge path and the flame kernel to the electrodes 210, 220 can be suppressed.

[0078] As shown in Fig. 6, by repeatedly turning the ignition signal ON and OFF, multiple discharges are added to perform multiple ignitions. This makes it possible to increase the temperature of the electrodes 210, 220 of the spark plug 200 before the main ignition of the spark plug 200 (discharge at the ignition timing). This multiple ignition by additional discharge can be performed at a timing that does not overlap with the ignition timing of the main ignition. For example, multiple ignition by additional discharge can be performed at least during the period from after the main ignition to the start of fuel injection (the period from the expansion stroke to the intake stroke in the embodiment of Fig. 6).

[0079] [Ignition coil temperature and discharge energy] Next, the temperature and discharge energy of the ignition coil 300 will be described with reference to FIG. FIG. 7 is a conceptual diagram showing the relationship between the temperature of the ignition coil and the difference between the available discharge energy and the required discharge energy.

[0080] The horizontal axis of the graph shown in FIG. 7 represents the temperature TC of the ignition coil 300 (see FIG. 4) (hereinafter referred to as "ignition coil temperature TC"), and the vertical axis represents ignition performance, which is expressed in megajoules (mJ), a unit of discharge energy. The ignition performance includes the required discharge energy, which is set based on the minimum ignition energy required to ignite the air-fuel mixture and is determined, for example, according to the operating state of the internal combustion engine 100, and the supplyable discharge energy, which is the upper limit for keeping the ignition coil temperature TC at or below the rated temperature. As described above, the required discharge energy is affected by the air-fuel ratio of the air-fuel mixture and the amount of exhaust gas recirculation. Furthermore, the supplyable discharge energy tends to increase as the ignition coil temperature TC moves away from the rated temperature. For example, if the rated temperature is 120°C in FIG. 7, when the ignition coil temperature TC drops to 80°C or 40°C, which are lower than the rated temperature, the value of the supplyable discharge energy increases in accordance with the temperature decrease.

[0081] A high current of, for example, about 15 A flows through the primary coil 310 and igniter 340 of the ignition coil 300, causing repeated instantaneous heat generation each time ignition is performed. Therefore, the supplyable discharge energy A is set based on the ignition coil temperature TC, and the supplyable discharge energy A is used as a reference to control the current flow through the ignition coil 300 so that the temperatures of the primary coil 310 and igniter 340 of the ignition coil 300 do not exceed a preset rated temperature (the designed heat resistance temperature of each component). The supplyable discharge energy A of the ignition coil 300 decreases as the ignition coil temperature TC increases and approaches the rated temperature.

[0082] The required discharge energy B is mainly affected by the state of the mixture near the spark plug electrode, i.e., the air-fuel ratio and intake air flow. The required discharge energy B is nearly at its minimum when the air-fuel ratio of the mixture is close to the stoichiometric air-fuel ratio. On the other hand, the required discharge energy B increases as the air-fuel ratio deviates from the stoichiometric air-fuel ratio.

[0083] Generally, the slopes of the supplyable discharge energy A and the required discharge energy B on the temperature axis of the ignition coil temperature TC, which is shown in the left-right direction in FIG. 7, are different. Therefore, as shown in FIG. 7, the supplyable discharge energy A and the required discharge energy B intersect. In this case, for example, if the temperature at the point where the two discharge energies A and B intersect is higher than the rated temperature (design operating temperature range) of the ignition coil 300, the discharge energy A that is equal to or greater than the required discharge energy B can always be output from the ignition coil 300 without exceeding the rated temperature. In this case, the ignition performance of the internal combustion engine 100 is always satisfied without being restricted by the temperature of the ignition coil 300.

[0084] On the other hand, when implementing lean burn technology to operate an internal combustion engine by burning a mixture with a higher than stoichiometric air-fuel ratio (lean fuel) to improve the fuel efficiency of a vehicle, the required discharge energy B increases as the air-fuel ratio of the mixture deviates from the stoichiometric air-fuel ratio, and the temperature at the point where the two discharge energies A and B intersect may fall below the rated temperature of the ignition coil 300 (within the operating temperature range). In this case, it is difficult to continuously supply the required discharge energy B, which exceeds the supplyable discharge energy A, to the ignition coil 300 on the higher temperature side than the temperature at the intersecting point. Therefore, the feasibility of so-called fuel efficiency improvement technologies such as lean burn and exhaust gas recirculation for the internal combustion engine 100 is restricted by the lack of supplyable discharge energy A on the higher temperature side than the temperature at the point where the two discharge energies A and B intersect.

[0085] Hereinafter, when the supplyable discharge energy A is lower than the required discharge energy B, the difference between the supplyable discharge energy A and the required discharge energy B is defined as an ignition performance shortage C.

[0086] [Relationship between conventional ignition coil temperature and discharge energy] Next, the relationship between the temperature and discharge energy of a conventional ignition coil will be described with reference to FIG. FIG. 8 is a conceptual diagram showing the relationship between the temperature and discharge energy of a conventional ignition coil.

[0087] The horizontal axis of the graph shown in Figure 8 represents ignition coil temperature TC, and the vertical axis represents ignition performance. The thick line in Figure 8 represents the discharge energy output from a conventional ignition coil. As shown in Figure 8, in conventional ignition devices (see, for example, Japanese Patent Application Laid-Open No. 2000-054941), the value of ignition coil temperature TC is unclear. Therefore, if, for example, 120°C is set as the rated temperature in Figure 8, the supplyable discharge energy A2 at 120°C is always applied as the output limit value of the discharge energy by the ignition coil. In other words, in conventional ignition devices, the supplyable discharge energy A2 is essentially unchanged with changes in ignition coil temperature TC. In other words, conventional ignition devices are designed so that when ignition is performed when the air-fuel ratio is close to the stoichiometric air-fuel ratio, the temperature at the point where the supplyable discharge energy A2 and the required discharge energy B intersect is higher than the rated temperature of the ignition coil. Therefore, the ignition performance of the internal combustion engine 100 to which the conventional ignition device is applied is always satisfactory without being restricted by the temperature of the ignition coil 300, at least under the condition that ignition is performed when the air-fuel ratio is close to the stoichiometric air-fuel ratio.

[0088] However, when lean burn or exhaust gas recirculation (ERC) is implemented, in which a portion of the exhaust gas after combustion is taken in and re-inhaled, as described above, the required discharge energy B is higher than when the air-fuel mixture is ignited at a state close to the stoichiometric air-fuel ratio, and the temperature at the point where the two discharge energies A and B intersect falls below the rated temperature. In this case, at temperatures higher than the point where the available discharge energy A and the required discharge energy B intersect, the ignition performance shortage C increases as the ignition coil temperature TC increases, which may result in misfires. For these reasons, in internal combustion engines using conventional ignition devices, restrictions were imposed so that lean burn or exhaust gas recirculation could be implemented only under low-load conditions where the amount of air flowing into the cylinder is reduced and the required discharge energy B is lower.

[0089] [Relationship between ignition coil temperature and discharge energy according to the present invention] Next, the relationship between the temperature and discharge energy of the ignition coil according to the present invention will be described with reference to FIG. FIG. 9 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] The horizontal axis of the graph shown in Fig. 9 represents the ignition coil temperature TC, and the vertical axis represents the ignition performance. The thick line in Fig. 9 represents the discharge energy output from the ignition coil 300. As shown in Fig. 9, in this embodiment, when the temperature of the ignition coil 300 becomes higher than the temperature at the point where the supplyable discharge energy A and the required discharge energy B intersect, the supplyable discharge energy A is prioritized over the required discharge energy B.

[0091] That is, in this embodiment, when the ignition coil temperature TC 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 is set to the supplyable discharge energy A. As a result, when the temperature of the ignition coil 300 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 is gradually reduced as the ignition coil temperature TC increases.

[0092] In this embodiment, the fuel injection amount can be increased so that ignition occurs when the air-fuel ratio is close to the stoichiometric air-fuel ratio at temperatures higher than the point where the available discharge energy A intersects with the required discharge energy B, thereby substantially lowering the required discharge energy B. That is, in this embodiment, the ignition performance that is insufficient due to the reduced discharge energy is compensated for by improving the ignition quality of the air-fuel mixture. This reduces the required discharge energy B, thereby satisfying the required ignition performance while preventing overheating of the ignition coil 300. As a result, misfires can be suppressed. Furthermore, in this embodiment, the required discharge energy B can be increased more than in conventional ignition devices at temperatures lower than the point where the available discharge energy A intersects with the required discharge energy B to achieve lean combustion and exhaust gas recirculation. This allows lean combustion and exhaust gas recirculation to be performed more effectively than in conventional ignition devices, even under high-load conditions where the required discharge energy B is highest due to an increase in the amount of air flowing into the cylinder, while simultaneously preventing misfires and overheating of the ignition coil 300. As a result, vehicle fuel economy can be improved.

[0093] In this way, 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 know the temperature of the ignition coil 300 (the temperature of the ignition device). The temperature of the ignition coil 300 can be detected, for example, by providing a temperature sensor.

[0094] However, providing a temperature sensor in the ignition coil 300 increases costs and the size of the housing due to the increase in detection elements and wiring. Therefore, in this embodiment, the temperature of the ignition coil 300 is estimated without providing a temperature sensor. This makes it possible to suppress misfires while also suppressing increases in costs and the size of the housing.

[0095] [Ignition and fuel injection control processing] Next, the ignition and fuel injection control process according to the first embodiment will be described with reference to FIG. FIG. 10 is a flowchart showing the ignition and fuel injection control process according to the first embodiment.

[0096] The ignition and fuel injection control process begins when the internal combustion engine 100 is started (engine start). First, the overall control unit 81 acquires the power supply voltage VB (S1). Next, the overall control unit 81 acquires the rotation 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 in accordance with the rotation speed NE (S3).

[0097] Next, the overall control unit 81 sets explanatory variables of the neural network model (S4). In this embodiment, the explanatory variables are set by detecting, estimating, or calculating a plurality of explanatory variables that are selected in advance from a group of various parameters including the temperature of the ignition coil 300 and parameters relating to the heat balance inside and outside the ignition device and the operating state of the internal combustion engine 100 that are related to the temperature of the ignition coil 300 and the operating state of the internal combustion engine 100.

[0098] Next, the ignition device temperature estimation unit 814 of the overall control unit 81 inputs explanatory variables to the first neural network model to estimate 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 explanatory variables to the second neural network model and outputs a limited current application time according 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 current application time is the upper limit of the time for which current is applied to the ignition coil 300 (primary coil 310), and corresponds to the above-mentioned supplyable discharge energy A. Therefore, the limited current application time can also be said to be the limited current amount.

[0101] Next, the requirement setting unit 812 of the overall control unit 81 inputs explanatory variables to the third neural network model and outputs a required current application time according 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 current supply time is the time for supplying current to the ignition coil 300 (primary coil 310) to satisfy the required discharge energy B. Therefore, the required current supply time can also be said to be the required current amount.

[0103] Next, the adjustment unit 813 of the overall control unit 81 determines whether the requested energization time is longer than the limited energization time (S8). When it is determined in step S8 that the requested energization time is not longer than the limited energization time (NO in S8), the adjustment unit 813 sets the requested energization time to the energization time of the ignition coil 300 (hereinafter referred to as "ignition coil energization time") (S9).

[0104] On the other hand, when it is determined in step S8 that the requested current application time is longer than the limited current application time (YES in S8), the adjustment unit 813 sets the limited current application time as the ignition coil current application 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 stoichiometry in accordance with the ignition coil temperature TC (S11). In the processing of step S11, for example, when ignition performance is reduced by setting a limited current supply time for the ignition coil current supply time, the target air-fuel ratio value related to the determination of the fuel injection amount Tinj in the fuel injection control unit 82 is set to the stoichiometric air-fuel ratio at which the required discharge energy B is minimized, or a value close to the stoichiometric air-fuel ratio, as described above, in accordance with the ignition coil temperature TC. This reduces the value of the minimum ignition energy of the air-fuel mixture (reducing the required discharge energy B), thereby making it possible to suppress misfires.

[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) to the fuel injection device 134 according 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.

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

[0108] [Neural network model] Next, the neural network model according to this embodiment will be described with reference to FIGS. Fig. 11 is a conceptual diagram showing the weights and biases of each neuron constituting each neural network model, such as a first neural network model using the ignition coil temperature TC as the response variable, a second neural network model using the limited current application time as the response variable, and a third neural network model using the required current application time as the response variable. Fig. 12 is a diagram explaining a method for realizing the calculation of each response variable using a neural network model according to this embodiment. Fig. 13 is a conceptual diagram showing a neural network model used in the ignition and fuel injection control process according to the first embodiment.

[0109] A neural network model is a mathematical model that mimics the structure of the neural circuits in the human brain. In this embodiment, the neural network model is configured as a multi-layer neural network model having an input layer to which explanatory variables are input, an output layer to which a target variable is output, and an intermediate layer connecting the input layer and the output layer. Neural network models are often used as a means of deep learning in so-called machine learning. For example, backpropagation can be applied as a machine learning algorithm. Note that while a neural network model is used in this embodiment, it is not limited to this example as long as it can estimate the ignition coil temperature TC and determine the limited current flow time and required current flow time using machine learning.

[0110] As shown in Figure 11, a weight w and a bias b are set for each neuron (unit) that makes up 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, the inputs a1 to an multiplied by the weights w1 to wn are added (combined) in the next layer neuron, and the output z is obtained by adding a bias b to the addition result. The next layer neuron outputs a, which is expressed by the function f(z).

[0111] In addition, a function called an activation function is defined for each neuron. The activation function may be a logistic function (sigmoid function) or a ramp function (ReLU (Rectified Linear Unit) function), etc., as appropriate. Figure 11 shows an example in which the neuron is activated as the input x is greater than 0, and the output y (= f(x)) approaches 1, and the neuron is deactivated as the input x is smaller than 0, and approaches 0. For example, when the input x is "5", the output y of the activation function is "1", and the neuron outputs "1" to the neuron in the next layer.

[0112] 12, the intermediate layer of the multi-layer neural network model is configured so that multiple layers, each formed with multiple neurons, are stacked on top of each other. By configuring a large-scale neural network model with a large number of neurons and multiple intermediate layers, it is possible to learn complex input-output relationships and improve the approximation accuracy of the target variable. However, since there is a trade-off between improving the approximation accuracy and the size of the neural network model, the neural network model of the vehicle internal combustion engine control device according to this embodiment is configured and provided after considering in advance a so-called cost-effective balance between the desired approximation accuracy and the model size, taking into account the calculation processing capacity of the control device 1, the housing size, cost reduction, etc.

[0113] Thus, by setting variables having a causal relationship with the objective variable as training data for the explanatory variables in the input layer, setting the objective variable as training data in the output layer, and then using a known algorithm such as backpropagation to machine-learn (supervised learning) weights w and biases b for multiple neurons in the intermediate layer, it is possible to accurately approximate the input-output relationship of the neural network model.When the explanatory variables used in the machine learning as training data are input to the input layer, the trained model that has undergone such training executes a calculation of the input-output relationship based on the learned content, and outputs the value of the objective variable based on the input explanatory variables as the calculation result.

[0114] A neural network model of the ignition and fuel injection control process according to the first embodiment of the present invention will be described with reference to FIGS. Fig. 13 shows the input / output relationships between explanatory variables and response variables among a plurality of neural network models in the ignition and fuel injection control process according to the first embodiment of the present invention shown in Fig. 10. Note that the ignition and fuel injection control process according to this embodiment can be configured to use an estimation algorithm that uses a fourth neural network model for fuel injection control in step S12 and a fifth neural network model for ignition control in step S13, in addition to the first, second, and third neural network models used in the processes of steps S5, S6, and S7 described above.

[0115] In this embodiment, a first neural network model is trained using the ignition coil temperature TC as a response variable, and a plurality of explanatory variables, including the power supply voltage VB and the rotational speed NE, which are causally related to the ignition coil temperature TC, are set in the input layer of the first neural network model. The ignition coil temperature TC is then output from the output layer through the calculation process in the intermediate layer described above (step S5). A second neural network model is trained using the limited energization time of the ignition coil 300 as a response variable, and a plurality of explanatory variables, including the power supply voltage VB, the rotational speed NE, and the ignition coil temperature TC output from the first neural network model, which are causally related to the limited energization time, are set in the input layer of the second neural network model. The limited energization time is then output from the output layer through the calculation process in the intermediate layer (step S6). A third neural network model is trained using the required energization time as a response variable, and a plurality of explanatory variables, including the power supply voltage VB and the rotational speed NE, which are causally related to the required energization time, are set in the input layer of the third neural network model. The required energization time is then output from the output layer through the calculation process in the intermediate layer (step S7). Next, the limited current flow time output from the second neural network model and the required current flow time output from the third neural network model are set in the comparison calculation of the requirement setting unit 812 (step S8), and the ignition coil current flow time is set based on the comparison result between the limited current flow time and the required current flow time (steps S8, S9, S10).

[0116] Next, a fourth neural network model is trained using the opening / closing timing of the fuel injector as a response variable. A plurality of explanatory variables, including a fuel injection amount corresponding to a target air-fuel ratio (step S11) set according to the power supply voltage VB, the rotational speed NE, and the ignition coil temperature TC, which are causally related to the opening / closing timing of the fuel injector, are set in the input layer of the fourth neural network model. The opening / closing timing of the fuel injector corresponding to the crank angle measured by the angle information generator 85 is output from the output layer through calculation processing in the middle layer (step S12). A fifth neural network model is trained using the ignition signal SA output to the ignition coil (i.e., the ignition coil energization command) as a response variable. A plurality of explanatory variables, including the rotational speed NE, the ignition timing IGADV, and the ignition coil energization time, which are causally related to the ignition signal SA, are set in the input layer of the fifth neural network model. The ignition signal SA corresponding to the crank angle measured by the angle information generator 85 is output from the output layer through calculation processing in the middle layer (step S13). As shown in FIG. 13, the ignition and fuel injection control process of the first embodiment shown in FIG. 10 can be configured using the first to fifth neural network models.

[0117] [Relationship between objective variable and explanatory variable] Next, the relationship between the objective variable and the explanatory variables according to this embodiment will be described with reference to FIG. 14 is a correspondence table showing the relationship between the dependent variables and explanatory variables of the first to fifth neural network models according to the first embodiment. It shows examples of explanatory variables that are input to estimate (calculate) each dependent variable.

[0118] As shown in Figure 14, when estimating the ignition coil temperature TC, which is the objective variable, in the first neural network model, in addition to the rotation speed NE and power supply voltage VB described above, variables selected from the intake air flow rate, intake air pressure, intake air temperature, intake air humidity, rainfall (rainfall detection), coolant temperature, values ​​related to cooling air speed, vehicle traveling speed, ignition timing, ignition coil energization time (executed value), number of energizations / energization cycles, elapsed time since engine (internal combustion engine) started, elapsed time since engine (internal combustion engine) stopped, and available discharge energy (previously calculated value) are input into the first neural network model as explanatory variables, and machine learning is performed on multiple neurons in the intermediate layer.

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

[0120] [Explanatory variables] Next, a method for selecting explanatory variables for estimating the ignition coil temperature TC will be described with reference to FIG. FIG. 15 is a table showing an example of variables related to influential factors that are considered when selecting explanatory variables for estimating the ignition coil temperature TC according to the first embodiment.

[0121] Factors affecting fluctuations in the ignition coil temperature TC include factors related to internal heat generation in the ignition coil and factors related to external heat transfer. For each variable shown in Figure 15, the absolute value of the correlation coefficient with the ignition coil temperature TC is examined. Then, for example, variables with the largest correlation coefficient are selected as explanatory variables for the first neural network model.

[0122] Internal heat generation in the ignition coil includes heat generation due to the secondary current, heat generation due to the primary current, and heat generation in the igniter 340 (see Figure 4). This heat generation is caused by power loss in the internal circuit of the ignition coil. Therefore, variables with a high correlation coefficient are selected as explanatory variables for each internal heat generation. Variables with a high correlation coefficient with heat generation due to the secondary current include the rotational speed NE, intake air flow rate, intake pressure, air-fuel ratio of the mixed gas, ignition timing, and ignition coil energization time / number of energization cycles. Variables with a high correlation coefficient with heat generation due to the primary current and the igniter include the rotational speed NE, power supply voltage VB, and ignition coil energization time / number of energization cycles.

[0123] External heat transfer from the ignition coil occurs at the contact portion of the ignition coil 300 on the outside of the housing. For example, in the case of an ignition coil in which an ignition coil is disposed adjacent to the spark plug for each cylinder of the internal combustion engine 1, the objects in direct contact with the ignition coil 300 are the air (atmosphere), the spark plug, and the cylinder head. Therefore, for each of the objects in direct contact with the ignition coil 300, variables with a large correlation coefficient are selected as explanatory variables. For example, variables with a large correlation coefficient with external heat transfer include intake air temperature, intake air humidity, rainfall, coolant temperature, lubricant oil temperature, cooling air speed, vehicle traveling speed, air-fuel ratio of the mixed gas, cylinder number, elapsed time since the engine (internal combustion engine) was started, and elapsed time since the engine (internal combustion engine) was stopped.

[0124] In this embodiment, an example has been described in which the required and limited energization amounts are determined and the ignition coil energization amount is adjusted when a spark is generated by discharge (ignition) to ignite the air-fuel mixture. This discharge (ignition) may be performed intermittently for one combustion cycle of the internal combustion engine 100 (one ignition at the compression top dead center every two crank rotations), or discharge and ignition may be performed at the compression top dead center and the exhaust top dead center. The present invention may also be applied to a case in which, in addition to the ignition at the top dead center, additional discharges are performed multiple times at the spark plug (the case in which the above-mentioned multiple ignition is performed). That is, the ignition coil energization amounts for the compression top dead center ignition, the per-revolution ignition, and the multiple ignition may be individually adjusted based on the total required and limited energization amounts for one combustion cycle of the internal combustion engine 100. For example, the energization time of the ignition coil at compression top dead center is set based on the required amount of energization, and the energization time of each ignition coil for discharge at exhaust top dead center or discharge in multiple ignition can be set by dividing the value obtained by subtracting the required amount of energization from the total amount of limited energization for one combustion cycle of the internal combustion engine 100 according to the planned number of discharges at exhaust top dead center or multiple ignition. Thus, discharge at exhaust top dead center or discharge in multiple ignition is performed at a temperature lower than the temperature at the point where the supplyable discharge energy A and the required discharge energy B intersect as shown in Figure 9 above.

[0125] Second Embodiment The internal combustion engine control device according to the second embodiment will be described below. The internal combustion engine control device according to the second embodiment differs from the internal combustion engine control device according to the first embodiment in the ignition and fuel injection control processing. Therefore, here, the ignition and fuel injection control processing of the internal combustion engine control device according to the second embodiment will be described, and a description of the common configuration will be omitted.

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

[0127] [Limited Dwell Map] The limit dwell map stored in the ROM 60 will be described with reference to FIG. FIG. 16 is a diagram illustrating the restricted dwell map.

[0128] The X-axis in Fig. 16 represents the rotational speed NE, and the Y-axis in Fig. 16 represents the ignition coil temperature TC. The Z-axis in Fig. 16 represents the limited current flow time. The limited current flow time is a variable that represents the limited current amount (supplyable discharge energy A) as the time during which current is flowing through the ignition coil 300 (primary coil 310).

[0129] The limited dwell map is map data in the form of a list, which defines multiple limited energization times by associating multiple index values ​​(e.g., 40, 80, 120 deg. C.) corresponding to multiple ignition coil temperatures TC and multiple index values ​​(e.g., idling rotation speeds IDLE, 3000, 7000 r / min) corresponding to multiple rotation speeds NE. The adjustment unit 813 according to the second embodiment calculates the limited energization time according to the ignition coil temperature TC and the rotation speed NE based on the values ​​defined in the limited dwell map. In this embodiment, as shown in FIG. 16 by the lines connecting the points of the multiple index values, when the ignition coil temperature TC and the rotation speed NE fall between the multiple index values, the limited energization time can be calculated by linear interpolation between the points of the multiple index values ​​that are close to each other.

[0130] [Required Dwell Map] The required dwell map stored in the ROM 60 will be described with reference to FIG. FIG. 17 is a diagram illustrating the required dwell map.

[0131] The horizontal axis of the graph shown in Fig. 17 represents the rotation speed NE, and the vertical axis of the graph shown in Fig. 17 represents the map current supply time. The map current supply time is a variable used when calculating the required current supply time, which will be described later.

[0132] The required dwell map is map data in a table format that defines a plurality of map energization times by associating a plurality of index values ​​(e.g., idling rotation speeds IDLE, 3000, 7000 r / min) associated with a plurality of rotation speeds NE. The requirement setting unit 812 according to the second embodiment calculates the map energization time corresponding to the value of the rotation speed NE based on the values ​​defined in the required dwell map.

[0133] [Voltage correction coefficient map] The voltage correction coefficient map stored in the ROM 60 will be described with reference to FIG. FIG. 18 is a diagram illustrating the voltage correction coefficient map.

[0134] The horizontal axis of the graph shown in Fig. 18 represents the power supply voltage VB, and the vertical axis of the graph shown in Fig. 18 represents the voltage correction coefficient. The voltage correction coefficient is a coefficient used when calculating the required current application time, which will be described later.

[0135] The voltage correction coefficient map is map data in tabular form that defines a plurality of voltage correction coefficients by associating them with a plurality of index values ​​(e.g., 5, 12, 14 V, 16 V) associated with a plurality of power supply voltages VB. In the second embodiment, a voltage correction coefficient corresponding to the value of the rotation speed NE is calculated based on the values ​​defined in the voltage correction coefficient map.

[0136] The requirement setting unit 812 according to the second embodiment calculates the required current supply time (required current amount) by multiplying the map current supply time by the voltage correction coefficient. The required current supply time is a variable that represents the required current amount (required discharge energy B) as the time required for current to be supplied to the ignition coil 300 (primary coil 310). In other words, the internal heat generation of the ignition coil, which affects the ignition coil temperature TC, is significantly affected by the power consumption of the ignition coil 300, and therefore the required current supply time is adjusted according to the value of the power supply voltage VB, which is related to the power consumption.

[0137] [Ignition and fuel injection control processing] Next, the ignition and fuel injection control process according to the second embodiment will be described with reference to FIG. FIG. 19 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 the second embodiment are the same as steps S1 to S5 of the ignition and fuel injection control process according to the first embodiment, so a 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 determines the limited current application time (limited current application amount) according to the rotation speed NE and the ignition coil temperature TC using the limited dwell map (see FIG. 16) (S26).

[0140] Next, the request setting unit 812 of the overall control unit 81 determines a map current conduction time corresponding to the rotation speed NE using a required dwell map (see FIG. 17) (S27). Next, the request setting unit 812 determines a voltage correction coefficient corresponding to the power supply voltage VB using a voltage correction coefficient map (S28). Then, the request setting unit 812 multiplies the map current conduction time by the voltage correction coefficient to calculate a required current conduction time (required current amount) (S29).

[0141] Next, the adjustment unit 813 of the overall control unit 81 determines whether the map energization time is longer than the limited energization time (S30). When it is determined in step S30 that the map energization time is not longer than the limited energization time (NO in S30), the adjustment unit 813 sets the requested energization time (a value obtained by multiplying the map 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 requested current flow time is longer than the limited current flow time (if S30 is determined as YES), the adjustment unit 813 sets the ignition coil current flow time to a value (limited current flow amount) obtained by multiplying the limited current flow time by the voltage correction coefficient (S32).

[0143] Steps S33 to S35 of the ignition and fuel injection control process according to the second embodiment are the same as steps S11 to S13 of the ignition and fuel injection control process according to the first embodiment, so a description of steps S33 to S35 will be omitted.

[0144] <Third embodiment> An internal combustion engine control device according to the third embodiment will be described below. The internal combustion engine control device according to the third embodiment differs from the internal combustion engine control devices according to the first and second embodiments in the ignition and fuel injection control processing. Therefore, here, the ignition and fuel injection control processing of the internal combustion engine control device according to the third embodiment will be described, and a description of the common configuration will be omitted.

[0145] The ROM 60 of the internal combustion engine control device according to the third embodiment stores a required dwell map, a voltage correction coefficient map, and a temperature correction coefficient map, which are used when executing the ignition and fuel injection control process. The required dwell map and the voltage correction coefficient map are the same as the required dwell map (see FIG. 17) and the voltage correction coefficient map (see FIG. 18) of the second embodiment.

[0146] [Temperature correction coefficient map] The temperature correction coefficient map stored in the ROM 60 will be described with reference to FIG. FIG. 20 is a diagram illustrating the temperature correction coefficient map.

[0147] The horizontal axis of the graph shown in Fig. 20 represents the ignition coil temperature TC, and the vertical axis of the graph shown in Fig. 18 represents the temperature correction coefficient. The temperature correction coefficient is used when calculating the ignition coil current conduction time, which will be described later.

[0148] The temperature correction coefficient map is map data in tabular form that defines a plurality of temperature correction coefficients by associating them with a plurality of index values ​​(e.g., −40, 0, 40, 80, 120 degC) related to a plurality of ignition coil temperatures TC. The adjustment unit 813 according to the third embodiment calculates the temperature correction coefficient according to the value of the ignition coil temperature TC based on the values ​​defined in the temperature correction coefficient map.

[0149] In the third embodiment, the ignition coil current conduction time is calculated by multiplying the required current conduction time (required current conduction amount) calculated by the requirement setting unit 812 by a temperature correction coefficient. In other words, the ignition coil current conduction time is adjusted according to the temperature correction coefficient based on the ignition coil temperature TC.

[0150] [Ignition and fuel injection control processing] Next, the ignition and fuel injection control process according to the third embodiment will be described with reference to FIG. FIG. 21 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 the third embodiment are the same as steps S1 to S5 of the ignition and fuel injection control process according to the first embodiment, so a description of steps S41 to S45 will be omitted.

[0152] After the process of step S45, the requirement setting unit 812 of the overall control unit 81 determines the map energization time (map energization amount) according to the rotation speed NE using the required dwell map (see FIG. 17) (S46).

[0153] Next, the adjustment unit 813 of the overall control unit 81 determines a temperature correction coefficient corresponding to the ignition coil temperature TC using a temperature correction coefficient map (see FIG. 20) (S47). Next, the requirement setting unit 812 determines a voltage correction coefficient corresponding to the power supply voltage VB using a voltage correction coefficient map (S48). After processing step S48, the process proceeds to step S49, where the requirement setting unit 812 calculates a required current conduction time by multiplying the map current conduction time by the voltage correction coefficient. The required current conduction time is supplied to the adjustment unit 813. The adjustment unit 813 calculates the ignition coil current conduction time by multiplying the requested current conduction time by the temperature correction coefficient (S49).

[0154] Steps S50 to S52 of the ignition and fuel injection control process according to the third embodiment are the same as steps S11 to S13 of the ignition and fuel injection control process according to the first embodiment, so a description of steps S50 to S52 will be omitted.

[0155] In both the second and third embodiments, the requirement setting unit 812 determines the required energization time by multiplying the map energization time determined using the required dwell map shown in FIG. 17 by the voltage correction coefficient (S29, S49). However, the calculation of the required energization time according to the present invention is not limited to this. For example, the required dwell map may be a map (not shown) that defines multiple required energization times (required energization amounts) by associating multiple index values ​​associated with multiple rotational speeds NE with multiple index values ​​associated with multiple power supply voltages VB. In this case, the voltage correction coefficient map (FIG. 18) and the multiplication of the map energization amount by the voltage correction coefficient can be omitted.

[0156] <Fourth embodiment> An internal combustion engine control device according to the fourth embodiment will be described below. The internal combustion engine control device according to the fourth embodiment differs from the internal combustion engine control devices according to the first to third embodiments in the ignition and fuel injection control process. Therefore, here, the ignition and fuel injection control process of the internal combustion engine control device according to the fourth embodiment will be described, and a description of the common configuration will be omitted.

[0157] The ROM 60 of the internal combustion engine control device according to the fourth embodiment stores a low-temperature required dwell map, a high-temperature required dwell map, and a voltage correction coefficient map, which are used when executing the ignition and fuel injection control process. The voltage correction coefficient map is the same as the voltage correction coefficient map (see FIG. 18) of the second embodiment.

[0158] [Low temperature required dwell map] The low temperature required dwell map stored in the ROM 60 will be described with reference to FIG. FIG. 22 is a diagram illustrating a low temperature required dwell map.

[0159] The horizontal axis of the graph shown in Fig. 22 represents the rotation speed NE, and the vertical axis of the graph shown in Fig. 22 represents the low temperature map energization time. As will be described later, the low temperature map energization time (low temperature map energization amount) is used when calculating the low temperature ignition coil energization time to be used when the ignition coil temperature TC is lower than a preset low temperature set value. The low 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 a preset high temperature set value and a preset low temperature set value.

[0160] The low temperature required dwell map defines a plurality of low temperature map energization times (low temperature map energization amounts) by associating a plurality of index values ​​related to a plurality of rotation speed NE values ​​(e.g., idling rotation speed IDLE, 3000, 7000 r / min). The requirement setting unit 812 according to the fourth embodiment calculates the low temperature map energization time corresponding to the rotation speed NE value based on the values ​​defined in the low temperature required dwell map.

[0161] [High temperature required dwell map] The high temperature required dwell map stored in the ROM 60 will be described with reference to FIG. FIG. 23 is a diagram illustrating a high temperature required dwell map.

[0162] The horizontal axis of the graph shown in Fig. 23 represents the rotation speed NE, and the vertical axis of the graph shown in Fig. 23 represents the high-temperature map energization time. As will be described later, the high-temperature map energization time (high-temperature map 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 set value. 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 set value and the preset low-temperature set value.

[0163] The high temperature required dwell map defines a plurality of high temperature map power supply times by associating a plurality of index values ​​with a plurality of rotation speed NE values ​​(e.g., idling rotation speed IDLE, 3000, 7000 r / min). The requirement setting unit 812 according to the fourth embodiment calculates the high temperature map power supply time according to the rotation speed NE value based on the values ​​defined in the high temperature required dwell map.

[0164] [Ignition and fuel injection control processing] Next, the ignition and fuel injection control process according to the fourth embodiment will be described with reference to FIG. FIG. 24 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 the fourth embodiment are the same as steps S1 to S5 of the ignition and fuel injection control process according to the first embodiment, so a description of steps S61 to S65 will be omitted.

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

[0167] Next, the adjustment unit 813 of the overall control unit 81 determines a voltage correction coefficient according to the value of the power supply voltage VB using a 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] In step S69, when it is determined that the ignition coil temperature TC is not higher than the predetermined low temperature set value (NO in S69), the adjustment unit 813 sets the temperature change determination flag to "0" (S70).

[0169] In step S69, when it is determined that the ignition coil temperature TC is higher than the predetermined low temperature set 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 set value (S71).

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

[0171] In step S72, when it is determined that the temperature change determination flag is not "1" (NO determination in S72), the adjustment unit 813 performs the process of step S73, which will be described later.

[0172] If it is determined in step S72 that the temperature change determination flag is "1" (YES in S72), the adjustment unit 813 performs the process of step S75, which will be described later.

[0173] After the process of step S70, or if the determination in 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 (NO in S71), the adjustment unit 813 sets the temperature change determination flag to "1" (S74).

[0175] After the process of step S74, or if the determination in step S72 is YES, the adjustment unit 813 calculates the ignition coil current conduction time by multiplying the high temperature map current conduction time by the voltage correction coefficient (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, so a description of steps S76 to S78 will be omitted.

[0177] As described above, the low-temperature required dwell map (see FIG. 22) and the high-temperature required dwell map (see FIG. 23) according to the fourth embodiment define 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 rotation speed NE. However, the low-temperature required dwell map and the high-temperature required dwell map according to the fourth embodiment may define the power-on time (required power-on amount) corresponding to both the value of the rotation speed NE and the value of the power supply voltage VB.

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

[0179] In the fourth embodiment described above, the low temperature map energization time and the high temperature map energization time are switched using the low temperature setting value and the high temperature setting value, and the ignition coil energization time is determined so as to change in a stepped manner in the temperature direction. However, when the ignition coil temperature TC is between the low temperature setting value and the high temperature setting value, the adjustment unit 813 according to the present invention may determine the ignition coil energization time by interpolating a value between the low temperature map energization time and the high temperature map energization time. In other words, the ignition coil energization time may be set so as to change in a slope-like manner via interpolation from the low temperature setting value to the high temperature setting value.

[0180] Fifth Embodiment An internal combustion engine control device according to the fifth embodiment will be described below. The internal combustion engine control device according to the fifth embodiment has a similar configuration to the internal combustion engine control device according to the first embodiment. The internal combustion engine control device according to the fifth embodiment differs from the internal combustion engine control device according to the first embodiment in the electrical circuit including the ignition coil. Therefore, here, the electrical circuit including the ignition coil of the internal combustion engine control device according to the fifth embodiment will be described, and a description of the common configuration will be omitted.

[0181] [Electrical circuit including ignition coil] An electric circuit including an ignition coil according to the fifth embodiment will be described with reference to FIG. FIG. 25 is a diagram illustrating an electric circuit including an ignition coil according to the fifth embodiment.

[0182] An electric circuit 501 shown in Fig. 25 has an ignition coil 301. The ignition coil 301 includes 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 the same as those in the first embodiment shown in Fig. 5.

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

[0184] Temperature switch unit 360 is provided for the purpose of preventing damage due to overheating of ignition coil 301. Temperature switch unit 360 includes temperature detection unit 361. Temperature detection unit 361 detects the temperature of ignition coil 301 via igniter 340. When the temperature detected by temperature detection unit 361 becomes equal to or higher than a predetermined threshold value A (first temperature), temperature switch unit 360 cuts off ignition signal SA output from ignition control unit 83 to 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 according to 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. In this way, the internal combustion engine control device according to the present invention is not limited to one that estimates the ignition coil temperature TC, and may also be one that has a temperature detection unit that detects the ignition coil temperature TC.

[0186] [summary] (1) The control device 1 (internal combustion engine control device) according to the first embodiment described above controls an internal combustion engine 100 in which current flowing through an ignition coil 300 of an ignition device is turned on and off in accordance with 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 amount of current (required current-on time) for the ignition coil 300 based on the rotation speed NE of the internal combustion engine 100. The adjustment unit 813 adjusts the ignition coil current-on time (amount of current on the ignition coil) in accordance with the ignition coil temperature TC (temperature related to the ignition device) and the required amount of current. The ignition control unit 83 controls the on / off state of the ignition coil 300 in accordance with the ignition coil current-on time adjusted by the adjustment unit 813. This makes it possible to appropriately control the heat balance of the ignition device of the ignition coil 300. As a result, it is possible to suppress an increase in the size and cost of the ignition device.

[0187] (2) The ROM 60 (storage unit) according to the second embodiment described above stores a required dwell map, a limited dwell map, and a voltage correction coefficient map. The required dwell map defines the relationship between the rotation speed NE and the map current amount. The limited dwell map defines the relationship between the rotation speed NE, the ignition coil temperature TC (temperature related to the ignition device), and the limited current amount, which is the current amount that can be supplied to the ignition coil. The voltage correction coefficient map defines the relationship between the power supply voltage VB of the ignition device and the voltage correction coefficient. The requirement setting unit 812 determines the map current amount according to the rotation speed NE using the required dwell map, and determines the voltage correction coefficient according to the power supply voltage using the voltage correction coefficient map. The requirement setting unit 812 then multiplies the map current amount by the voltage correction coefficient to calculate the required current amount. The adjustment unit 813 determines the limited current amount according to the rotation speed NE and the ignition coil temperature TC using the limited dwell map. If the requested amount of current is equal to or less than the limited amount of current, the adjustment unit 813 sets the ignition coil current conduction time (the amount of current conducted through the ignition coil) based on the requested amount of current. On the other hand, if the requested amount of current is greater than the limited amount of current, the adjustment unit 813 sets the ignition coil current conduction time based on the limited amount of current. This makes it possible to easily adjust the ignition coil energization time in accordance with the ignition coil temperature TC and the required amount of energization.

[0188] (3) The ROM 60 (storage unit) according to the third embodiment described above stores a required dwell map, a voltage correction coefficient map, and a temperature correction coefficient map. The required dwell map defines the relationship between the rotation speed NE and the map current amount. The voltage correction coefficient map defines the relationship between the power supply voltage VB of the ignition device and the voltage correction coefficient. The temperature correction coefficient map defines 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 current amount according to the rotation speed NE using the required dwell map. The voltage correction coefficient map is used to determine the voltage correction coefficient according to the power supply voltage VB, and the temperature correction coefficient map is used to determine the temperature correction coefficient according to the ignition coil temperature TC. The adjustment unit 813 then multiplies the map current amount by the voltage correction coefficient and the temperature correction coefficient to calculate the ignition coil current duration (the current amount of the ignition coil). This makes it possible to easily adjust the ignition coil energization time in accordance with the ignition coil temperature TC and the required amount of energization.

[0189] (4) The ROM 60 (storage unit) according to the fourth embodiment described above stores a low temperature required dwell map, a high temperature required dwell map, and a voltage correction coefficient map. The low temperature required dwell map defines the relationship between the rotation speed and the low temperature map power supply amount. The high temperature required dwell map defines the relationship between the rotation speed and the high temperature map power supply amount. The voltage correction coefficient map defines the relationship between the power supply voltage VB of the ignition device and the voltage correction coefficient. The requirement setting unit 812 determines the low temperature map power supply time according to the rotation speed NE using the low temperature required dwell map, and determines the high temperature map power supply time according to the rotation speed NE using the high temperature required dwell map. The adjustment unit 813 sets the low temperature map power supply time and the ignition coil power supply time (the power supply amount of the ignition coil) based on the high temperature map power supply time in accordance with the ignition coil temperature TC (the temperature related to the ignition device). This makes it possible to easily adjust the ignition coil energization time in accordance with the ignition coil temperature TC and the required amount of energization.

[0190] (5) The adjustment unit 813 according to the fourth embodiment described above sets the ignition coil energization time (ignition coil energization amount) based on the low temperature map energization time (low temperature map energization amount) when the ignition coil temperature TC (temperature related to the ignition device) is lower than a predetermined low temperature setting value. Furthermore, the adjustment unit 813 sets the ignition coil energization time based on the high temperature map energization time (high temperature map energization amount) when the ignition coil temperature TC is higher than a predetermined high temperature setting value that is higher than the low temperature setting value. Furthermore, when the ignition coil temperature TC is between the low temperature setting value and the high temperature setting value, the adjustment unit 813 sets the ignition coil energization time based on the low temperature map energization time if the ignition coil temperature TC is changing from a state equal to or lower than the low temperature setting value toward the high temperature setting value. Furthermore, when the ignition coil temperature TC is changing from a state equal to or higher than the high temperature setting value toward the low temperature setting value, the adjustment unit 813 sets the ignition coil energization time based on the high temperature map energization time. As a result, 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 performing hysteresis control.

[0191] (6) The ignition coil energization time (amount of current flowing through the ignition coil) in the above-described embodiment is a total value obtained by summing up the actual energization time of the ignition coil 300, which performs a single ignition at each compression top dead center, two ignitions at each compression and exhaust top dead center, or multiple discharges (multiple ignitions / discharges) at times other than top dead center for one combustion cycle of the internal combustion engine 100. This makes it possible to easily adjust the ignition coil energization time (ignition coil energization amount) adjusted according to the ignition coil temperature TC and the required energization amount, and to apply the ignition coil energization time to multiple types of discharge (ignition) methods.

[0192] (7) The internal combustion engine according to the above-described embodiment includes a fuel injection device 134. The control device 1 (internal combustion engine control device) includes a fuel injection amount setting unit 815 that adjusts the amount of fuel injected by 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 ignition ability of the air-fuel mixture can be improved, thereby reducing the required amount of current. This makes it possible to easily adjust the ignition coil energization time according to the ignition coil temperature TC and the required amount of energization, and also to suppress misfires.

[0193] (8) The ignition coil temperature TC (temperature related to the ignition device) according to the first to fourth embodiments described above is calculated using a neural network model that uses at least the rotational speed NE as an explanatory variable. This makes it possible to estimate the ignition coil temperature TC 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 current application time, which is adjusted according to the ignition coil temperature TC, can be improved, and the heat balance of the ignition device can be appropriately controlled. As a result, the cost of the ignition device can be reduced.

[0194] (9) The explanatory variables input into the neural network models according to the first to fourth embodiments described above include parameters related to the heat generation of the ignition coil 300 in the ignition device (rotational speed NE, power supply voltage VB, amount of current flowing through the ignition coil, etc.) and parameters related to the heat balance inside and outside the ignition device (intake air temperature, intake air humidity, cooling water temperature, cooling air speed, etc.). This allows the ignition coil temperature TC to be estimated with high accuracy.

[0195] (10) The internal combustion engine control method according to the embodiment described above is a method for controlling an internal combustion engine 100 in which current flowing through an ignition coil 300 of an ignition device is turned on and off in accordance with a predetermined ignition timing. In this internal combustion engine control method, a requirement setting unit 812 determines a required amount of current flowing through the ignition coil 300 based on the rotational speed NE of the internal combustion engine 100. Next, an adjustment unit 813 adjusts the ignition coil current conduction time (amount of current flowing through the ignition coil) in accordance with the ignition coil temperature TC (temperature related to the ignition device) and the required amount of current. Then, an ignition control unit 83 controls the on / off state of the ignition coil 300 in accordance with the ignition coil current conduction time adjusted by the adjustment unit 813. This allows the heat balance of the ignition device to be appropriately controlled, and as a result, it is possible to prevent the ignition device from becoming larger and the costs from increasing.

[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 a first neural network model that uses at least the rotational speed NE of the internal combustion engine 100 as an explanatory variable. The adjustment unit 813 outputs a limited current supply time (limited current amount), which is the amount of current that can be supplied to the ignition coil 300, using a second neural network model that uses the ignition coil temperature TC, the power supply voltage VB, and the rotational speed NE as explanatory variables. The requirement setting unit 812 outputs a required current supply time (required current amount) for the ignition coil 300 using a third neural network model that uses at least the rotational speed NE and the ignition coil temperature TC as explanatory variables. The adjustment unit 813 also adjusts the ignition coil current supply time (the amount of current supplied to the ignition coil) based on the limited current supply time and the required current supply time. The ignition control unit then controls the on / off state of the ignition coil 300 in accordance with the ignition coil current supply time adjusted by the adjustment unit 813. This makes it possible to grasp the ignition coil temperature TC 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 reduced. In addition, the accuracy of the ignition coil temperature TC, limited current application time, and required current application time can be improved, improving the reliability of the adjusted ignition coil current application time and enabling appropriate control of the heat balance of the ignition device.

[0197] (12) The explanatory variables of the first neural network model or the third neural network model according to the first embodiment described above include parameters related to heat generation of the ignition coil 300 in the ignition device (rotational speed NE, power supply voltage VB, intake air flow rate, etc.) and parameters related to the heat balance inside and outside the ignition device (intake air temperature, intake air humidity, cooling water temperature, cooling air speed, etc.). This allows the ignition coil temperature TC to 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 spirit of the invention as defined in the claims.

[0199] Furthermore, the above-described embodiments have been described in detail to clearly explain the present invention, and are not necessarily limited to those including all of the configurations described. Furthermore, it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment, or to add the configuration of another embodiment to the configuration of one embodiment. Furthermore, it is possible to add, delete, or replace part of the configuration of each embodiment with another configuration. [Explanation of symbols]

[0200] 1...internal combustion engine control device, 10...analog input section, 20...digital input section, 30...A / D conversion section, 40...RAM, 50...MPU, 60...ROM, 70...I / O port, 80...output circuit, 81...overall control section, 82...fuel injection control section, 83...ignition control section, 84...cylinder discrimination section, 85...angle information generation section, 86...rotational speed information generation section, 87...intake amount measurement section, 88...load information generation section, 89...water temperature measurement section, 90...voltage measurement section, 100...internal combustion engine, 110...air cleaner, 111...intake pipe, 112...intake manifold, 113...throttle valve, 113a...throttle opening sensor, 114...flow rate 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 piping, 134...Fuel injector, 140...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 section, 361... Temperature detection section, 500, 501... Electric circuit, 811... Ignition timing setting section, 812... Demand setting section, 813... Adjustment section, 814... Ignition device temperature estimation section, 815... Fuel injection amount setting section, 816... Fuel injection timing setting section

Claims

1. An internal combustion engine control device that controls an internal combustion engine in which a current flowing through an ignition coil of an ignition device is turned on and off according to a predetermined ignition timing, a requirement setting unit that determines a required amount of current to be applied to the ignition coil based on a rotation speed of the internal combustion engine; an adjustment unit that adjusts the amount of current supplied to the ignition coil in accordance with the temperature related to the ignition device and the required amount of current; an ignition control unit that controls an on / off state of the ignition coil in accordance with the amount of current supplied to the ignition coil adjusted by the adjustment unit, The temperature related to the ignition device is output using a neural network model that uses at least the rotational speed as an explanatory variable. Internal combustion engine control device.

2. a required dwell map that defines the relationship between the rotation speed and the map current supply amount; a storage unit that stores a limited dwell map that defines a relationship between the rotational speed and a temperature related to the ignition device and a limited amount of current that is an amount of current that can be supplied to the ignition coil; the requirement setting unit calculates the required amount of current corresponding to the rotation speed using the required dwell map; The adjustment unit determines a limited amount of current depending on the rotation speed and a temperature related to the ignition device using the limited dwell map, and when the required amount of current is equal to or less than the limited amount of current, sets the amount of current to the ignition coil based on the required amount of current, and when the required amount of current is greater than the limited amount of current, sets the amount of current to the ignition coil based on the limited amount of current. The internal combustion engine control device according to claim 1.

3. a required dwell map that defines the relationship between the rotation speed and the map current supply amount; a voltage correction coefficient map that defines the relationship between a power supply voltage of the ignition device and a voltage correction coefficient; a temperature correction coefficient map that defines a relationship between a temperature and a temperature correction coefficient related to the ignition device; the requirement setting unit determines a map current supply amount according to the rotation speed using the requirement dwell map; A voltage correction coefficient corresponding to the power supply voltage is determined using the voltage correction coefficient map, and a temperature correction coefficient corresponding to a temperature related to the ignition device is determined using the temperature correction coefficient map. The adjustment unit calculates the amount of current supplied to the ignition coil by multiplying the map current supply amount by the voltage correction coefficient and the temperature correction coefficient. The internal combustion engine control device according to claim 1.

4. a low-temperature required dwell map that defines the relationship between the rotation speed and a low-temperature map energization amount; a high temperature required dwell map that defines the relationship between the rotation speed and a high temperature map energization amount; a storage unit that stores a voltage correction coefficient map that defines a relationship between a power supply voltage of the ignition device and a voltage correction coefficient; the requirement setting unit determines a low-temperature map energization amount corresponding to the rotational speed using the low-temperature required dwell map, and determines a high-temperature map energization amount corresponding to the rotational speed using the high-temperature required dwell map; The adjustment unit sets the amount of current supplied to the ignition coil based on the temperature related to the ignition device, the low temperature map current supply amount, and the high temperature map current supply amount. The internal combustion engine control device according to claim 1.

5. The adjustment unit sets the amount of current supplied to the ignition coil based on the low temperature map current supply amount when the temperature related to the ignition device is equal to or lower than a predetermined low temperature setting value, and sets the amount of current supplied to the ignition coil based on the high temperature map current supply amount when the temperature related to the ignition device is equal to or higher than a predetermined high temperature setting value that is higher than the low temperature setting value.

5. The internal combustion engine control device according to claim 4.

6. The amount of current flowing through the ignition coil is a value obtained by aggregating the actual time during which current is flowing through the ignition coil, which is turned on and off one or more times during one combustion cycle of the internal combustion engine. The internal combustion engine control device according to claim 1.

7. the internal combustion engine is equipped with a fuel injection device, a fuel injection amount setting unit that adjusts the amount of fuel injected by the fuel injection device based on the temperature related to the ignition device; The internal combustion engine control device according to claim 1.

8. 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 the heat balance inside and outside the ignition device. The internal combustion engine control device according to claim 1.

9. 1. A method for controlling an internal combustion engine in which a current flowing through an ignition coil of an ignition device is turned on and off in accordance with a predetermined ignition timing, comprising: a requirement setting unit that determines a required amount of current to be applied to the ignition coil based on a rotation speed of the internal combustion engine; an adjusting unit adjusting the amount of current supplied to the ignition coil in accordance with the temperature related to the ignition device and the required amount of current supplied; an ignition control unit controls an on / off state of the ignition coil in accordance with the amount of current supplied to the ignition coil adjusted by the adjustment unit; The temperature related to the ignition device is output using a neural network model that uses at least the rotational speed as an explanatory variable. Internal combustion engine control method.

10. 1. A method for controlling an internal combustion engine in which a current flowing through an ignition coil of an ignition device is turned on and off in accordance with a predetermined ignition timing, comprising: an ignition device temperature estimation unit outputs a temperature related to the ignition device using a first neural network model having at least a power supply voltage of the ignition device and a rotational speed of the internal combustion engine as explanatory variables; an adjustment unit outputs a limited current amount that is a current amount that can be supplied to the ignition coil using a second neural network model having a temperature related to the ignition device, the power supply voltage, and the rotational speed as explanatory variables; a requirement setting unit outputs a required amount of current to be supplied to the ignition coil using a third neural network model having at least the rotational speed and a temperature related to the ignition device as explanatory variables; the adjusting unit adjusts the amount of current supplied to the ignition coil based on the limited amount of current supplied and the required amount of current supplied; An ignition control unit controls the on / off state of the ignition coil in accordance with the amount of current supplied to the ignition coil adjusted by the adjustment unit. Internal combustion engine control method.

11. 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.

11. The method of controlling an internal combustion engine according to claim 10.

Images