JP2020133620A - Catalyst deterioration detection device, catalyst deterioration detection system, data analysis device, control device of internal combustion engine, and method for providing state information of used vehicle - Google Patents

Abstract

To provide a catalyst deterioration detection device which can reduce an accumulated amount of deviation of components of a fluid flowing into the catalyst with respect to components appropriate to purification of the catalyst.SOLUTION: Map data 76a stored in a storage device 76 is data specifying a neural network which uses, as inputs, time series data of variables corresponding to an upstream air-fuel ratio Afu and a downstream air-fuel ratio Afd so as to output a deterioration level variable, which is a variable indicating a deterioration level of an upstream catalyst 32. A CPU 72 calculates the deterioration level variable of the upstream catalyst 32 by input of the time series data of the variables corresponding to the upstream air-fuel ratio Afu and the downstream air-fuel ratio Afd into a mapping defined by the map data 76a.SELECTED DRAWING: Figure 1

Description

The present invention relates to a catalyst deterioration detection device for a catalyst provided in an exhaust passage of an internal combustion engine, a catalyst deterioration detection system, a data analysis device, a control device for an internal combustion engine, and a method for providing state information of a used car.

For example, in Patent Document 1 below, the air-fuel ratio of the air-fuel mixture to be burned in the combustion chamber is intentionally made lean to maximize the oxygen occlusion amount of the catalyst, and then the air-fuel ratio of the air-fuel mixture is intended. Devices that make it rich are described. This device detects that the oxygen storage amount of the catalyst becomes zero based on the detection value of the air-fuel ratio sensor downstream of the catalyst when the air-fuel ratio of the air-fuel mixture is intentionally enriched. Calculate the maximum value of the quantity. Here, since the maximum value of the oxygen storage amount decreases due to the aged deterioration of the catalyst, the maximum value indicates the degree of deterioration of the catalyst.

Japanese Unexamined Patent Publication No. 2012-117406

By the way, in the case of the above device, in order to detect the degree of deterioration, the time for shifting the air-fuel ratio of the air-fuel mixture from an appropriate value for exhaust gas purification control becomes long, or the amount of shifting becomes large, so that the catalyst is purified. The cumulative amount of deviation of the components of the fluid flowing into the catalyst with respect to the appropriate components may increase.

Hereinafter, means for solving the above problems and their actions and effects will be described.
1. 1. It is applied to a catalyst deterioration detection device for detecting deterioration of a catalyst provided in an exhaust passage of an internal combustion engine, and includes a storage device and an execution device, and the storage device includes oxygen contained in a fluid flowing into the catalyst. It corresponds to the time series data in the first predetermined period of the excess amount variable, which is a variable corresponding to the excess amount of the actual fuel amount with respect to the excess amount of the fuel that reacts without excess or deficiency, and the detection value of the air fuel ratio sensor on the downstream side of the catalyst. It stores the mapping data, which is the data that defines the mapping that inputs the time-series data in the second predetermined period of the downstream detection variable, which is a variable, and outputs the deterioration degree variable, which is a variable related to the deterioration degree of the catalyst. The execution device acquires the time-series data of the excess amount variable in the first predetermined period and the time-series data of the downstream detection variable in the second predetermined period, and the data acquired by the acquisition process. Determined when the degree of deterioration of the catalyst is equal to or higher than a predetermined value based on the calculation results of the deterioration degree variable calculation process for calculating the deterioration degree variable of the catalyst based on the output of the mapping as input and the calculation result of the deterioration degree variable calculation process. By operating the hardware of the above, a coping process for coping with the degree of deterioration of the catalyst being equal to or higher than a predetermined value is executed, and the mapping data includes data learned by machine learning. Is.

In the above configuration, the deterioration degree variable is calculated by mapping the time series data of the excess quantity variable and the time series data of the downstream detection variable as inputs. Here, the excess amount variable is an excess amount of the actual fuel amount with respect to the fuel amount that reacts with oxygen in just proportion, and becomes a negative value when the actual fuel amount is insufficient. In that case, information on oxygen and fuel flowing into the catalyst can be obtained from the time series data of the excess amount variable, and information on oxygen and unburned fuel flowing out downstream of the catalyst can be obtained from the time series data of the downstream detection variable. Therefore, it is possible to obtain information on the maximum value of the oxygen storage amount of the catalyst, and thus information on the degree of deterioration of the catalyst. Moreover, by using the above time series data, it is not always necessary to shift the air-fuel ratio of the air-fuel mixture from a value appropriate for exhaust gas purification control, and even if it is shifted, the time is shortened or the amount of shift is reduced. Can be done. Therefore, it is possible to reduce the cumulative amount of deviation of the components of the fluid flowing into the catalyst with respect to the components suitable for purification of the catalyst. Moreover, since the mapping data is learned by machine learning, it is necessary to associate the time series data of the excess amount variable and the downstream detection variable with the deterioration degree variable as compared with the human adaptation. Man-hours can be reduced.

2. 2. The input of the map includes the temperature of the catalyst, the acquisition process includes a process of acquiring the temperature of the catalyst, and the deterioration degree variable calculation process inputs the temperature of the catalyst to the map. The catalyst deterioration detection device according to 1 above, which is a process of calculating a deterioration degree variable of the catalyst based on the output of the map including the above.

The maximum value of oxygen storage of the catalyst changes depending on the temperature of the catalyst. Therefore, in the above configuration, by including the temperature of the catalyst in the input of the map, the deterioration degree variable can be made highly accurate while distinguishing whether the oxygen storage amount of the catalyst is decreasing due to deterioration or the temperature. Can be calculated.

3. 3. The catalyst deterioration detection device according to 1 or 2 above, wherein the excess amount variable includes a variable corresponding to a value detected by the air-fuel ratio sensor on the upstream side of the catalyst.
In the above configuration, by including the variable related to the detection value of the air-fuel ratio sensor on the upstream side as the excess amount variable, it is compared with the case where only the respective amounts of fuel and air provided for combustion in the combustion chamber are set as the excess amount variable. , It is possible to shorten the time until the influence of the excess amount variable reaches the detected value of the air-fuel ratio sensor on the downstream side. Therefore, it becomes easy to reduce the number of time series data as compared with the case where only the respective amounts of fuel and air to be burned in the combustion chamber are set as excess quantity variables.

4. The storage device includes a plurality of types of the mapping data, and the deterioration degree variable calculation process selects the mapping data to be used for calculating the deterioration degree variable of the catalyst from the plurality of types of mapping data. The catalyst deterioration detecting apparatus according to any one of 1 to 3 above, which includes a treatment.

In all situations, when constructing a map capable of outputting the deterioration degree variable with high accuracy, the structure of the map tends to be complicated. Therefore, in the above configuration, a plurality of types of mapping data are provided. This makes it possible to select the appropriate map according to the situation, in which case it is easier to simplify the structure of each of the multiple types of maps compared to dealing with all situations with a single map. ..

5. The plurality of types of mapping data include data for each region classified by the flow rate of the fluid flowing into the catalyst, and the selection process is used to calculate a deterioration degree variable of the catalyst based on the flow rate. The catalyst deterioration detecting apparatus according to 4 above, which includes a process of selecting the mapping data.

Even if the air-fuel ratio of the air-fuel mixture to be burned in the combustion chamber is the same, the excess amount of the actual fuel amount with respect to the amount of fuel that reacts with oxygen contained in the fluid flowing into the catalyst in just proportion flows into the catalyst. It changes greatly depending on the magnitude of the flow rate of the flowing fluid, and as a result, the change in the amount of oxygen stored in the catalyst per unit time becomes large. Therefore, the influence of the flow rate of the fluid flowing into the catalyst is likely to become apparent in the time series data of the downstream detection variable. Therefore, if a single mapping data is used regardless of the flow rate of the fluid flowing into the catalyst, it is necessary to learn the behavior of the time series data of the downstream detection variable that changes according to the flow rate of the fluid. Therefore, the structure of the mapping tends to be complicated. On the other hand, in the above configuration, it is easy to simplify the structure of the mapping by using different mapping data for each magnitude of the flow rate of the fluid flowing into the catalyst.

6. The plurality of types of the mapping data include data for each of a plurality of regions classified by the temperature of the catalyst, and the selection process is used to calculate the degree of deterioration of the catalyst based on the temperature of the catalyst. The catalyst deterioration detecting apparatus according to 4 above, which includes a process of selecting the mapping data.

Since the maximum value of oxygen occlusion of a catalyst changes depending on the temperature of the catalyst, even if the catalysts have the same degree of deterioration, if the temperatures differ between the catalysts, the time series of the downstream detection variables. The behavior of the data is different. Therefore, the structure of the map tends to be complicated when trying to discriminate the difference in the behavior of the time series data of the downstream detection variable according to the temperature. On the other hand, in the above configuration, it is easy to simplify the structure of the mapping by using different mapping data for each temperature of the catalyst.

7. The plurality of types of the mapping data include different data depending on whether or not the fuel cut process is executed, and the selection process is based on whether or not the fuel cut process is executed. The catalyst deterioration detecting apparatus according to 4 above, which includes a process of selecting the mapping data.

Since a large amount of oxygen flows into the catalyst during the execution period of the fuel cut treatment, the behavior of the time series data of the downstream detection variable differs greatly depending on whether or not the execution period of the fuel cut treatment is performed. Then, when the deterioration degree variable is calculated from a single mapping data in spite of these differences, the mapping structure tends to be complicated. On the other hand, in the above configuration, it is easy to simplify the structure of the mapping by using different mapping data depending on whether or not the fuel cut processing is executed.

8. The acquisition process is a process for acquiring a variable to be input to the mapping when a predetermined condition is satisfied, and the flow rate of the fluid flowing into the catalyst is within a predetermined range under the predetermined condition. The catalyst deterioration detection device according to any one of 1 to 4 above, which includes conditions.

Even if the air-fuel ratio of the air-fuel mixture to be burned in the combustion chamber is the same, the excess amount of the actual fuel amount with respect to the amount of fuel that reacts with oxygen contained in the fluid flowing into the catalyst in just proportion flows into the catalyst. It changes greatly depending on the magnitude of the flow rate of the flowing fluid, and as a result, the change in the amount of oxygen stored in the catalyst per unit time becomes large. Therefore, the influence of the flow rate of the fluid flowing into the catalyst is likely to become apparent in the time series data of the downstream detection variable. Therefore, if a single mapping data is used regardless of the flow rate of the fluid flowing into the catalyst, it is necessary to learn the behavior of the time-series data of the downstream detection variable that changes according to the flow rate of the fluid. Therefore, the structure of the mapping tends to be complicated. On the other hand, in the above configuration, by using the sampling value when the flow rate of the fluid flowing into the catalyst is within the predetermined range, it is possible to obtain a specialized mapping when the flow rate is within the predetermined range. It is easy to simplify the structure of the map.

9. The acquisition process is a process for acquiring a variable to be input to the mapping when a predetermined condition is satisfied, and the predetermined condition includes a condition that the temperature of the catalyst is within a predetermined range. The catalyst deterioration detection device according to any one of 1 to 4 above.

Since the maximum value of oxygen occlusion of a catalyst changes depending on the temperature of the catalyst, even if the catalysts have the same degree of deterioration, if the temperatures differ between the catalysts, the time series of the downstream detection variables. The behavior of the data is different. Then, when trying to discriminate the difference in the behavior of the time series data of the downstream detection variable according to the temperature, the structure of the map tends to be complicated. On the other hand, in the above configuration, it is easy to simplify the structure of the map by using the sampling value when the temperature of the catalyst is within a predetermined range.

10. The acquisition process is a process of acquiring a variable to be input to the map in synchronization with the condition of satisfying a predetermined condition. Under the predetermined condition, the amount of oxygen stored in the catalyst is the maximum value or the minimum value. The catalyst deterioration detection device according to any one of 1 to 4 above, which is a condition to the effect that the value is obtained.

Since the behavior of the time-series data of the downstream detection variable changes according to the amount of oxygen stored, the earliest downstream detection variable of the time-series data of the downstream detection variable is the oxygen storage amount. The behavior of the time-series data of the downstream detection variable differs depending on what happened. Therefore, when dealing with the case where the oldest downstream detection variable in the time series data of the downstream detection variable varies depending on the oxygen occlusion, a single mapping is used. , The structure of the map tends to be complicated. Therefore, in the above configuration, sampling is performed in synchronization with the time when the oxygen occlusion reaches the maximum value or the minimum value, so that it is possible to determine whether or not the time series data is in a situation, and by extension, the structure of the map. Can be simplified. Moreover, by inputting the time series data of the downstream detection variable, oxygen or not downstream of the catalyst can be clearly specified when the oxygen storage amount of the catalyst is switched from either the maximum value or zero to the other. The requirement to wait until a large amount of fuel is spilled can be relaxed or eliminated.

11. The coping process is the catalyst deterioration detection device according to any one of 1 to 10 above, which includes a limiting process for limiting the amount of unburned fuel flowing into the catalyst to a smaller side.
When the degree of deterioration is large, if a large amount of unburned fuel flows into the catalyst, it becomes difficult to sufficiently oxidize by oxygen in the catalyst, and there is a concern that the amount of unburned fuel flowing out to the downstream of the catalyst increases. To. Therefore, in the above configuration, when the degree of deterioration is equal to or higher than a predetermined value, the amount of unburned fuel flowing into the catalyst is limited to the smaller side, so that the amount of unburned fuel flowing out downstream of the catalyst can be suppressed from increasing.

12. The executing device and the storage device according to any one of the above 1 to 10 are provided, and the deterioration degree variable calculation process uses at least a part of the mapping data to obtain the maximum value of the oxygen occlusion of the catalyst. The execution device includes a first execution device and a second execution device, and the first execution device is mounted on a vehicle and includes the acquisition process, and includes an oxygen storage amount calculation process for calculating a corresponding value. The vehicle-side transmission process of transmitting the data acquired by the acquisition process to the outside of the vehicle, the vehicle-side reception process of receiving a signal based on the calculation result of the oxygen storage amount calculation process, and the countermeasure process are executed. The second execution device is arranged outside the vehicle and receives data transmitted by the vehicle-side transmission process, an external reception process, an oxygen storage amount calculation process, and an oxygen storage amount calculation. It is a catalyst deterioration detection system that executes an external transmission process of transmitting a signal based on the calculation result of the process to the vehicle.

In the above configuration, the calculation load of the in-vehicle device can be reduced by executing the oxygen storage amount calculation process outside the vehicle.
13. A data analysis device including the second execution device and the storage device according to the above 12.

14. A control device for an internal combustion engine including the first execution device according to the above 12.
15. A method of providing state information of a used car equipped with an internal combustion engine provided with a catalyst in an exhaust passage, wherein the acquisition process and the deterioration degree variable calculation process according to any one of 1 to 10 above. , A storage process for storing the calculation result of the deterioration degree variable calculation process in the storage device together with the vehicle ID, and an output process for outputting the deterioration degree information of the catalyst corresponding to the vehicle ID in response to an access from the outside. This is a method of providing status information of a used car that causes a computer to execute.

The degree of deterioration of the catalyst is useful information for grasping how much repair costs will be incurred after purchasing a used car. Therefore, in the above method, useful information about the state of the used car can be provided by storing the calculation result of the deterioration degree of the catalyst together with the vehicle ID and outputting the deterioration degree information according to the access from the outside. ..

The figure which shows the structure of the control device and the drive system of a vehicle which concerns on 1st Embodiment. The block diagram which shows a part of the processing executed by the control device which concerns on this embodiment. The flow chart which shows the procedure of the process specified by the deterioration detection program concerning this embodiment. The flow chart which shows the procedure of the fail-safe processing concerning this embodiment. The figure which shows the system which generates the mapping data concerning this embodiment. The flow chart which shows the procedure of the learning process of the mapping data which concerns on the same embodiment. The flow chart which shows the procedure of the process specified by the deterioration detection program which concerns on 2nd Embodiment. The flow chart which shows the procedure of the process specified by the deterioration detection program which concerns on 3rd Embodiment. The flow chart which shows the procedure of the process specified by the deterioration detection program which concerns on 4th Embodiment. The flow chart which shows the procedure of the selection process of the mapping data which concerns on 5th Embodiment. The flow chart which shows the procedure of the process specified by the deterioration detection program which concerns on 6th Embodiment. The flow chart which shows the procedure of the process specified by the deterioration detection program which concerns on 7th Embodiment. The figure which shows the structure of the catalyst deterioration detection system and the dealer terminal which concerns on 8th Embodiment. (A) and (b) are flow charts showing the procedure of the process executed by the catalyst deterioration detection system.

<First Embodiment>
Hereinafter, the first embodiment of the catalyst deterioration detecting apparatus will be described with reference to the drawings.
In the internal combustion engine 10 mounted on the vehicle VC shown in FIG. 1, a throttle valve 14 is provided in the intake passage 12, and a port injection valve 16 is provided downstream of the throttle valve 14. The air sucked from the intake passage 12 and the fuel injected from the port injection valve 16 flow into the combustion chamber 20 when the intake valve 18 opens. The internal combustion engine 10 is provided with an in-cylinder injection valve 22 for directly injecting fuel into the combustion chamber 20 and an ignition device 24 for generating spark discharge. In the combustion chamber 20, the air-fuel mixture is subjected to combustion, and the energy generated by the combustion is taken out as the rotational energy of the crankshaft 26. The air-fuel mixture used for combustion is discharged into the exhaust passage 30 as exhaust gas as the exhaust valve 28 is opened. The exhaust passage 30 is provided with an upstream catalyst 32 which is a three-way catalyst having an oxygen storage capacity and a downstream catalyst 34 which is a three-way catalyst having an oxygen storage capacity. The exhaust passage 30 is communicated with the intake passage 12 via the EGR passage 36. The EGR passage 36 is provided with an EGR valve 38 for adjusting the cross-sectional area of the flow path.

The rotational power of the crankshaft 26 is transmitted to the intake side camshaft 42 via the intake side valve timing variable device 40, while being transmitted to the exhaust side camshaft 46 via the exhaust side valve timing variable device 44. The intake side valve timing variable device 40 changes the relative rotational phase difference between the intake side cam shaft 42 and the crank shaft 26. The exhaust-side valve timing variable device 44 changes the relative rotational phase difference between the exhaust-side camshaft 46 and the crankshaft 26.

The crankshaft 26 of the internal combustion engine 10 is mechanically connected to the carrier C of the planetary gear mechanism 50 that constitutes the power split mechanism. The rotating shaft of the motor generator 52 is mechanically connected to the sun gear S of the planetary gear mechanism 50, and the rotating shaft of the motor generator 54 and the drive wheels 56 are mechanically connected to the ring gear R of the planetary gear mechanism 50. It is connected. The voltage of the battery 62 is applied to each terminal of the motor generator 52 via the inverter 58, and the voltage of the battery 62 is applied to each terminal of the motor generator 54 via the inverter 60.

The control device 70 targets the internal combustion engine 10, and in order to control the torque, the exhaust component ratio, etc., which are the controlled amounts thereof, the throttle valve 14, the port injection valve 16, the in-cylinder injection valve 22, the ignition device 24, and the like. The operation units of the EGR valve 38, the intake side valve timing variable device 40, the exhaust side valve timing variable device 44, and the like are operated. Further, the control device 70 controls the motor generator 52, and operates the inverter 58 in order to control the torque and the rotation speed which are the control amounts thereof. Further, the control device 70 targets the motor generator 54 as a control target, and operates the inverter 60 in order to control the torque and the rotation speed which are the control amounts thereof. In addition, FIG. 1 shows a throttle valve 14, a port injection valve 16, an in-cylinder injection valve 22, an ignition device 24, an EGR valve 38, an intake side valve timing variable device 40, an exhaust side valve timing variable device 44, and inverters 58 and 60. The respective operation signals MS1 to MS9 of the above are described.

When controlling the control amount, the control device 70 has an intake air amount Ga detected by the air flow meter 80 and an upstream side detection value which is a detection value of the upstream side air-fuel ratio sensor 82 provided on the upstream side of the upstream side catalyst 32. Afu, the downstream side detection value Afd which is the detection value of the downstream side air-fuel ratio sensor 84 provided between the upstream side catalyst 32 and the downstream side catalyst 34 is referred to. Further, the control device 70 refers to the output signal Scr of the crank angle sensor 86, the accelerator operation amount ACCP which is the amount of depression of the accelerator pedal detected by the accelerator sensor 88, and the vehicle speed SPD detected by the vehicle speed sensor 90. Further, the control device 70 uses the atmospheric pressure Pa detected by the atmospheric pressure sensor 92, the outside temperature TO detected by the outside temperature sensor 94, the charge / discharge current I of the battery 62 detected by the current sensor 96, and the voltage sensor 98. Refer to the detected terminal voltage V of the battery 62.

The control device 70 includes a CPU 72, a ROM 74, a storage device 76 which is an electrically rewritable non-volatile memory, and a peripheral circuit 77, which are made communicable by the local network 78. The peripheral circuit 77 includes a circuit that generates a clock signal that defines the internal operation, a power supply circuit, a reset circuit, and the like.

The control device 70 executes the control of the control amount by the CPU 72 executing the program stored in the ROM 74.
FIG. 2 shows a part of the processing realized by the CPU 72 executing the program stored in the ROM 74.

The base injection amount calculation process M10 is a process of calculating the base injection amount Qb, which is the base value of the fuel amount for setting the air-fuel ratio of the air-fuel mixture in the combustion chamber 20 as the target air-fuel ratio, based on the filling efficiency η. Specifically, in the base injection amount calculation process M10, for example, when the filling efficiency η is expressed as a percentage, the filling efficiency η is set to the fuel amount QTH per 1% of the filling efficiency η for setting the air-fuel ratio as the target air-fuel ratio. The process may be such that the base injection amount Qb is calculated by multiplying. The base injection amount Qb is a fuel amount calculated to control the air-fuel ratio to the target air-fuel ratio based on the amount of air filled in the combustion chamber 20. By the way, the target air-fuel ratio is the theoretical air-fuel ratio. The filling efficiency η is a parameter that determines the amount of air filled in the combustion chamber 20, and is calculated by the CPU 72 based on the rotation speed NE and the intake air amount Ga. Further, the rotation speed NE is calculated by the CPU 72 based on the output signal Scr of the crank angle sensor 86.

The feedback processing M12 obtains a feedback correction coefficient KAF obtained by adding "1" to the correction ratio δ of the base injection amount Qb as the feedback operation amount, which is the operation amount for feedback-controlling the upstream detection value Afu to the target value Af *. This is a process to calculate and output. Specifically, the feedback processing M12 holds and outputs each output value of the proportional element and the differential element that input the difference between the upstream detection value Afu and the target value Af *, and the integrated value of the values corresponding to the difference. The sum with the output value of the integrating element is defined as the correction ratio δ.

The required injection amount calculation process M14 is a process of calculating the required injection amount Qd by multiplying the base injection amount Qb by the feedback correction coefficient KAF.
The injection valve operation process M16 outputs an operation signal MS2 to the port injection valve 16 or an operation signal to the in-cylinder injection valve 22 in order to operate the port injection valve 16 and the in-cylinder injection valve 22 based on the required injection amount Qd. It is a process of outputting MS3. Specifically, the injection valve operation process M16 sets the ratio of the fuel injection amount by the port injection valve 16 to the required injection amount Qd as the injection rate Kp, and operates the port injection valve 16 and the in-cylinder injection valve 22 accordingly. It is a process to do.

In the sub-feedback processing M18, when the downstream detection value Afd is rich by a predetermined amount εr or more with respect to the stoichiometric point Afs indicating the stoichiometric air-fuel ratio, the target value Af * is set to lean by a specified amount δl with respect to the stoichiometric point Afs. It is a process to do. Further, in the sub-feedback processing M18, when the downstream detection value Afd is lean by a predetermined amount εl or more with respect to the stoichiometric point Afs indicating the stoichiometric air-fuel ratio, the target value Af * is set to the specified amount δr with respect to the stoichiometric point Afs. It is a process to make it rich.

In the fuel cut process M19, when it is detected that the accelerator pedal is released based on the accelerator operation amount ACCP and the rotation speed NE is equal to or higher than a predetermined speed, the fuel from the port injection valve 16 and the in-cylinder injection valve 22 is charged. This is a process to stop the injection. The injection valve operation process M16 includes a process of increasing and correcting the required injection amount Qd in a predetermined period after returning from the fuel cut process.

The ignition process M20 is a process of outputting an operation signal MS4 to the ignition device 24 in order to operate the ignition timing aim, which is the operation amount of the ignition device 24. The ignition process M20 basically includes a process of setting the base ignition timing according to the rotation speed NE and the filling efficiency η, and setting the ignition timing aim based on the base ignition timing. The ignition process M20 includes a process of setting the ignition timing aig based on the ignition timing retarded by the retard angle Δaig with respect to the base ignition timing during the warm-up process of the upstream catalyst 32.

The catalyst temperature calculation process M22 is a process of calculating the catalyst temperature Tcat, which is the temperature of the upstream catalyst 32, based on the rotation speed NE, the filling efficiency η, the ignition timing aim, and the vehicle speed SPD. Specifically, the catalyst temperature calculation process M22 is realized as follows. That is, the base temperature is map-calculated by the CPU 72 in a state where the map data having the rotation speed NE and the filling efficiency η as the input variables and the base temperature as the output variables is stored in the ROM 74 in advance. Further, the ignition timing correction amount is mapped by the CPU 72 in a state where the map data in which the ignition timing aig is used as an input variable and the ignition timing correction amount which is the correction amount of the base temperature by the ignition timing aig is used as an output variable is stored in the ROM 74 in advance. It is calculated. Further, the map calculation is performed by the CPU 72 in a state where the map data in which the vehicle speed SPD is used as an input variable and the vehicle speed correction amount which is the correction amount of the base temperature by the vehicle speed SPD is used as an output variable is stored in the ROM 74 in advance. Then, the CPU 72 calculates the catalyst temperature Tcat by correcting the base temperature with the ignition timing correction amount and the vehicle speed correction amount.

The map data is a set of data of discrete values of input variables and values of output variables corresponding to the values of the input variables. In the map calculation, for example, when the value of the input variable matches any of the values of the input variable of the map data, the value of the output variable of the corresponding map data is used as the calculation result, whereas when they do not match, the map is used. The processing may be performed on the value obtained by interpolating the values of a plurality of output variables included in the data as the calculation result.

The in-catalyst flow rate calculation process M24 is a process for calculating the in-catalyst flow rate CF, which is the volumetric flow rate of the fluid flowing through the upstream catalyst 32, based on the rotation speed NE and the filling efficiency η. Specifically, this process is realized as follows. That is, the CPU 72 calculates the mass flow rate of the fluid flowing into the upstream catalyst 32 based on the filling efficiency η and the rotation speed NE. Further, the CPU 72 estimates the pressure and temperature of the fluid flowing into the upstream catalyst 32 based on the rotation speed NE and the filling efficiency η, and converts the mass flow rate into a volume flow rate based on this. Then, the CPU 72 converts the converted volumetric flow rate into the volumetric flow rate in the upstream catalyst 32 based on the ratio of the flow path cross-sectional area of the upstream catalyst 32 to the flow path cross-sectional area of the exhaust passage 30 upstream thereof. , Calculate the flow rate CF in the catalyst.

The output control process M30 is a process of calculating the output Pmg required for the motor generators 52 and 54 and the output Peg required for the internal combustion engine 10 based on the accelerator operation amount ACCP and the vehicle speed SPD. In particular, the output control process M30 selects the EV mode in which the output Pmg of the internal combustion engine 10 is zero when the charge rate SOC of the battery 62 is equal to or higher than the predetermined value Sth, while the charge rate SOC is less than the predetermined value Sth. Is a process of selecting an EHV mode that secures a required output in cooperation with the internal combustion engine 10 and the motor generators 52 and 54. The charge rate SOC is calculated by the CPU 72 based on the terminal voltage V and the charge / discharge current I. That is, for example, when the absolute value of the charge / discharge current I is negligibly small, the CPU 72 considers the terminal voltage V as the open end voltage and calculates the charge rate SOC based on the relationship between the open end voltage and the charge rate SOC. .. When the absolute value of the charge / discharge current I is large, the charge rate SOC is updated by the charge / discharge current I.

The MG control process M32 is a process of outputting operation signals MS8 and MS9 to the inverters 58 and 60, respectively, so that the sum of the outputs of the motor generators 52 and 54 is the output Pmg.

The throttle operation process M34 is a process of outputting the operation signal MS1 to the throttle valve 14 so that the output of the internal combustion engine 10 becomes the output Peg based on the output Peg.
In addition to the process shown in FIG. 2, the control device 70 executes a process of calculating the degree of deterioration of the upstream catalyst 32. Hereinafter, this will be described in detail based on FIG. 3 and the like.

The process shown in FIG. 3 is realized by the CPU 72 repeatedly executing the deterioration detection program 74a stored in the ROM 74 shown in FIG. 1, for example, at a predetermined cycle. In the following, the step number of each process is represented by a number prefixed with "S".

In the series of processes shown in FIG. 3, the CPU 72 first determines a predetermined period for each of the upstream average value Afave, the downstream average value Afdave, the flow rate CF in the catalyst, the rotation speed NE, the filling efficiency η, and the catalyst temperature Tcat. Acquires the time series data in (S10). In the following, the time-series data of, for example, the upstream average value Afave will be described as "Afave (1) to Afave (sn)" in the order of oldest sampling timing. Here, "sn" is the number of data included in the time series data of each variable. That is, the predetermined period is set to a period in which "sn" of each variable is sampled, and is determined by the sampling period and the number of data "sn", and is determined by a value such as the downstream detection value Afd. It's not a thing.

The upstream average value Afuave is the average value of the upstream detection value Afu at the sampling interval of the time series data. That is, the CPU 72 samples the upstream side detection value Afu a plurality of times during the sampling interval of the time series data, calculates the average value thereof, and sets it as the upstream side average value Afuave. Similarly, the downstream average value Afdave is the average value of the downstream detected value Afd at the sampling interval of the time series data.

Next, the CPU 72 substitutes the values acquired by the processing of S10 into the input variables x (1) to x (6sn) of the map that outputs the deterioration degree variable Rd, which is a variable indicating the deterioration degree of the upstream catalyst 32 (. S12). That is, assuming that m = 1 to sn, the CPU 72 substitutes the upstream average value Afave (m) into the input variable x (m) and substitutes the downstream average value Afdave (m) into the input variable x (sn + m). , The in-catalyst flow rate CF (m) is substituted into the input variable x (2sn + m), and the rotation speed (m) is substituted into the input variable x (3sn + m). Further, the CPU 72 substitutes the filling efficiency η (m) into the input variable x (4 sn + m) and substitutes the catalyst temperature Tcat (m) into the input variable x (5 sn + m).

Next, the CPU 72 inputs the input variables x (1) to x (6sn) into the mapping defined by the mapping data 76a stored in the storage device 76 shown in FIG. 1, and thereby, the degree of deterioration which is the output value of the mapping. The variable Rd is calculated (S14). Here, calculating the output value of the map means calculating the variable, which means calculating the value of the variable. In the present embodiment, the deterioration degree variable Rd is quantified as follows.

Rd = 1-RR
RR = (maximum value of actual oxygen occlusion at a predetermined temperature of the upstream catalyst 32) / (maximum value of oxygen occlusion at a predetermined temperature of the reference catalyst)
As a result, the deterioration degree variable Rd expresses that the larger the value is, the larger the degree of deterioration is. In particular, when the maximum value of the oxygen storage amount of the upstream catalyst 32 is equal to the maximum value of the oxygen storage amount of the reference catalyst. Becomes "0".

In the present embodiment, in this mapping, the number of intermediate layers is "α", the activation functions h1 to hα of each intermediate layer are hyperbolic tangents, and the activation function f of the output layer is ReLU. It is composed of networks. Note that ReLU is a function that outputs the smaller of the input and zero. For example, the value of each node in the first intermediate layer is a linear map defined by the coefficient w (1) ji (j = 0 to n1, i = 0 to 6 sn), and the above input variables x (1) to x ( It is generated by inputting the output when 6sn) is input to the activation function h1. That is, assuming that m = 1, 2, ..., α, the value of each node in the mth mesosphere is generated by inputting the output of the linear map defined by the coefficient w (m) into the activation function hm. Will be done. Here, n1, n2, ..., Nα are the number of nodes in the first, second, ..., And α intermediate layers, respectively. Incidentally, w (1) j0 and the like are bias parameters, and the input variable x (0) is defined as “1”.

Next, the CPU 72 determines whether or not the deterioration degree variable Rd is equal to or greater than the specified value RdsH (S16). Then, when the CPU 72 determines that the value is equal to or higher than the specified value RdsH (S16: YES), the CPU 72 operates the warning light 99 shown in FIG. 1 to execute a notification process to notify the outside in order to prompt the user for repair (S18). ..

On the other hand, when the CPU 72 determines that the value is less than the specified value RdsH (S16: NO), the CPU 72 determines whether or not the deterioration degree variable Rd is equal to or greater than the predetermined value RdsL (S20). Here, the predetermined value RdsL is a value smaller than the specified value RdsH. When the CPU 72 determines that the value is RdsL or more (S20: YES), the fail flag F is set to “1” (S22). When the processing of S18 is performed, it is assumed that the fail flag F is already set to "1". On the other hand, when the CPU 72 determines that the value is less than the predetermined value RdsL (S20: NO), the CPU 72 substitutes “0” for the fail flag F (S24).

When the processes of S18, S22, and S24 are completed, the CPU 72 temporarily ends the series of processes shown in FIG.
FIG. 4 shows a procedure of treatment other than the treatment of S18 among the treatments for dealing with the deterioration of the upstream catalyst 32. The process shown in FIG. 4 is realized by the CPU 72 repeatedly executing the fail-safe program 74b stored in the ROM 74 shown in FIG. 1, for example, at a predetermined cycle.

In the series of processes shown in FIG. 4, the CPU 72 determines whether or not the fail flag F is “1” (S30). When the CPU 72 determines that the value is "0" (S30: NO), the CPU 72 substitutes the reference value Sth0 for the predetermined value Sth used in the output control process M30, and sets the reference amount δl0 to the above-mentioned specified amount δl of the subfeedback. Substituting and substituting the reference amount δr0 into the specified amount δr, and substituting the reference amount Δaig0 into the retard angle amount Δaig for the catalyst warm-up treatment (S32).

On the other hand, when the CPU 72 determines that the fail flag F is “1” (S30: YES), the CPU 72 substitutes a value obtained by increasing and correcting the reference value Sth0 by a predetermined amount ΔSth into the predetermined value Sth (S34). In this treatment, the amount of unburned fuel flowing into the upstream catalyst 32 is reduced by stopping the internal combustion engine 10 as much as possible in view of the fact that the oxidizing ability of the unburned fuel is reduced due to the deterioration of the upstream catalyst 32. Is a process that limits to the smaller side.

Further, the CPU 72 substitutes the value obtained by reducing and correcting the reference amount δl0 by the correction amount Δδl into the specified amount δl, and substitutes the value obtained by reducing and correcting the reference amount δr0 by the correction amount Δδr into the specified amount δr (S36). .. This treatment is a treatment for limiting the amount of unburned fuel flowing into the upstream catalyst 32 to the smaller side in view of the fact that the oxidizing ability of the unburned fuel is reduced due to the deterioration of the upstream catalyst 32. That is, when the fail flag F is "1", the specified amount δr is smaller than that when the fail flag F is "0". Therefore, the target value Af * is enriched when it is richer than the stoichiometric point Afs. The degree becomes smaller. Therefore, the amount of unburned fuel in the exhaust gas flowing into the upstream catalyst 32 in a unit time is smaller than that when the fail flag F is "0", and the unburned fuel flows out to the downstream of the upstream catalyst 32. Can be suppressed.

Further, the CPU 72 substitutes the value obtained by increasing and correcting the reference amount Δaig0 by the correction amount ΔF into the retard angle amount Δaig (S38). In this process, when the upstream catalyst 32 deteriorates, the exhaust gas purification performance is lower than when it is not deteriorated. Therefore, in order to warm up the upstream catalyst 32 at an early stage, the combustion energy of the air-fuel mixture becomes torque. The purpose is to reduce the conversion ratio and raise the temperature of the exhaust gas discharged to the exhaust passage 30.

When the processes of S32 and S38 are completed, the CPU 72 temporarily ends the series of processes shown in FIG.
Next, a method for generating mapping data 76a will be described.

FIG. 5 shows a system for generating mapping data 76a.
As shown in FIG. 5, in the present embodiment, the dynamometer 100 is mechanically connected to the crankshaft 26 of the internal combustion engine 10. Then, various state variables when the internal combustion engine 10 is operated are detected by the sensor group 102, and the detection results are input to the matching device 104, which is a computer that generates mapping data 76a. The sensor group 102 includes an upstream air-fuel ratio sensor 82, a downstream air-fuel ratio sensor 84, a crank angle sensor 86, and the like, which are sensors that detect values for generating an input to a map.

FIG. 6 shows a procedure for generating mapping data. The process shown in FIG. 6 is performed by the matching device 104. The process shown in FIG. 6 may be realized, for example, by equipping the conforming device 104 with a CPU and a ROM and executing the program stored in the ROM by the CPU.

In the series of processes shown in FIG. 6, the matching device 104 first acquires the same data as the training data acquired in the process of S10 based on the detection result of the sensor group 102 (S40). In this process, a plurality of upstream catalysts 32 having different values of deterioration degree variables Rd measured in advance individually are prepared, and one of them is selectively mounted on the internal combustion engine 10. The deterioration degree variable Rdt of the mounted upstream catalyst 32 is the teacher data.

Next, the matching device 104 substitutes training data other than the teacher data into the input variables x (1) to x (6sn) in the same manner as in S12 (S42). Then, the matching device 104 calculates the deterioration degree variable Rd by inputting the input variables x (1) to x (6sn) obtained by the processing of S42 into the map in the same manner as the processing of S14 (S44). Then, the CPU 72 determines whether or not the number of samples of the deterioration degree variable Rd calculated by the process of S44 is equal to or greater than a predetermined number (S46). Here, in order to exceed a predetermined value, it is required that the deterioration degree variable Rd is calculated a plurality of times for all of the plurality of upstream catalysts 32 described above. Further, here, it is required that the deterioration degree variable Rd is calculated at various operating points defined by the rotation speed NE and the filling efficiency η by changing the operating state of the internal combustion engine 10.

When the conforming device 104 determines that the value is not equal to or higher than the predetermined value (S46: NO), the process returns to the process of S40. On the other hand, when the CPU 72 determines that the value is equal to or higher than a predetermined value (S46: YES), the sum of squares of the differences between the deterioration degree variable Rdt as the teacher data and the deterioration degree variable Rd calculated by the processing of S44. The coefficients w (1) ji, w (2) kj, ..., W (α) 1p are updated so as to minimize the above (S48). Then, the matching device 104 stores the coefficients w (1) ji, w (2) kj, ..., W (α) 1p as the learned mapping data 76a (S50).

Here, the action and effect of this embodiment will be described.
The mapping data 76a receives time-series data of each of the upstream average value Afave, the downstream average value Afdave, the flow rate CF in the catalyst, the rotation speed NE, the filling efficiency η, and the catalyst temperature Tcat, and outputs the deterioration degree variable Rd. It is learned as defining the mapping to be performed. Here, the rotation speed NE and the filling efficiency η that define the operating point of the internal combustion engine 10 can be regarded as flow rate variables indicating the flow rate of the fluid flowing into the upstream catalyst 32. The upstream average value Afave is a variable indicating the ratio of the actual fuel amount to the fuel amount that reacts with oxygen contained in the fluid flowing into the upstream catalyst 32 without excess or deficiency. Therefore, the upstream average value Afave, the rotation speed NE, and the filling efficiency η collaborate with each other to be an excess amount of the actual fuel amount with respect to the amount of fuel that reacts with oxygen contained in the fluid flowing into the upstream side catalyst 32 in just proportion. Construct an excess variable that is a corresponding variable. However, the excess amount can also be a negative amount. In other words, it can be a value obtained by multiplying the actual shortage of fuel amount by "-1" with respect to the amount of fuel that reacts with oxygen contained in the fluid flowing into the upstream catalyst 32 in just proportion.

The behavior of the downstream average value Afdave changes according to the maximum value of the oxygen occlusion of the upstream catalyst 32 in addition to the excess amount of the fluid flowing into the upstream catalyst 32. The maximum value of the oxygen storage amount changes not only according to the degree of deterioration of the upstream catalyst 32 but also according to the temperature of the upstream catalyst 32. Therefore, the deterioration degree variable Rd of the upstream catalyst 32 can be calculated by inputting the time series data of the excess amount variable and the time series data of the catalyst temperature Tcat and the time series data showing the behavior of the downstream average value Afdave. it is conceivable that. As described above, in the present embodiment, the map for calculating the deterioration degree variable Rd by randomly inputting various variables of the internal combustion engine 10 is not learned by machine learning, but is familiar with the control of the internal combustion engine 10. Based on the findings of the inventor, the variables to be input to the map were carefully selected. Therefore, compared with the case where the inventor's knowledge is not used, it is possible to reduce the number of layers in the intermediate layer of the neural network and the number sn of the time series data, and the structure of the map for calculating the deterioration degree variable Rd can be reduced. Easy to simplify.

In particular, by grasping the behavior of the downstream average value Afdave with respect to the excess amount variable and the catalyst temperature Tcat from the time series data of each of these variables, it is directly understood that the oxygen storage amount of the upstream side catalyst 32 becomes zero or the maximum value. The deterioration degree variable Rd can be calculated without detecting it. Therefore, since the deterioration degree variable Rd can be calculated without changing the target value Af * for detecting the degree of deterioration, the fluid flowing into the upstream side catalyst 32 for a component suitable for purification of the upstream side catalyst 32 The cumulative amount of component deviation can be reduced.

According to the present embodiment described above, the effects described below can be further obtained.
(1) The upstream average value Afave was included in the input of the map. As a result, compared with the case of using the upstream detection value Afu for each time interval of the time series data, the oxygen and unburned fuel flowing into the upstream catalyst 32 without increasing the number of data of the time series data can be obtained. Accurate information can be obtained, and the deterioration degree variable Rd can be calculated with higher accuracy.

(2) The downstream average value Afdave was included in the input of the map. As a result, compared with the case where the downstream detection value Afd for each time interval of the time series data is used, the oxygen and unburned fuel flowing out from the upstream catalyst 32 without increasing the number of data of the time series data can be obtained. Accurate information can be obtained, and the deterioration degree variable Rd can be calculated with higher accuracy.

(3) Rotation speed NE and filling efficiency η as operating point variables that define the operating point of the internal combustion engine 10 were used as mapping inputs. The amount of operation of the operation unit of the internal combustion engine 10 such as the ignition device 24, the EGR valve 38, and the intake side valve timing variable device 40 tends to be determined based on the operating point of the internal combustion engine 10. Therefore, the operating point variable is a variable that not only constitutes a flow rate variable together with the upstream average value Afave, but also includes information on the operation amount of each operation unit. Therefore, by inputting the operating point variable to the mapping, the deterioration degree variable Rd can be calculated based on the information on the operation amount of each operation unit, and the deterioration degree variable Rd can be calculated with higher accuracy. ..

(4) The flow rate CF in the catalyst was included in the input of the map. The flow rate CF in the catalyst is a variable that affects the reaction rate between the unburned fuel and oxygen in the upstream catalyst 32. Therefore, the deterioration degree variable Rd can be calculated with higher accuracy by using the flow rate CF in the catalyst as the input of the map. Incidentally, in the present embodiment, the flow rate CF in the catalyst was calculated from the operating point variable of the internal combustion engine 10. Therefore, in principle, by including the operating point variable in the input of the map, the flow rate CF in the catalyst affects the reaction rate between the unburned fuel and oxygen in the upstream catalyst 32 without using the flow rate CF in the catalyst. It is possible to calculate the deterioration degree variable Rd while grasping the effect. However, in order to make this possible, the number of layers in the intermediate layer of the neural network and the number sn of time series data tend to increase. On the other hand, by including the flow rate CF in the catalyst in the input of the map as in the present embodiment, the structure of the map can be simplified.

<Second embodiment>
Hereinafter, the second embodiment will be described with reference to the drawings, focusing on the differences from the first embodiment.

In the present embodiment, the output of the neural network is set to the maximum value Cmax of the current oxygen occlusion of the upstream catalyst 32.
FIG. 7 shows a procedure of processing executed by the control device 70 in the present embodiment. The process shown in FIG. 7 is realized by the CPU 72 repeatedly executing the deterioration detection program 74a stored in the ROM 74 shown in FIG. 1, for example, at a predetermined cycle. In the process shown in FIG. 7, the same step number is assigned to the process corresponding to the process shown in FIG. 3 for convenience.

In the series of processes shown in FIG. 7, when the process of S10 is completed, the CPU 72 inputs time series data other than the catalyst temperature Tcat to the mapping input variables x (1) to x (5sn) instead of the process of S12. Input (S12a). The input variables x (1) to x (5sn) are assigned the same variables as in the process of S12.

Then, the CPU 72 calculates the maximum value Cmax using a neural network that inputs the input variables x (1) to x (5sn) and outputs the maximum value Cmax (S14a). Next, the CPU 72 uses map data in which the catalyst temperature average value Tcatave, which is the average value of the catalyst temperature Tcat acquired in S10, and the maximum value Cmax are input variables, and the deterioration degree variable Rd is an output variable. The deterioration degree variable Rd is mapped (S52).

Then, the CPU 72 shifts to the process of S16.
In the present embodiment, the coefficients w (1) ji, w (2) kj, ..., W (α) 1p of the neural network may be learned using the following teacher data. That is, by measuring the relationship between the temperature of each of the plurality of upstream catalysts 32 and the maximum value Cmax in advance, the current maximum of the target upstream catalyst 32 in the process corresponding to the process of FIG. The value Cmax may be obtained and used as the teacher data.

<Third embodiment>
Hereinafter, the third embodiment will be described with reference to the drawings, focusing on the differences from the first embodiment.

In the present embodiment, some average values of the respective time series data of the flow rate CF in the catalyst, the rotation speed NE, the filling efficiency η, and the catalyst temperature Tcat are calculated, and these are used as the mapping input. Hereinafter, in FIG. 8, this embodiment will be described assuming that the number sn of the time series data of each variable acquired by the process of S10 is a multiple of “5”.

FIG. 8 shows a procedure of processing executed by the control device 70 in the present embodiment. The process shown in FIG. 8 is realized by the CPU 72 repeatedly executing the deterioration detection program 74a stored in the ROM 74 shown in FIG. 1, for example, at a predetermined cycle. In the process shown in FIG. 8, the same step number is assigned to the process corresponding to the process shown in FIG. 3 for convenience.

In the series of processes shown in FIG. 8, when the process of S10 is completed, the CPU 72 has "sn / 5" pieces of each of the catalyst flow rate CF, the rotation speed NE, the filling efficiency η, and the catalyst temperature Tcat in order from the earliest. The average value of each is calculated (S60). That is, for example, the average value of the in-catalyst flow rates CF (1), CF (2), ..., CF (sn / 5) is set as the in-catalyst flow rate average value CFave (1), and the in-catalyst flow rate CF ((sn / 5)). Let +1), CF ((sn / 5) +2), ..., CF (2sn / 5) be the average value of the flow rate in the catalyst CFave (2). In this way, time-series data consisting of "5" each of the average flow rate in the catalyst CFave, the average rotation speed NEave, the average filling efficiency ηave, and the average catalyst temperature Tcatave is generated.

Next, the CPU 72 substitutes the time-series data generated by the processing of S60 and the time-series data of the upstream average value Afave and the downstream average value Afdave acquired in the processing of S10 into the input variable x of the map. (S12b). That is, the CPU 72 substitutes the upstream average value Afave (m) into the input variable x (m) and substitutes the downstream average value Afdave (m) into the input variable x (sn + m), assuming that m = 1 to sn. Further, the CPU 72 substitutes the in-catalyst flow rate average value CFave (m) into the input variable x (2sn + m) and substitutes the rotation speed average value NEave (m) into the input variable x (2sn + 5 + m), assuming that m = 1-5. .. Further, the CPU 72 substitutes the filling efficiency average value ηave (m) into the input variable x (2sn + 10 + m), and substitutes the catalyst temperature average value Tcatave into the input variable x (2sn + 15 + m).

Then, the CPU 72 calculates the deterioration degree variable Rd by a neural network that inputs the input variables x (1) to x (2sn + 20) generated in S12b and outputs the deterioration degree variable Rd (S14b). Here, the coefficient w (1) ji is “i = 0 to 2 sn + 20”.

When the CPU 72 completes the process of S14b, the CPU 72 shifts to the process of S16.
As described above, according to the present embodiment, the dimension of the map input is set by using the catalyst flow average value CFave, the rotation speed average value NEave, the filling efficiency average value ηave, and the catalyst temperature average value Tcatave as the mapping inputs. It can be reduced. In the present embodiment, the excess amount variable is constructed by the cooperation of the time series data of the upstream average value Afave, the time series data of the rotation speed average value NEave, and the time series data of the filling efficiency average value ηave. Here, the rotation speed average value NEave and the filling efficiency average value ηave indicate the operating points of the internal combustion engine 10 in the sampling period for "sn / 5" pieces of the upstream average value Afave.

<Fourth Embodiment>
Hereinafter, the fourth embodiment will be described with reference to the drawings, focusing on the differences from the first embodiment.

In the present embodiment, the storage device 76 stores different mapping data for each operating point of the internal combustion engine 10 and the catalyst temperature Tcat as mapping data 76a.
FIG. 9 shows a procedure of processing executed by the control device 70 in the present embodiment. The process shown in FIG. 9 is realized by the CPU 72 repeatedly executing the deterioration detection program 74a stored in the ROM 74 shown in FIG. 1, for example, at a predetermined cycle. In the process shown in FIG. 9, the same step number is assigned to the process corresponding to the process shown in FIG. 3 for convenience.

In the series of processes shown in FIG. 9, the CPU 72 first obtains mapping data for calculating the deterioration degree variable Rd according to the rotation speed NE that defines the operating point of the internal combustion engine 10, the filling efficiency η, and the catalyst temperature Tcat. Select (S62). For example, the CPU 72 specifies the mapping data in a state where the map data in which the rotation speed NE, the filling efficiency η, and the catalyst temperature Tcat are input variables and the variables that specify the mapping data are the output variables are stored in the ROM 74 in advance. This can be achieved by performing map operations on the variables to be used. Next, the CPU 72 acquires time-series data of the upstream average value Afave and the downstream average value Afdave (S10c).

Next, the CPU 72 substitutes the time series data acquired in the process of S10c into the input variable x of the map defined by the map data selected by the process of S62 (S12c). That is, the CPU 72 substitutes the upstream average value Afave (m) into the input variable x (m) and substitutes the downstream average value Afdave (m) into the input variable x (sn + m), assuming that m = 1 to sn. Then, the CPU 72 calculates the deterioration degree variable Rd by a neural network that inputs the input variables x (1) to x (2sn) generated in the process of S12c and outputs the deterioration degree variable Rd (S14c). Here, the coefficient w (1) ji is “i = 0 to 2 sn”.

When the CPU 72 completes the process of S14c, the CPU 72 shifts to the process of S16.
For learning the mapping data used when the operating point of the plurality of mapping data is in the predetermined range and the catalyst temperature Tcat is in the predetermined range, the operating point is in the predetermined range and the catalyst temperature Tcat is set. Only training data within a predetermined range is used.

As described above, in the present embodiment, the deterioration degree variable Rd is calculated using the mapping data of each of the operating points of the internal combustion engine 10 and the catalyst temperature Tcat. Therefore, when the operating points of the internal combustion engine 10 are significantly different, the CPU 72 calculates the deterioration degree variable Rd using different mapping data. Therefore, the flow rate of the fluid flowing into the upstream catalyst 32 when the mapping defined by one mapping data is used does not change significantly. In that case, the excess amount of the actual fuel amount with respect to the amount of fuel that reacts with oxygen contained in the fluid flowing into the upstream side catalyst 32 without excess or deficiency can be grasped only from the upstream side average value Afave. That is, the excess amount variable can be constructed only from the upstream average value Afave. Also, the catalyst temperature Tcat when the mapping defined by one mapping data is used does not change significantly. In that case, in the situation where the mapping defined by one mapping data is used, the degree of deterioration of the upstream catalyst 32 is larger when the maximum value Cmax of the oxygen storage amount is small than when it is large. That is, the degree of deterioration can be quantified according to the maximum value Cmax at the current temperature.

Therefore, in the present embodiment, the dimension of the variable that is the input of the map can be reduced, and thereby the number of layers nα of the intermediate layer can be reduced. Therefore, in this embodiment, the structure of the map can be simplified.

<Fifth Embodiment>
Hereinafter, the fifth embodiment will be described with reference to the drawings, focusing on the differences from the first embodiment.

In the present embodiment, three types of mapping data are stored in the storage device 76 as mapping data 76a.
FIG. 10 shows a procedure for selecting which of the above three types of mapping data is used to calculate the degree of deterioration Rd. The process shown in FIG. 10 is realized by repeatedly executing the deterioration detection program 74a stored in the ROM 74 shown in FIG. 1 by the CPU 72, for example, at a predetermined cycle.

In the series of processes shown in FIG. 10, the CPU 72 first determines whether or not the fuel cut process is in progress (S70). Then, when the CPU 72 determines that the fuel cut process is in progress (S70: YES), the CPU 72 selects the first mapping data (S74). The first mapping data is dedicated mapping data when the fuel cut processing is being executed, and is learned by using the data at the time of the fuel cut processing as training data.

On the other hand, when the CPU 72 determines that the fuel cut process is not in progress (S70: NO), the CPU 72 determines whether or not it is within the above-mentioned predetermined period after the fuel cut process (S72). Then, when the CPU 72 determines that the period is within the predetermined period (S72: YES), the CPU 72 selects the second mapping data (S76). The second mapping data is learned as training data using time series data sampled in a predetermined period after the fuel cut process. That is, the time-series data sampled during the period in which the required injection amount Qd is increased and corrected is learned as training data.

On the other hand, when the CPU 72 determines that the period is not within the predetermined period (S72: NO), the CPU 72 selects the third mapping data (S78). The third mapping data is learned by using the sampled time series data as training data in the region excluding the fuel cut process and the predetermined period after the fuel cut process.

When the processes of S74, S76, and S78 are completed, the CPU 72 temporarily ends the series of processes shown in FIG.
As described above, in the present embodiment, the deterioration degree variable Rd is calculated using the mapping data separately for the predetermined period during the fuel cut processing, the predetermined period after the fuel cut processing, and the rest. Here, during the fuel cut treatment, a large amount of oxygen flows into the upstream catalyst 32, and the air-fuel ratio of the air-fuel mixture to be burned tends to be disturbed in a predetermined period after the fuel cut treatment. Therefore, it is easy to simplify the structure of the map as compared with the case where the same map data is used for these different situations.

<Sixth Embodiment>
Hereinafter, the sixth embodiment will be described with reference to the drawings, focusing on the differences from the fourth embodiment.

In the present embodiment, the structure of the map is simplified by limiting the conditions for permitting sampling of the variable used for calculating the deterioration degree variable Rd.
FIG. 11 shows a procedure of processing executed by the control device 70 in the present embodiment. The process shown in FIG. 11 is realized by the CPU 72 repeatedly executing the deterioration detection program 74a stored in the ROM 74 shown in FIG. 1, for example, at a predetermined cycle. In the process shown in FIG. 11, the same step number is assigned to the process corresponding to the process shown in FIG. 3 for convenience.

In the series of processes shown in FIG. 11, the CPU 72 determines whether or not the logical product of the following conditions (a) to (c) is true (S80).
Condition (a): The condition that the rotation speed NE is equal to or higher than the first speed NEL and equal to or lower than the second speed NEH.

Condition (a): It is a condition that the filling efficiency η is equal to or more than the first efficiency ηL and is equal to or less than the second efficiency ηH.
Condition (c): It is a condition that the catalyst temperature Tcat is equal to or higher than the first temperature TcatL and lower than the second temperature TcatH.

When the CPU 72 determines that the logical product is true (S80: YES), the CPU 72 executes the processing after S10c in FIG. 9, assuming that sampling of the mapping input is permitted.
As described above, in the present embodiment, the deterioration degree variable Rd is calculated only when the operating point of the internal combustion engine 10 is within the predetermined range and the catalyst temperature Tcat is within the predetermined range. Here, by limiting the range in which the operating point can be taken, the deterioration degree variable Rd can be calculated only when the flow rate of the fluid flowing into the upstream catalyst 32 does not deviate significantly from the reference value. In that case, the excess amount of the actual fuel amount with respect to the amount of fuel that reacts with oxygen contained in the fluid flowing into the upstream side catalyst 32 without excess or deficiency can be grasped only from the upstream side average value Afave. That is, the excess amount variable can be constructed only from the upstream average value Afave. Further, by limiting the range in which the catalyst temperature Tcat can be taken, the deterioration degree variable Rd can be calculated only when the catalyst temperature Tcat does not deviate significantly from the reference temperature. In that case, when the maximum value Cmax of the oxygen storage amount is small, the degree of deterioration of the upstream catalyst 32 is larger than when it is large. That is, the degree of deterioration can be quantified according to the maximum value Cmax at the current temperature.

Therefore, in the present embodiment, the dimension of the variable that is the input of the map can be reduced, and thereby the number of layers nα of the intermediate layer can be reduced. Therefore, in this embodiment, the structure of the map can be simplified.

<7th Embodiment>
Hereinafter, the seventh embodiment will be described with reference to the drawings, focusing on the differences from the first embodiment.

In the present embodiment, the structure of the map is simplified by limiting the conditions for permitting sampling of the variable used for calculating the deterioration degree variable Rd.
FIG. 12 shows a procedure of processing executed by the control device 70 in the present embodiment. The process shown in FIG. 12 is realized by the CPU 72 repeatedly executing the deterioration detection program 74a stored in the ROM 74 shown in FIG. 1, for example, at a predetermined cycle. In the process shown in FIG. 12, the same step number is assigned to the process corresponding to the process shown in FIG. 3 for convenience.

In the series of processes shown in FIG. 12, the CPU 72 first has a true logical sum of the condition (d) that it is the time of recovery from the fuel cut process and the condition (e) that the oxygen storage amount is zero. It is determined whether or not there is (S82). This process is a process of determining whether or not the oxygen storage amount of the upstream catalyst 32 is zero or the maximum value Cmax. Here, if the oxygen storage amount is zero, for example, the air-fuel ratio feedback control is greatly deviated, and if it is detected that the upstream side detection value Afu becomes rich and the downstream side detection value Afd becomes rich soon. Good.

When the CPU 72 determines that the logical sum is true (S82: YES), the CPU 72 executes the processes of S10 to S24. Note that once the process of S14 is executed, the CPU 72 does not calculate the deterioration degree variable Rd until a positive determination is made again in the process of S82.

As described above, according to the present embodiment, the first value of the time series data that is the input of the mapping can be fixed when the oxygen storage amount of the upstream catalyst 32 is the maximum value Cmax or zero. .. Therefore, the mapping that outputs the deterioration degree variable Rd may be a mapping that outputs the deterioration degree variable Rd by inputting the time series data when the oxygen storage amount of the upstream catalyst 32 is the maximum value Cmax or zero. Therefore, it is easy to simplify the structure of the map as compared with the map that outputs the deterioration degree variable Rd in all situations.

<8th Embodiment>
Hereinafter, the eighth embodiment will be described with reference to the drawings, focusing on the differences from the first embodiment.

In the present embodiment, the deterioration degree variable Rd is calculated outside the vehicle.
FIG. 13 shows a catalyst deterioration detection system according to this embodiment. In FIG. 13, the members corresponding to the members shown in FIG. 1 are designated by the same reference numerals for convenience.

The control device 70 in the vehicle VC shown in FIG. 13 includes a communication device 79. The communication device 79 is a device for communicating with the center 120 via the network 110 outside the vehicle VC.

The center 120 analyzes the data transmitted from the plurality of vehicle VCs. The center 120 includes a CPU 122, a ROM 124, a storage device 126, a peripheral circuit 127, and a communication device 129, which can be communicated by the local network 128. The deterioration detection main program 124a is stored in the ROM 124, and the mapping data 126a is stored in the storage device 126.

The center 120 can communicate with the terminal 130 of the used car dealer via the network 110.
FIG. 14 shows a procedure of processing executed by the system shown in FIG. The process shown in FIG. 14A is realized by the CPU 72 executing the deterioration detection subprogram 74c stored in the ROM 74 shown in FIG. Further, the process shown in FIG. 14B is realized by the CPU 122 executing the deterioration detection main program 124a and the state information providing program 124b stored in the ROM 124. Note that the processes corresponding to the processes shown in FIG. 2 in FIG. 14 are assigned the same step numbers for convenience. In the following, the process shown in FIG. 14 will be described along with the time series of the deterioration detection process.

As shown in FIG. 14A, in the vehicle VC, the CPU 72 first acquires some variables to be input to the mapping in addition to the time series data acquired in the process of S10 (S90). That is, the CPU 72 acquires time-series data of the increased amount average value Qiave, which is the average value of the increased amount Qi of the required injection amount Qd with respect to the base injection amount Qb. Here, the increased amount Qi can take a negative value and indicates an excess or deficiency with respect to the amount of fuel required to make the air-fuel ratio of the air-fuel mixture the stoichiometric air-fuel ratio, and constitutes an excess amount variable. To do.

Further, the CPU 72 is a variable related to the amount of operation of the operation unit of the internal combustion engine 10, and is a variable that changes the combustion of the air-fuel mixture in the combustion chamber 20 and changes the component of the fluid flowing into the upstream catalyst 32. Get the variable of. That is, the CPU 72 acquires time-series data of the ignition timing average value American, which is the average value of the ignition timing aid by the ignition device 24. Further, the CPU 72 has an EGR rate which is an average value of the EGR rate Regr, which is the ratio of the flow rate of the same fluid to the sum of the flow rate of the air sucked into the intake passage 12 and the flow rate of the fluid flowing from the EGR passage 36 into the intake passage 12. Acquire the time series data of the average value Regave. Further, the CPU 72 separates the time series data of the overlap amount average value ROave, which is the average value of the overlap amount RO, which is the period in which the valve opening period of the intake valve 18 and the valve opening period of the exhaust valve 28 overlap. The time-series data of the spray rate average value Kpave, which is the average value of the rate Kp, is acquired.

Further, the CPU 72 acquires the alcohol concentration Da in the fuel. This is in view of the fact that the stoichiometric air-fuel ratio of the fuel changes depending on the alcohol concentration. The alcohol concentration Dal may be estimated from, for example, the correction ratio δ of the feedback process M12 described above. Further, the CPU 72 acquires the atmospheric pressure Pa and the outside air temperature TO as variables related to the environment and changing the combustion of the air-fuel mixture in the combustion chamber 20 to change the components of the fluid flowing into the upstream catalyst 32. ..

Further, the CPU 72 acquires the sulfur poisoning amount Qs of the upstream catalyst 32, which is a state variable related to aging among the state variables of the upstream catalyst 32. This is in view of the fact that the purification capacity of the upstream catalyst 32 changes depending on the sulfur poisoning amount Qs. The sulfur poisoning amount Qs is calculated by the CPU 72 by an integration process of a value obtained by multiplying the required injection amount Qd by a predetermined coefficient. Further, the CPU 72 uses the maximum value Cmax at the reference temperature, the length Lud from the upstream side to the downstream side, and the amount of the noble metal supported as specification variables which are variables indicating the specifications of the state variables of the upstream catalyst 32. Get Qpm. This is a setting for calculating the degree of deterioration of the upstream catalyst 32 having various specifications with one mapping data.

When the processing of S90 is executed, the CPU 72 operates the communication device 79 to transmit the data acquired in the processing of S90 to the center 120 together with the vehicle ID which is the identification information of the vehicle VC (S92).

On the other hand, the CPU 122 of the center 120 receives the transmitted data (S96) and substitutes the data acquired by the processing of S90 into the mapping input variable x (S12d), as shown in FIG. 14 (b). ). Here, in addition to the processing of S12, the CPU 122 substitutes the increase amount average value Qiave (m) into the input variable x (6 sn + m) with m = 1 to sn, and sets the input variable x (7 sn + m) to the ignition timing average value aidave. Substitute (m) and substitute the EGR rate average value Regave (m) into the input variable x (8sn + m). Further, the CPU 122 substitutes the overlap amount average value ROave (m) into the input variable x (9sn + m), and substitutes the ejection rate average value Kpave (m) into the input variable x (10sn + m). Further, the CPU 122 substitutes the alcohol concentration Dal for x (11sn + 1), substitutes the atmospheric pressure Pa for the input variable x (11sn + 2), substitutes the outside temperature TO for the input variable x (11sn + 3), and substitutes the input variable x ( Substitute the sulfur poisoning amount Qs into 11sn + 4). Further, the CPU 122 substitutes the maximum value Cmax into the input variable x (11sn + 5), substitutes the length Lud into the input variable x (11sn + 6), and substitutes the carrying amount Qpm into the input variable x (11sn + 7).

Then, the CPU 122 inputs the input variables x (1) to x (11sn + 7) generated by S12d into the mapping defined by the mapping data 126a, and calculates the deterioration degree variable Rd (S14d). Here, the mapping input coefficient wji defined by the mapping data 126a is “i = 0 to 11sn + 7”.

Then, by operating the communication device 129, the CPU 122 transmits a signal regarding the deterioration degree variable Rd to the vehicle VC to which the data received by the processing of S96 is transmitted (S98). On the other hand, as shown in FIG. 14A, the CPU 72 receives the deterioration degree variable Rd (S94) and executes the processes S16 to S24.

Further, as shown in FIG. 14A, the CPU 122 updates the deterioration degree variable Rd relating to the vehicle specified by the vehicle ID among the state information data 126b stored in the storage device 126 shown in FIG. S100).

Then, the CPU 122 determines whether or not there is a request for vehicle state information such as the deterioration degree variable Rd for a specific vehicle from the terminal 130 of the used car dealer (S102). Then, when the CPU 122 determines that there is a request (S102: YES), the CPU 122 accesses the storage device 126 and searches for the deterioration degree variable Rd corresponding to the vehicle ID (S104). Then, by operating the communication device 129, the CPU 122 outputs the deterioration degree variable Rd or the like corresponding to the requested vehicle ID to the terminal 130 as the state information of the used car (S106).

The CPU 122 temporarily ends the process shown in FIG. 14B when the process of S106 is completed or when a negative determination is made in the process of S102. Incidentally, the processes of S96 to S98 are defined in the deterioration detection main program 124a, and the processes of S100 to S106 are defined in the state information providing program 124b.

As described above, in the present embodiment, since the deterioration degree variable Rd is calculated at the center 120, the calculation load of the CPU 72 can be reduced.
Further, in the present embodiment, the deterioration degree variable Rd is stored and updated together with the vehicle ID at the center 120. Therefore, when the vehicle specified by the vehicle ID is handed over to the used car dealer and sold as a used car, the deterioration degree variable Rd is provided to the used car dealer as state information indicating the state of the used car. be able to. As a result, a customer who is considering purchasing a used car can obtain detailed information on the degree of deterioration of the vehicle under consideration.

<Correspondence>
The correspondence between the matters in the above embodiment and the matters described in the column of "Means for Solving the Problem" is as follows. In the following, the correspondence is shown for each number of the solution means described in the column of "Means for solving the problem". [1 to 3] The execution device corresponds to the CPU 72 and the ROM 74. The first predetermined period and the second predetermined period correspond to the periods in which the upstream average values Afave (1) to Afave (sn) are sampled. The acquisition process corresponds to the processes of S10 and S10c. The deterioration degree variable calculation process corresponds to the process of S12 and S14, the process of S12a, S14a and S52, the process of S12b and S14b, and the process of S12c and S14c. The coping process corresponds to the process of S18 and the process of FIG. In the process of FIG. 3, the time-series data regarding the excess amount variable corresponds to the respective time-series data of the upstream average value Afave, the rotation speed NE, and the filling efficiency η. The downstream detection variable corresponds to the time series data of the downstream average value Afdave. [4] The selection process corresponds to the process of S62 and the process of S70 to S78. [5, 6] Corresponds to the processing of S62. [7] Corresponds to the process of FIG. [8] The predetermined conditions correspond to the conditions (a) and (b) in the processing of S80. [9] The predetermined condition corresponds to the condition (c) in the processing of S80. [10] The predetermined condition corresponds to the condition to be determined whether or not it is satisfied by the process of S82. [11] The restriction process corresponds to the processes of S34 and S36. That is, processing such as operating the inverters 58 and 60 as predetermined hardware to increase the output of the motor generators 52 and 54 and stopping the internal combustion engine 10 is supported. [12] The catalyst deterioration detection system corresponds to the control device 70 and the center 120. The value corresponding to the oxygen occlusal amount corresponds to the deterioration degree variable Rd. The first execution device corresponds to the CPU 72 and the ROM 74. The second execution device corresponds to the CPU 122 and the ROM 124. The acquisition process corresponds to the process of S90, the vehicle-side transmission process corresponds to the process of S92, and the vehicle-side reception process corresponds to the process of S94. The external reception process corresponds to the process of S96. The oxygen storage amount calculation process corresponds to the processes of S12d and S14d. The vehicle-side transmission process corresponds to the process of S98. [13] The data analysis device corresponds to the center 120. [14] The control device of the internal combustion engine corresponds to the control device 70. [15] The acquisition process corresponds to the process of S90, the deterioration degree variable calculation process corresponds to the process of S12d and S14d, the storage process corresponds to the process of S100, and the output process corresponds to the process of S106. To do. The computer corresponds to CPUs 72, 122 and ROMs 74, 124.

<Other Embodiments>
In addition, this embodiment can be implemented by changing as follows. The present embodiment and the following modified examples can be implemented in combination with each other within a technically consistent range.

・ "About the first predetermined period and the second predetermined period"
In the above configuration, the first predetermined period, which is the sampling period of the time series data of the upstream average value Afave, and the second predetermined period, which is the sampling period of the time series data of the downstream average value Afdave, are set to be the same period. Not limited to this. For example, the second predetermined period may be slightly delayed from the first predetermined period. Here, the delay time of the second predetermined period with respect to the first predetermined period may be shorter than when the flow rate of the fluid flowing into the upstream catalyst 32 is large, but it is possible to reduce the conforming man-hours. It is desirable to set the delay time to a fixed value.

Further, it is not essential that the length of the first predetermined period and the length of the second predetermined period match.
・ "About time series data of excess variables"
The time-series data of the excess amount variable is not limited to the data exemplified in the above embodiment. That is, the set data consisting of equal numbers of the three state variables of the upstream average value Afave, the rotation speed NE, and the filling efficiency η, the time series data of the upstream average value Afave, and the upstream average value Afave. The number of samplings is not limited to the set data of the rotation speed NE and the filling efficiency η. For example, in the case of the above embodiment, even if the rotation speed NE and the filling efficiency η are not included in the mapping input, the flow rate CF in the catalyst can be regarded as a variable that determines the flow rate of the fluid flowing into the upstream catalyst 32. Further, for example, the intake air amount Ga may be used as a variable that determines the flow rate of the fluid flowing into the upstream catalyst 32 included in the time series data of the excess amount variable.

For example, it may consist of time-series data of the upstream average value Afave in a predetermined period and a single data in a predetermined period of a variable that determines the flow rate of the fluid flowing into the upstream catalyst 32. That is, for example, it may be a single set of the time series data of the upstream average value Afave in the predetermined period, the rotation speed NE and the filling efficiency η in the predetermined period. In this case, the rotation speed NE and the filling efficiency η are variables that determine the flow rate of the fluid flowing into the upstream catalyst 32 in a predetermined period corresponding to the time series data of the upstream average value Afave, and the flow rate in the predetermined period. We consider the change to be negligible.

The time series data regarding the excess amount variable is not limited to the one using the upstream average value Afave. For example, if the sampling period of the upstream detection value Afu is shortened, the time series data itself of the upstream detection value Afu may be used.

Further, the data on the upstream detection value Afu is not limited to the one using the data. For example, it may be the integrated value of the required injection amount Qd at the sampling interval of the time series data and the time series data of the intake air amount Ga. Further, for example, the increase amount Qi and the rotation speed NE may be used.

・ "About downstream detection variables"
Instead of using the time-series data of the downstream average value Afdave as the input to the map, the time-series data of the downstream-side detection value Afd may be used.

・ "About flow rate CF in catalyst"
The input to the map may be a single sampling value of the flow rate CF in the catalyst instead of using the time series data of the flow rate CF in the catalyst.

In the above embodiment, the flow rate CF in the catalyst is calculated from the rotation speed NE and the filling efficiency η, but the present invention is not limited to this. For example, a pressure sensor and a temperature sensor are provided on the upstream side of the upstream side catalyst 32 in the exhaust passage 30 and in the immediate vicinity of the upstream side catalyst 32, and the flow rate in the catalyst is based on these values and the intake air amount Ga. CF may be calculated.

・ "Catalyst temperature"
The input to the mapping may be a single sampling value of the catalyst temperature Tcat instead of using the time series data of the catalyst temperature Tcat or the time series data of the catalyst temperature average value Tcatave.

Further, for example, the catalyst temperature Tcat may be deleted from the input to the map, and all the inputs of the catalyst temperature calculation process M22 may be input to the map instead. Even with this, the deterioration degree variable Rd can be calculated with high accuracy by increasing the number of layers of the intermediate layer.

・ "About map input"
In the above embodiment, the set of the rotation speed NE and the filling efficiency η is used as the operating point variable that defines the operating point of the internal combustion engine 10 for the input of the map, but the present invention is not limited to this. For example, the intake air amount Ga and the rotation speed NE may be used as the operating point variables. Further, for example, as described in the column of "About the internal combustion engine" below, when applied to a compression ignition type internal combustion engine, the rotation speed NE and the injection amount, the rotation speed NE and the accelerator operation amount ACCP are used as operating point variables. May be good. However, it is not essential to include the operating point variable in the map input.

The mapping input illustrated in the process of FIG. 14 does not require that the process of S14d be executed at the center 120. In other words, the processing of S12d and S14d may be executed in the control device 70.

The input variables exemplified in the process of S14d may be changed as follows, for example.
For example, instead of the time-series data of the increased amount average value Qiave, the time-series data of the increased amount Qi may be used. Further, it is not limited to the increased amount Qi and the increased amount average value Qiave, for example, the time series data of the excess rate obtained by dividing the increased amount Qi by the base injection amount Qb, the time series data of the average value of the excess rate, and the required injection amount. Time series data of Qd and its average value may be used. At this time, it is not necessary that the sampling number of the time series data used as the input of the mapping matches the sampling number of the downstream average value Afdave. Further, instead of the time series data, a single increase amount Qi, excess rate, and required injection amount Qd within a predetermined period may be used. Further, instead of the time series data, a single increase amount average value Qiave within a predetermined period, an excess rate average value, and a required injection amount Qd average value may be used. The average value in this case is preferably an average value over a predetermined period. However, even in the processing shown in FIG. 14B, it is not essential to include the above variables related to the injection amount in the mapping input.

Further, for example, instead of the time-series data of the ignition timing average value American, the time-series data of the ignition timing aid itself may be used. Further, not limited to the time series data, a single ignition timing aim within a predetermined period or a single ignition timing average value agiave within a predetermined period may be used. However, it is desirable that the average ignition timing value aigave in this case is an average value over a predetermined period. However, even in the process shown in FIG. 14B, it is not essential to include such a variable related to the ignition timing aim in the mapping input.

Further, for example, the time series data of the EGR rate Regr itself may be used instead of the time series data of the EGR rate average value Regave. Further, the data is not limited to the time series data, and a single EGR rate Regr within a predetermined period or a single EGR rate average value Regave within a predetermined period may be used. However, it is desirable that the EGR rate average value Regave in this case is an average value over a predetermined period. However, even in the processing shown in FIG. 14B, it is not essential to include such a variable related to the EGR rate Regr in the input of the map.

Further, for example, instead of the time-series data of the overlap amount average value ROave, the time-series data of the overlap amount RO itself may be used. Further, the data is not limited to the time series data, and a single overlap amount RO within a predetermined period or a single overlap amount average value ROave within a predetermined period may be used. However, it is desirable that the average value ROave of the overlap amount in this case is an average value over a predetermined period. Further, as a variable related to the overlap amount, set data of the valve opening timing of the intake valve 18 and the valve opening timing of the exhaust valve 28 may be used. However, even in the processing shown in FIG. 14B, it is not essential to include such a variable related to the overlap amount RO in the mapping input.

Further, for example, instead of the time-series data of the average value Kpave of the spraying rate, the time-series data of the spraying rate Kp itself may be used. Further, the data is not limited to the time series data, and a single spouting rate Kp within a predetermined period or a single spouting rate average value Kpave within a predetermined period may be used. However, it is desirable that the average value Kpave of the spraying rate in this case is an average value over a predetermined period. However, even in the processing shown in FIG. 14B, it is not essential to include such a variable related to the ejection rate Kp in the input of the map.

Further, for example, instead of the alcohol concentration Dal, the average value of the alcohol concentration Dal within a predetermined period may be used. Further, time-series data of the alcohol concentration Dal within a predetermined period or time-series data of the average value of the alcohol concentration Dal within a predetermined period may be used. The fuel property variable, which is a variable indicating the fuel property, is not limited to the theoretical air-fuel ratio variable indicating the difference in the stoichiometric air-fuel ratio of the fuel, such as alcohol concentration Dal, and is, for example, either heavy fuel or light fuel. It may indicate that. However, even in the processing shown in FIG. 14B, it is not essential to include the fuel property variable in the mapping input.

Further, for example, instead of the atmospheric pressure Pa, the average value of the atmospheric pressure Pa within a predetermined period may be used. Further, the time-series data of the atmospheric pressure Pa within the predetermined period and the time-series data of the average value of the atmospheric pressure Pa within the predetermined period may be used. However, even in the processing shown in FIG. 14B, it is not essential to include the variable related to the atmospheric pressure Pa in the input of the map.

Further, for example, instead of the outside air temperature TO, the average value of the outside air temperature TO within a predetermined period may be used. Further, time-series data of the outside air temperature TO within a predetermined period or time-series data of the average value of the outside air temperature TO within a predetermined period may be used. However, even in the processing shown in FIG. 14B, it is not essential to include the variable related to the outside air temperature TO in the mapping input.

Further, for example, instead of the sulfur poisoning amount Qs, the average value of the sulfur poisoning amount Qs within a predetermined period may be used. Further, time-series data of the sulfur poisoning amount Qs within a predetermined period and time-series data of the average value of the sulfur poisoning amount Qs within a predetermined period may be used. However, even in the processing shown in FIG. 14B, it is not essential to include the variable related to the sulfur poisoning amount Qs in the input of the map.

The specification variables that determine the specifications of the upstream catalyst 32 are not limited to those consisting of the maximum value Cmax, the length Lud from the upstream to the downstream, and the supported amount Qpm. For example, for these three parameters, only one or two of them may be used. However, even in the processing shown in FIG. 14B, it is not essential to include the specification variable in the mapping input.

For example, as described in the column of "About the internal combustion engine" below, when the internal combustion engine 10 includes a supercharger and a wastegate valve, the opening degree of the wastegate valve may be included in the input of the map. That is, since the flow of the fluid to the upstream catalyst 32 changes according to the opening degree of the wastegate valve, the consumption of stored oxygen is affected. Therefore, the opening degree is included in the mapping input. By doing so, it is possible to learn such a phenomenon as well.

The variable related to the flow rate of the fluid flowing into the upstream catalyst 32 is not input to the map, and is not limited to the one illustrated in the above embodiment. For example, when the internal combustion engine mounted on the series hybrid vehicle described in the "About vehicle" column below is driven only at a predetermined operating point, a variable related to the flow rate of the fluid flowing into the upstream catalyst 32. Does not have to be entered in the mapping. Further, for example, as described in the column of "About the sampling period of time series data" below, when the process of changing the target value Af * for the calculation of the deterioration degree variable Rd is executed only at a predetermined operation point, etc. Also, it is not necessary to input a variable related to the flow rate of the fluid flowing into the upstream catalyst 32 into the map.

The input to the neural network and the input to the regression equation described in the "About machine learning algorithm" column below are not limited to those in which each dimension consists of a single physical quantity. For example, for some of the plurality of types of physical quantities input to the mapping in the above embodiment, instead of directly inputting to the neural network or regression equation, some principal components by their principal component analysis are used. It may be a direct input to a neural network or regression equation. However, when the principal component is the input of the neural network or the regression equation, it is not essential that only a part of the input to the neural network or the regression equation is the principal component, and the whole may be the principal component. When the principal component is input to the mapping, the mapping data 76a and 126a include data that defines the mapping that defines the principal component.

・ "About mapping data"
For example, according to the description of FIG. 11 and the like, the number of layers of the intermediate layer of the neural network is expressed as more than two layers, but the present invention is not limited to this. In particular, from the viewpoint of reducing the computing load of the control device 70, it is desirable to limit the number of layers of the intermediate layer of the neural network to one or two layers, for example, performing the processes of FIGS. 9 to 12. In this case, it is easier to realize as compared with the case of executing the process of FIG.

In the above embodiment, the activation functions h1, h2, ... Hα are set to hyperbolic tangents, and the activation function f is set to ReLU, but the present invention is not limited to this. For example, the activation functions h1, h2, ... Hα may be ReLU. For example, the activation functions h1, h2, ... Hα may be used as a logistic jigmoid function. Further, for example, the activation function f may be a logistic jigmoid function.

・ "About multiple types of mapping data"
In the process of FIG. 9, rotation speed NE and filling efficiency η are used as variables related to the flow rate of the fluid flowing into the upstream catalyst 32, and different mapping data are used for each region divided by the rotation speed NE and filling efficiency η. However, the variable relating to the flow rate of the fluid flowing into the upstream catalyst 32 is not limited to this. For example, the intake air amount Ga or the flow rate CF in the catalyst may be used.

In the process of FIG. 9, different mapping data was used for each region divided by the variable related to the flow rate of the fluid flowing into the upstream catalyst 32 and the catalyst temperature Tcat, but the processing is not limited to this. For example, regardless of the catalyst temperature Tcat, different mapping data may be used for each region divided by the variable related to the flow rate of the fluid flowing into the upstream catalyst 32. Further, for example, different mapping data may be used for each region divided by the catalyst temperature Tcat regardless of the variable related to the flow rate of the fluid flowing into the upstream catalyst 32.

In the process of FIG. 10, if denied in S72, different mapping data may be used for each region divided by the variable related to the flow rate of the fluid flowing into the upstream catalyst 32. Further, for example, when denied in S72, different mapping data may be used for each region divided by the catalyst temperature Tcat. Further, for example, when denied in S72, different mapping data may be used for each region divided by the variable regarding the flow rate of the fluid flowing into the upstream catalyst 32 and the catalyst temperature Tcat.

The input of the mapping data when a plurality of types of mapping data are provided is not limited to the one illustrated in the above embodiment. For example, when different mapping data is used for each region divided by the catalyst temperature Tcat regardless of the variable related to the flow rate of the fluid flowing into the upstream catalyst 32, the fluid flowing into the upstream catalyst 32 is input to the mapping. You may include variables related to the flow rate of. Further, for example, when different mapping data is used for each region divided by a variable related to the flow rate of the fluid flowing into the upstream catalyst 32 regardless of the catalyst temperature Tcat, the catalyst temperature Tcat is included in the mapping input. May be good. However, it is not essential that the variable used for dividing the region is not used as the input of the map. For example, the variable related to the flow rate of the fluid flowing into the upstream catalyst 32 and the region divided by the catalyst temperature Tcat are separately separated. When using the mapping data of, variables related to the flow rate of the fluid flowing into the upstream side catalyst 32 and the catalyst temperature Tcat may be included in the mapping input. Further, it is possible to include variables such as the mean value Qiave of the weight increase amount, which do not directly determine the division of the area, in the input of the map.

・ "Regarding certain conditions"
In the process of S80 of FIG. 11, the condition that the flow rate of the fluid flowing into the upstream catalyst 32 is within the predetermined range is defined as the condition that the logical product of the condition (a) and the condition (b) is true. However, it is not limited to this. For example, it may be a condition that the intake air amount Ga and the flow rate CF in the catalyst are within a predetermined range.

In the process of S80 of FIG. 11, the predetermined condition for sampling the variable used for calculating the deterioration degree variable Rd is the condition and the condition that the flow rate of the fluid flowing into the upstream catalyst 32 is within the predetermined range ( The condition is that the logical product with c) is true, but it is not limited to this. Regarding these two conditions, it may be a condition that only one of them is satisfied.

The processing of FIG. 11 and the input of mapping data in the modified example are not limited to those illustrated in the above embodiment. For example, when the variable used to calculate the deterioration degree variable Rd is allowed to be sampled when the catalyst temperature Tcat is within a predetermined range regardless of the variable related to the flow rate of the fluid flowing into the upstream catalyst 32, the mapping is input. Variables relating to the flow rate of the fluid flowing into the upstream catalyst 32 may be included. Further, for example, when sampling of the variable used for calculating the deterioration degree variable Rd is permitted when the flow rate of the fluid flowing into the upstream catalyst 32 is within a predetermined range regardless of the catalyst temperature Tcat, the catalyst is input to the mapping. Temperature Tcat may be included. However, it is not essential that the variables included in the sampling permission conditions of the variables used for calculating the deterioration degree variable Rd are not input to the mapping. For example, a variable related to the flow rate of the fluid flowing into the upstream catalyst 32 when the sampling of the variable used for calculating the deterioration degree variable Rd is permitted when the logical product of the above conditions (a) to (c) is true. And the catalyst temperature Tcat may be included in the mapping input. Further, it is also possible to include a variable such as Qiave, which is the average value of the increased amount, in the mapping input, which does not directly determine the sampling permission condition of the variable used for calculating the deterioration degree variable Rd.

In the processing of S82 of FIG. 12, the predetermined condition for sampling the variable used for calculating the deterioration degree variable Rd was set to the condition that the logical sum of the condition (d) and the condition (e) is true. , Not limited to this. For example, it may be a condition that the condition (d) is satisfied.

・ "About sampling period of time series data"
In the above embodiment, time series data to be input to the map is sampled when the target value Af * is set as usual, but the present invention is not limited to this. For example, the target value Af * may be set for calculating the deterioration degree variable Rd. Even in this case, by using the time-series data exemplified in the above-described embodiment or the like, the target value Af * is set to the component of the fluid flowing into the catalyst with respect to the component suitable for purification of the catalyst as compared with the conventional method. It is possible to set the deviation amount to be small, or to shorten the period during which the deviation amount is large.

・ "Corrective action"
The notification process is not limited to operating a device that outputs visual information such as the warning light 99, and may be a process that operates a device that outputs audio information, for example.

The coping process is not limited to all the processes of S34, S36, and S38, and for those three processes, only one of them may be performed, or for example, only one of the two processes is performed. You may. Further, only the process of S18 may be executed without executing the process of FIG.

Further, for example, when controlling the temperature rise of the upstream catalyst 32 such as sulfur poisoning regeneration treatment, the operation amount of the temperature rise control may be changed according to the degree of deterioration of the upstream catalyst 32. In that case, when the operation amount is the same when the degree of deterioration is large and when the degree of deterioration is small, the rate of temperature rise is lower when the degree of deterioration is large, so basically the rate of temperature rise is increased. It is desirable to change the operation amount so as to.

・ "About machine learning algorithms"
The machine learning algorithm is not limited to the one using a neural network. For example, a regression equation may be used. This corresponds to the neural network having no intermediate layer.

・ "Generation of mapping data"
In the above embodiment, the data when the internal combustion engine 10 is operated with the dynamometer 100 connected to the crankshaft 26 is used as training data, but the data is not limited to this. For example, data when the internal combustion engine 10 is driven while mounted on the vehicle VC may be used as training data.

・ "About data analysis equipment"
At the center 120, instead of the processes of S12d and S14d, a process of calculating the maximum value Cmax may be executed as in S12a and S14a, and the maximum value Cmax may be transmitted to the vehicle VC side.

At the center 120, the processes of S16 and S18 may be executed, and as the process of S18, a process of notifying that there is an abnormality in the user's mobile terminal may be executed.
The processing of S96, S12d, S14d, S98 of FIG. 14B may be executed by, for example, a mobile terminal owned by the user.

・ "About the execution device"
The execution device is not limited to the one provided with the CPU 72 (122) and the ROM 74 (124) to execute software processing. For example, a dedicated hardware circuit (for example, ASIC or the like) for hardware processing at least a part of the software processed in the above embodiment may be provided. That is, the executing device may have any of the following configurations (a) to (c). (A) A processing device that executes all of the above processing according to a program and a program storage device such as a ROM that stores the program are provided. (B) A processing device and a program storage device that execute a part of the above processing according to a program, and a dedicated hardware circuit that executes the remaining processing are provided. (C) A dedicated hardware circuit for executing all of the above processes is provided. Here, there may be a plurality of software execution devices including a processing device and a program storage device, and a plurality of dedicated hardware circuits.

・ "About storage device"
In the above embodiment, the storage device that stores the mapping data 76a and 126a and the storage device (ROM74, 124) that stores the deterioration detection program 74a and the deterioration detection main program 124a are different storage devices. Not limited to.

・ "How to provide status information"
In the processing of FIG. 14, the processing of S12d and S14d is performed by the center 120, but the processing is not limited to this, and the control device 70 may perform the processing. In that case, the control device 70 may output the deterioration degree variable Rd together with the vehicle ID to the center 120, and the center 120 may execute the processing after S100. However, in that case, it is not essential that the control device 70 outputs the deterioration degree variable Rd to the center 120 together with the vehicle ID each time the deterioration degree variable Rd is calculated. For example, the deterioration degree variable Rd may be registered in the center 120 at the stage when the vehicle ID is purchased as a used car by a used car dealer.

・ "About internal combustion engine"
The internal combustion engine is not limited to the one provided with both the port injection valve 16 and the in-cylinder injection valve 22, and may be provided with only one of the two types of fuel injection valves.

The internal combustion engine is not limited to the spark ignition type internal combustion engine, and may be, for example, a compression ignition type internal combustion engine that uses light oil or the like as fuel.
·"others"
The vehicle is not limited to the series / parallel hybrid vehicle, and may be, for example, a series hybrid vehicle or a parallel hybrid vehicle. Further, the vehicle is not limited to the hybrid vehicle, and the vehicle may be a vehicle in which the device for generating the propulsive force of the vehicle is only the internal combustion engine.

The catalyst is not limited to the three-way catalyst, and may be, for example, one in which the three-way catalyst is supported on a filter that collects particulate matter.

10 ... Internal engine, 12 ... Intake passage, 14 ... Throttle valve, 16 ... Port injection valve, 18 ... Intake valve, 20 ... Combustion chamber, 22 ... In-cylinder injection valve, 24 ... Ignition device, 26 ... Crank shaft, 28 ... Exhaust valve, 30 ... Exhaust passage, 32 ... Upstream side catalyst, 34 ... Downstream side catalyst, 36 ... EGR passage, 38 ... EGR valve, 40 ... Intake side valve timing variable device, 42 ... Intake side cam shaft, 44 ... Exhaust side Valve timing variable device, 46 ... Exhaust side cam shaft, 50 ... Planetary gear mechanism, 52, 54 ... Motor generator, 56 ... Drive wheels, 58, 60 ... Inverter, 62 ... Battery, 70 ... Control device, 72 ... CPU, 74 ... ROM, 74a ... Deterioration detection program, 74c ... Deterioration detection subprogram, 76 ... Storage device, 76a ... Mapping data, 77 ... Peripheral circuit, 78 ... Local network, 79 ... Communication device, 80 ... Airflow meter, 82 ... Upstream side Air fuel ratio sensor, 84 ... downstream air fuel ratio sensor, 86 ... crank angle sensor, 88 ... accelerator sensor, 90 ... vehicle speed sensor, 92 ... atmospheric pressure sensor, 96 ... current sensor, 98 ... voltage sensor, 99 ... warning light, 100 ... Dynamometer, 102 ... Sensor group, 104 ... Compatible device, 110 ... Network, 120 ... Center, 122 ... CPU, 124 ... ROM, 124a ... Deterioration detection main program, 126 ... Storage device, 126a ... Mapping data, 126b ... State Information data, 127 ... peripheral circuits, 128 ... local networks, 129 ... communication devices, 130 ... terminals.

Claims (15)

It is applied to a catalyst deterioration detection device that detects deterioration of the catalyst provided in the exhaust passage of an internal combustion engine.
Equipped with a storage device and an execution device,
The storage device is a time-series data of an excess amount variable in a first predetermined period, which is a variable corresponding to an excess amount of an actual fuel amount with respect to an excess amount of fuel that reacts with oxygen contained in a fluid flowing into the catalyst in just proportion. And the time series data in the second predetermined period of the downstream detection variable, which is a variable corresponding to the detection value of the air-fuel ratio sensor on the downstream side of the catalyst, is input, and the deterioration degree variable, which is a variable related to the deterioration degree of the catalyst, is output. It stores mapping data, which is data that defines the mapping to be performed.
The execution device acquires the time-series data of the excess amount variable in the first predetermined period and the time-series data of the downstream detection variable in the second predetermined period, and the data acquired by the acquisition process. Determined when the degree of deterioration of the catalyst is equal to or higher than a predetermined value based on the calculation results of the deterioration degree variable calculation process for calculating the deterioration degree variable of the catalyst based on the output of the mapping as input and the calculation result of the deterioration degree variable calculation process. By operating the hardware of the above, a coping process for coping with the deterioration degree of the catalyst exceeding a predetermined level is executed.
The mapping data is a catalyst deterioration detection device including data learned by machine learning. The input of the map includes the temperature of the catalyst,
The acquisition process includes a process of acquiring the temperature of the catalyst.
The catalyst deterioration detection device according to claim 1, wherein the deterioration degree variable calculation process is a process of calculating a deterioration degree variable of the catalyst based on the output of the map in which the temperature of the catalyst is further included in the input to the map. The catalyst deterioration detecting apparatus according to claim 1 or 2, wherein the excess amount variable includes a variable corresponding to a value detected by an air-fuel ratio sensor on the upstream side of the catalyst. The storage device includes a plurality of types of mapping data.
The deterioration degree variable calculation process is any one of claims 1 to 3, which includes a selection process of selecting the mapping data to be used for calculating the deterioration degree variable of the catalyst from the plurality of types of mapping data. The catalyst deterioration detection device according to. The plurality of types of mapping data include data for each region classified by the flow rate of the fluid flowing into the catalyst.
The catalyst deterioration detecting apparatus according to claim 4, wherein the selection process includes a process of selecting the mapping data used for calculating a deterioration degree variable of the catalyst based on the flow rate. The plurality of types of the mapping data include data for each of a plurality of regions classified by the temperature of the catalyst.
The catalyst deterioration detecting apparatus according to claim 4, wherein the selection process includes a process of selecting the mapping data used for calculating the degree of deterioration of the catalyst based on the temperature of the catalyst. The plurality of types of mapping data include different data depending on whether or not the fuel cut process is executed.
The catalyst deterioration detecting apparatus according to claim 4, wherein the selection process includes a process of selecting the mapping data depending on whether or not it is an execution period of the fuel cut process. The acquisition process is a process of acquiring a variable to be an input of the map when a predetermined condition is satisfied.
The catalyst deterioration detecting apparatus according to any one of claims 1 to 4, wherein the predetermined condition includes a condition that the flow rate of the fluid flowing into the catalyst is within a predetermined range. The acquisition process is a process of acquiring a variable to be an input of the map when a predetermined condition is satisfied.
The catalyst deterioration detecting apparatus according to any one of claims 1 to 4, wherein the predetermined condition includes a condition that the temperature of the catalyst is within a predetermined range. The acquisition process is a process of acquiring a variable to be an input of the map in synchronization when a predetermined condition is satisfied.
The catalyst deterioration detecting apparatus according to any one of claims 1 to 4, wherein the predetermined condition is a condition that the amount of oxygen stored in the catalyst is the maximum value or the minimum value. The catalyst deterioration detecting apparatus according to any one of claims 1 to 10, wherein the coping process includes a limiting process for limiting the amount of unburned fuel flowing into the catalyst to a smaller side. The executing device and the storage device according to any one of claims 1 to 10 are provided.
The deterioration degree variable calculation process includes an oxygen storage amount calculation process for calculating a value corresponding to the maximum value of the oxygen storage amount of the catalyst using at least a part of the mapping data.
The execution device includes a first execution device and a second execution device.
The first execution device is mounted on the vehicle and is used as a calculation result of the acquisition process, the vehicle side transmission process of transmitting the data acquired by the acquisition process to the outside of the vehicle, and the oxygen storage amount calculation process. The vehicle-side reception process for receiving the signal based on the above and the countermeasure process are executed.
The second execution device is arranged outside the vehicle and receives data transmitted by the vehicle-side transmission process, an external reception process, an oxygen storage amount calculation process, and an oxygen storage amount calculation process. A catalyst deterioration detection system that executes an external transmission process for transmitting a signal based on the calculation result of the above to the vehicle. A data analysis device including the second execution device and the storage device according to claim 12. A control device for an internal combustion engine including the first execution device according to claim 12. It is a method of providing status information of a used car equipped with an internal combustion engine having a catalyst in the exhaust passage.
The acquisition process according to any one of claims 1 to 10 and the deterioration degree variable calculation process.
A storage process for storing the calculation result of the deterioration degree variable calculation process in the storage device together with the vehicle ID,
A method for providing state information of a used car, which causes a computer to execute an output process for outputting deterioration degree information of the catalyst corresponding to the vehicle ID in response to an access from the outside.