JP2021099049A - On-vehicle device and filter regeneration control method - Google Patents

Abstract

To optimize regeneration of a filter.SOLUTION: An on-vehicle device mounted on a vehicle equipped with an internal combustion engine includes an acquisition section, an estimation section, and a regeneration control section. The acquisition section acquires a state of the vehicle. The estimation section estimates duration time of fuel cut of the internal combustion engine on the basis of the state acquired by the acquisition section. The regeneration control section controls regeneration of a filter provided in an exhaust passage of the internal combustion engine on the basis of the duration time estimated by the estimation section.SELECTED DRAWING: Figure 2A

Description

The disclosed embodiments relate to in-vehicle devices and filter regeneration control methods.

In recent years, stricter emission regulations have been introduced for automobile exhaust gas, and the regulation value of the particle number (PN: Particulate Number) of emitted fine particles has been strengthened.

Therefore, in order to reduce the number of fine particulate matter (PM: Particulate Matter) emitted by each automobile manufacturer, a gasoline particulate filter (GPF:) having a function of collecting particulate matter emitted from an automobile engine is used. Gasoline Particulate Filter) is being considered for mounting, for example, in the subsequent stage of a three-way catalyst.

GPF needs to be regenerated regularly because the collection function deteriorates when fine particles are accumulated too much. A common regeneration method is to burn the accumulated fine particles by fuel-cutting the engine (hereinafter referred to as "F / C") and supplying oxygen when the GPF is at a high temperature to some extent. ..

However, if the GPF becomes too hot, the GPF may burn out. For such a situation, (1) a method of prohibiting F / C at the time of high deposition and high temperature from the estimated amount of fine particle deposition and estimated temperature of GPF, and (2) a temperature sensor is installed after the GPF to raise the temperature. A method of controlling the end timing of the F / C from the inclination of the F / C can be used (see, for example, Patent Document 1).

Japanese Unexamined Patent Publication No. 2008-057333

However, there is room for further improvement in the prior art in optimizing the regeneration of GPF. For example, in the method (1) above, due to insufficient estimation accuracy, reproduction may be insufficient, the collection function may be deteriorated, or failure or waste may occur. In addition, in the method (2) above, there is a risk of failure or waste due to variations in the temperature sensor and response delay.

It should be noted that such a problem is not limited to GPF, but is a problem common to all filters having a function of collecting exhaust fine particles discharged from an internal combustion engine, such as a diesel particulate filter (DPF).

One aspect of the embodiment is made in view of the above, and an object of the present invention is to provide an in-vehicle device and a filter regeneration control method capable of optimizing the regeneration of the filter.

The in-vehicle device according to one aspect of the embodiment is an in-vehicle device mounted on a vehicle having an internal combustion engine, and includes an acquisition unit, an estimation unit, and a reproduction control unit. The acquisition unit acquires the status of the vehicle. The estimation unit estimates the duration of fuel cut of the internal combustion engine based on the situation acquired by the acquisition unit. The regeneration control unit controls the regeneration of the filter provided in the exhaust path of the internal combustion engine based on the duration estimated by the estimation unit.

According to one aspect of the embodiment, the regeneration of the filter can be optimized.

FIG. 1A is a schematic explanatory view (No. 1) of the GPF regeneration control method according to the embodiment. FIG. 1B is a schematic explanatory view (No. 2) of the GPF regeneration control method according to the embodiment. FIG. 1C is a schematic explanatory view (No. 3) of the GPF regeneration control method according to the embodiment. FIG. 2A is a block diagram showing a configuration example of the GPF regeneration control system according to the embodiment. FIG. 2B is a block diagram showing a configuration example of the estimation unit according to the embodiment. FIG. 3 is an explanatory diagram of the estimation model according to the embodiment. FIG. 4 is an explanatory diagram of map information according to the embodiment. FIG. 5 is an operation explanatory view of the GPF reproduction control system according to the embodiment. FIG. 6 is a flowchart showing a processing procedure executed by the in-vehicle device according to the embodiment.

Hereinafter, embodiments of the in-vehicle device and the filter regeneration control method disclosed in the present application will be described in detail with reference to the accompanying drawings. The present invention is not limited to the embodiments shown below. Further, in the following, the case where the filter is GPF will be described as an example.

First, the outline of the GPF regeneration control method according to the embodiment will be described with reference to FIGS. 1A to 1C. 1A to 1C are schematic explanatory views (No. 1) to (No. 3) of the GPF reproduction control method according to the embodiment.

As shown in FIG. 1A, the GPF 5 is provided on the exhaust path 3 of the engine 2, for example, after the three-way catalyst 4. Since the collection function of GPF5 deteriorates when fine particles are accumulated too much, it is necessary to burn the accumulated fine particles by periodically performing F / C to supply oxygen. However, if the GPF becomes too hot, the GPF may burn out.

Here, (1) a method of prohibiting F / C at the time of high deposition and high temperature from the estimated amount of fine particle deposition and estimated temperature of GPF5, and (2) a temperature sensor is mounted in the subsequent stage of GPF5, and F from the inclination of temperature rise. It is conceivable to use a method of controlling the end timing of / C.

However, in the method (1) above, the estimation accuracy is insufficient, and in the method (2) above, the reproduction is insufficient due to the variation of the temperature sensor and the response delay, respectively, and the collection function deteriorates or malfunctions. There was a risk of waste.

Therefore, in the GPF control method according to the embodiment, the vehicle condition is acquired, the F / C duration is estimated based on the acquired condition, and the throttle opening is controlled based on the estimated F / C duration. It was decided to.

Specifically, as shown in FIG. 1B, in the GPF regeneration control system 1 to which the GPF regeneration control method according to the embodiment is applied, the in-vehicle device 10 acquires the vehicle status (step S1).

The in-vehicle device 10 is an ECU (Electronic Control) having, for example, a camera, an acceleration sensor, a steering angle sensor, a gyro sensor, a temperature sensor, a GPS (Global Positioning System) sensor, various sensors such as a millimeter wave radar, a storage device, and a microcomputer. Unit), car navigation device, etc.

The situation acquired by the in-vehicle device 10 includes both a static situation and a dynamic situation inside and outside the vehicle, and for example, as shown in FIG. 1B, the vehicle speed, the slope, and the distance between the vehicle and the vehicle in front. It includes various situations such as the driver's pedal work habit. It should be noted that these may be rephrased as various characteristics related to the vehicle.

Then, the in-vehicle device 10 estimates the F / C duration from the start of the F / C based on these various acquired situations (step S2). In such estimation, the in-vehicle device 10 utilizes an estimation model generated in advance by using a machine learning algorithm such as deep learning. Such an estimation model will be described later with reference to FIG.

Then, the in-vehicle device 10 controls the throttle opening degree during the F / C based on the estimated F / C duration (step S3).

More specifically, as shown in FIG. 1C, for example, the in-vehicle device 10 repeats the estimation of the F / C duration every moment at the start of the F / C, and fine-tunes the estimated F / C duration with the passage of time. At the same time, the throttle opening is controlled so that the maximum oxygen can be supplied within the range where the GPF 5 reaches the upper limit temperature and does not burn out. As a result, the in-vehicle device 10 burns the fine particles deposited on the GPF 5 in the F / C as much as possible.

The control value of the throttle opening degree is performed, for example, based on the map information in which the temporal transition of the GPF temperature for each throttle opening degree is set in advance. Such map information will be described later with reference to FIG.

As described above, in the GPF regeneration control method according to the embodiment, the in-vehicle device 10 acquires the vehicle condition in the GPF control method according to the embodiment, and estimates the F / C duration based on the acquired condition. , It was decided to control the throttle opening based on the estimated F / C duration.

Therefore, according to the GPF regeneration control method according to the embodiment, fine particles deposited on the GPF 5 can be formed during the F / C according to the F / C duration estimated from various situations acquired from moment to moment. It is possible to burn as much as possible.

That is, according to the GPF regeneration control method according to the embodiment, the regeneration of GPF can be optimized.

Hereinafter, a configuration example of the GPF regeneration control system 1 to which the GPF regeneration control method according to the above-described embodiment is applied will be described more specifically.

FIG. 2A is a block diagram showing a configuration example of the GPF regeneration control system 1 according to the embodiment. Further, FIG. 2B is a block diagram showing a configuration example of the estimation unit 12b according to the embodiment. Note that, in FIGS. 2A and 2B, only the components necessary for explaining the features of the present embodiment are shown, and the description of general components is omitted.

In other words, each component shown in FIGS. 2A and 2B is functionally conceptual and does not necessarily have to be physically configured as shown. For example, the specific form of distribution / integration of each block is not limited to the one shown in the figure, and all or part of it may be functionally or physically distributed in arbitrary units according to various loads and usage conditions. It can be integrated and configured.

Further, in the description using FIGS. 2A and 2B, the description of the components already described may be simplified or omitted.

As shown in FIG. 2A, the GPF regeneration control system 1 according to the embodiment includes an in-vehicle device 10, various sensors 20, and an electronically controlled throttle 30. As described above, the in-vehicle device 10 is configured as, for example, a car navigation device, an ECU, or the like.

The various sensors 20 correspond to various in-vehicle sensors such as the above-mentioned camera, acceleration sensor, steering angle sensor, gyro sensor, temperature sensor, GPS sensor, and millimeter-wave radar, and are communicably connected to the in-vehicle device 10.

The electronically controlled throttle 30 is a so-called throttle-by-wire including a throttle which is a valve for adjusting the inflow amount of intake air to the engine 2 and adjusting the output of the engine 2, and is a throttle calculated by the regeneration control unit 12c. The throttle opening is controlled based on the control value of the opening.

The various sensors 20 and the electronically controlled throttle 30 are connected to the in-vehicle device 10 via, for example, a CAN (Controller Area Network) bus. It may be connected so that communication can be performed by a protocol other than CAN. Moreover, it may be in a wireless form.

The in-vehicle device 10 includes a storage unit 11 and a control unit 12. The storage unit 11 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory (Flash Memory), or a storage device such as a hard disk or an optical disk. The estimation model 11b and the map information 11c are stored.

The characteristic information 11a is information on various characteristics related to the vehicle, and mainly includes static information among such characteristics. For example, the characteristic information 11a includes information on user characteristics, and the information on such user characteristics includes various parameters indicating the gender and age of the driver of the vehicle, driving history, driving habits, and the like.

Further, the characteristic information 11a includes, for example, information on vehicle characteristics, and the information on such vehicle characteristics includes a vehicle type, a vehicle body shape, and the like. Further, the characteristic information 11a includes, for example, information on the route characteristic, and the information on the route characteristic includes map information such as a high-precision map and a dynamic map, route information set by the user, and the like. The characteristic information 11a may be appropriately acquired from a server device such as a data center and updated.

The estimation model 11b inputs the characteristic information 11a and various static and dynamic situations acquired from the various sensors 20 by the acquisition unit 12a, which will be described later, to input the GPF temperature at the start of the F / C and the continuation of the F / C. It is a prediction model that estimates and outputs the time. As described above, the estimation model 11b is generated in advance using a machine learning algorithm such as deep learning and stored in the storage unit 11.

Here, the estimation model 11b will be described more specifically with reference to FIG. FIG. 3 is an explanatory diagram of the estimation model 11b according to the embodiment.

As shown in FIG. 3, the estimation model 11b is generated as a prediction model that estimates and outputs the GPF temperature at the start of F / C and the F / C duration by inputting various situations related to the vehicle. .. As shown in FIG. 3 as an autoencoder, the estimation model 11b uses, for example, deep learning as a machine learning algorithm when generating the estimation model 11b. Since deep learning is known, detailed description here will be omitted.

For example, the estimation model 11b includes a temperature estimation model 11ba and a duration estimation model 11bb. At the time of learning, the temperature estimation model 11ba executes machine learning based on each data indicating various operating conditions collected as learning data, and when these data are input, the GPF temperature at the start of F / C Estimated value (hereinafter, may be referred to as "estimated GPF temperature") is generated to function as an output function.

Further, the duration estimation model 11bb executes machine learning based on each data indicating various operation statuses, each data indicating a route status, and each data indicating a user status collected as learning data at the time of learning. However, when each of these data is input, the F / C duration (hereinafter, may be referred to as "estimated F / C duration") is generated so as to function as an output function.

As shown in FIG. 3, for example, as shown in FIG. 3, each data showing the operating state includes information on the temperature sensor value provided upstream of the GPF 5, the vehicle speed, the inter-vehicle distance, and the like as various parameters. Each data indicating the route status includes, for example, information on a gradient, a curve, a signal, and the like as various parameters. Each data related to the user situation includes, for example, the habit of pedal work, or the above-mentioned information on gender, age, driving history, etc. as various parameters.

Each of the data indicating the operation status, the route status, the user status, and the like can be rephrased as each data indicating the status of the vehicle, and includes both static information and dynamic information.

The estimation model 11b is generated in a server device such as a data center at the time of development of the in-vehicle device 10, for example, and is pre-installed and used before the in-vehicle device 10 is shipped. In addition, during the operation of the in-vehicle device 10, the in-vehicle device 10 itself may perform additional learning based on various data acquired moment by moment, and the estimation model 11b may be updated as appropriate.

In addition, various data acquired by the in-vehicle device 10 in operation are collected at any time on the server device side, additional learning is performed on the data center side based on the collected data, and the updated estimation model 11b is obtained by the in-vehicle device 10. It may be delivered to as appropriate.

Returning to the description of FIG. 2A. The map information 11c is, for example, map information in which the temporal transition of the GPF temperature for each throttle opening is preset. Here, the map information 11c will be described more specifically with reference to FIG. FIG. 4 is an explanatory diagram of map information 11c according to the embodiment.

As shown in FIG. 4, the map information 11c is map information in which the temporal transition of the GPF temperature for each throttle opening is set. The map information 11c is generated in advance based on, for example, verification results by simulations, experiments, etc. at the time of development of the in-vehicle device 10. As with the estimation model 11b, it may be generated by executing machine learning.

FIG. 4 shows an example in which the throttle opening is of three types, "large", "medium", and "small", but this is just a rough example, and the throttle opening is set with a finer resolution. You may. In the case of the example shown in FIG. 4, from the viewpoint of the estimated F / C duration, it is the throttle opening "medium" that can supply oxygen to the GPF 5 to the maximum without reaching the upper limit temperature. In this case, the curve with the throttle opening "medium" is adopted for control.

Returning to the description of FIG. 2A. The control unit 12 is a controller, and for example, various programs stored in a storage device inside the in-vehicle device 10 by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like use the RAM as a work area. It is realized by being executed. Further, the control unit 12 can be realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

The control unit 12 includes an acquisition unit 12a, an estimation unit 12b, and a reproduction control unit 12c, and realizes or executes an information processing function or operation described below.

The acquisition unit 12a receives output data from various sensors 20 and acquires dynamic conditions inside and outside the vehicle that change from moment to moment based on the output data.

For example, the acquisition unit 12a acquires image data inside and outside the vehicle based on the camera. Further, for example, the acquisition unit 12a acquires the current position of the vehicle based on the GPS sensor. Further, for example, the acquisition unit 12a acquires the operation status, route status, and user status of the vehicle based on the acceleration sensor, steering angle sensor, gyro sensor, temperature sensor, millimeter wave radar, and the like. Further, the acquisition unit 12a mainly acquires a static situation based on the characteristic information 11a.

The estimation unit 12b estimates the GPF temperature at the start of the F / C and the F / C duration by using the estimation model 11b based on the situation acquired by the acquisition unit 12a.

Specifically, as shown in FIG. 2B, the estimation unit 12b includes a temperature estimation unit 12ba and a duration estimation unit 12bb. At the start of the F / C, the temperature estimation unit 12ba obtains an output of the estimated GPF temperature from the temperature estimation model 11ba by inputting, for example, each data indicating the operating state of the vehicle into the temperature estimation model 11ba (see FIG. 3).

Further, the duration estimation unit 12bb estimates the duration by inputting data indicating, for example, the operating status, the route status, and the user status of the vehicle into the duration estimation model 11bb (see FIG. 3) during the F / C. Obtain the estimated F / C duration output from model 11bb.

Returning to the description of FIG. 2A. Further, the estimation unit 12b notifies the reproduction control unit 12c of the estimated GPF temperature and the estimated F / C duration. Further, the estimation unit 12b repeatedly estimates the F / C duration based on the situation regarding the vehicle acquired by the acquisition unit 12a at any time during the F / C, and notifies the reproduction control unit 12c.

The reproduction control unit 12c calculates a control value of the throttle opening degree based on the estimated GPF temperature, the estimated F / C duration, and the map information 11c estimated by the estimation unit 12b, and outputs the control value to the electronically controlled throttle 30.

Here, a specific operation example of the GPF reproduction control system 1 will be described with reference to FIG. FIG. 5 is an operation explanatory view of the GPF reproduction control system 1 according to the embodiment.

When the F / C is started, as shown in FIG. 5, the temperature estimation unit 12ba estimates the GPF temperature at the start of the F / C based on the GPF upstream temperature sensor and the like, and notifies the reproduction control unit 12c.

Further, the duration estimation unit 12bb determines, for example, the current vehicle speed based on the vehicle speed sensor, the inter-vehicle distance to the vehicle in front based on the millimeter-wave radar, and the status of the gradient, curve, signal, etc. based on the high-precision map or dynamic map. Also, get the habit of the user's pedal work. Then, the duration estimation unit 12bb estimates the F / C duration based on the acquired information and notifies the reproduction control unit 12c.

Then, the reproduction control unit 12c is based on a predetermined GPF upper limit temperature, an estimated GPF temperature at the start of F / C, an estimated F / C duration, an engine speed based on various sensors 20, an estimated GPF accumulation amount, and the like. The control value of the throttle opening is calculated, and the throttle opening is controlled based on this. The estimated GPF deposit amount can be calculated, for example, by monitoring the combustion state of the engine 2.

Next, the processing procedure executed by the in-vehicle device 10 according to the embodiment will be described with reference to FIG. FIG. 6 is a flowchart showing a processing procedure executed by the in-vehicle device 10 according to the embodiment.

As shown in FIG. 6, first, the acquisition unit 12a acquires the vehicle status from the various sensors 20 and the characteristic information 11a (step S101).

Then, it is determined whether or not the trip is completed based on the acquired situation (step S102). Here, when the trip ends (step S102, Yes), the process ends. If it is not the end of the trip (steps S102, No), it is determined whether or not the F / C has been started (step S103).

Here, when the F / C is started (steps S103, Yes), the F / C flag is turned ON (S104). Then, the estimation unit 12b estimates the GPF temperature at the start of F / C based on the acquired situation (step S105). If the F / C is not started (steps S103, No), the process proceeds to step S106.

Subsequently, it is determined whether or not the F / C flag is ON (step S106). Here, when the F / C flag is ON (step S106, Yes), the estimation unit 12b estimates the F / C duration based on the acquired situation (step S107).

Then, the reproduction control unit 12c calculates the throttle opening degree based on the estimated GPF temperature and the estimated F / C duration estimated by the estimation unit 12b (step S108), and controls the throttle opening degree (step S109). If the F / C flag is not ON (steps S106, No), the process proceeds to step S110.

Subsequently, it is determined whether or not the F / C has been completed (step S110). Here, when the F / C is completed (step S110, Yes), the F / C flag is turned off (step S111). Then, the process from step S101 is repeated. Even if the F / C is not completed (steps S110, No), the processing from step S101 is repeated.

As described above, the in-vehicle device 10 according to the embodiment is an in-vehicle device mounted on a vehicle having an engine 2 (corresponding to an example of an “internal combustion engine”), and includes an acquisition unit 12a, an estimation unit 12b, and the like. It includes a reproduction control unit 12c. The acquisition unit 12a acquires the status of the vehicle. The estimation unit 12b estimates the duration of the F / C (fuel cut) of the engine 2 based on the situation acquired by the acquisition unit 12a. The regeneration control unit 12c controls the regeneration of the GPF 5 provided in the exhaust path 3 of the engine 2 based on the duration estimated by the estimation unit 12b.

Therefore, according to the in-vehicle device 10 according to the embodiment, the reproduction of the GPF can be optimized.

Further, the regeneration control unit 12c regenerates the GPF 5 by adjusting the amount of oxygen supplied to the GPF 5 during the F / C by controlling the throttle opening degree.

Therefore, according to the in-vehicle device 10 according to the embodiment, the GPF 5 can be regenerated by burning the fine particles deposited on the GPF 5.

Further, the estimation unit 12b estimates the temperature of the GPF 5 at the start of the F / C based on the situation acquired by the acquisition unit 12a, and the reproduction control unit 12c estimates the throttle opening degree based on the temperature of the GPF 5 and the duration. Is calculated.

Therefore, according to the in-vehicle device 10 according to the embodiment, it is possible to optimally control the regeneration of the GPF 5 according to the temperature of the GPF 5 and the duration.

Further, the estimation unit 12b repeatedly estimates the duration during the F / C, and causes the reproduction control unit 12c to update the throttle opening degree.

Therefore, according to the in-vehicle device 10 according to the embodiment, the duration and the throttle opening can be appropriately updated according to the situation that changes from moment to moment, so that the reproduction control unit 12c can reproduce the optimum GPF 5 according to the update. Control can be performed.

Further, the reproduction control unit 12c supplies the most oxygen within the range in which the GPF 5 does not reach the upper limit temperature during the above duration, based on the map information 11c in which the temporal transition of the temperature of the GPF 5 is associated with each throttle opening. Select the throttle opening that can be done.

Therefore, according to the in-vehicle device 10 according to the embodiment, the fine particles deposited on the GPF 5 can be burned with the maximum efficiency during the above duration. Further, since the GPF 5 does not reach the upper limit temperature, it is possible to prevent the GPF 5 from burning.

In addition, the estimation unit 12b estimates the temperature and the duration of the GPF 5 using the estimation model 11b generated by executing machine learning using each element indicating the vehicle condition.

Therefore, according to the in-vehicle device 10 according to the embodiment, by using the estimation model 11b, it is possible to accurately estimate the temperature and the duration of the GPF 5 according to the situation of the vehicle.

In addition, each element indicating the situation of the vehicle includes parameters relating to at least one of the vehicle speed, the distance from the vehicle in front, the slope, the curve, the signal, and the habit of pedal work.

Therefore, according to the in-vehicle device 10 according to the embodiment, it is possible to estimate the temperature and the duration of the GPF 5 with high accuracy based on at least one of the above parameters.

In addition, the acquisition unit 12a acquires the vehicle status using a millimeter-wave radar, a high-precision map, or a dynamic map.

Therefore, according to the in-vehicle device 10 according to the embodiment, it is possible to estimate the temperature and the duration of the GPF 5 at a higher level based on the inter-vehicle distance to the vehicle in front, highly accurate map information, and the like.

In the above-described embodiment, deep learning is used as the machine learning algorithm, but the algorithm used is not limited. Therefore, machine learning may be executed by a regression analysis method such as support vector regression using a pattern classifier such as SVM (Support Vector Machine) to generate an estimation model 11b. Further, here, the pattern classifier is not limited to the SVM, and may be, for example, AdaBoost. Moreover, you may use a random forest or the like.

Further, in the above-described embodiment, the case where the filter is GPF5 is taken as an example, but the filter is not limited to GPF5, and any filter having a function of collecting particulates discharged from an internal combustion engine, such as DPF, is used. Good.

Further effects and variations can be easily derived by those skilled in the art. For this reason, the broader aspects of the invention are not limited to the particular details and representative embodiments expressed and described as described above. Therefore, various modifications can be made without departing from the spirit or scope of the general concept of the invention as defined by the appended claims and their equivalents.

1 GPF regeneration control system 2 Engine 3 Exhaust path 5 GPF
10 In-vehicle device 11 Storage unit 11a Characteristic information 11b Estimated model 11c Map information 12 Control unit 12a Acquisition unit 12b Estimating unit 12c Reproduction control unit 20 Various sensors 30 Electronically controlled throttle

Claims (9)

An in-vehicle device mounted on a vehicle having an internal combustion engine.
The acquisition unit that acquires the status of the vehicle and
An estimation unit that estimates the duration of fuel cut of the internal combustion engine based on the situation acquired by the acquisition unit, and an estimation unit.
An in-vehicle device including a regeneration control unit that controls regeneration of a filter provided in an exhaust path of the internal combustion engine based on the duration estimated by the estimation unit. The reproduction control unit
The vehicle-mounted device according to claim 1, wherein the filter is regenerated by adjusting the amount of oxygen supplied to the filter during fuel cutting by controlling the throttle opening degree. The estimation unit
The temperature of the filter at the start of fuel cut is estimated based on the situation acquired by the acquisition unit.
The reproduction control unit
The vehicle-mounted device according to claim 1 or 2, wherein the throttle opening degree is calculated based on the temperature of the filter and the duration of the filter. The estimation unit
The vehicle-mounted device according to claim 1, 2 or 3, wherein the duration is repeatedly estimated during the fuel cut, and the reproduction control unit updates the throttle opening degree. The reproduction control unit
Based on the map information associated with the temporal transition of the temperature of the filter for each throttle opening, the throttle opening that can supply the most oxygen within the range in which the filter does not reach the upper limit temperature during the duration is selected. The vehicle-mounted device according to any one of claims 1 to 4, wherein the in-vehicle device is characterized by the above. The estimation unit
The third, fourth or fifth aspect of the present invention, wherein the temperature and the duration of the filter are estimated using an estimation model generated by performing machine learning using each element indicating the situation of the vehicle. The in-vehicle device described. Each element indicating the condition of the vehicle is
The vehicle-mounted device according to claim 6, further comprising parameters relating to at least one of a vehicle speed, a distance from a vehicle in front, a gradient, a curve, a signal, and a habit of pedal work. The acquisition unit
The vehicle-mounted device according to any one of claims 1 to 7, wherein the condition of the vehicle is acquired by using a millimeter-wave radar, a high-precision map, or a dynamic map. It is a filter regeneration control method using an in-vehicle device mounted on a vehicle having an internal combustion engine.
The acquisition process for acquiring the status of the vehicle and
An estimation process for estimating the duration of fuel cut of the internal combustion engine based on the situation acquired in the acquisition process, and an estimation process.
A filter regeneration control method including a regeneration control step of controlling regeneration of a filter provided in an exhaust path of an internal combustion engine based on the duration estimated in the estimation step.

Images