阅读说明：本技术 用于混合动力车辆的控制系统和控制方法 (Control system and control method for hybrid vehicle ) 是由 横山大树 岛田真典 于 2021-04-28 设计创作，主要内容包括：本发明涉及用于混合动力车辆的控制系统和控制方法。一种用于混合动力车辆的控制系统,该混合动力车辆包括内燃机和电动机并且其驱动模式可在电动车辆模式与混合动力车辆模式之间切换,该控制系统包括：车载学习单元,该车载学习单元被安装在混合动力车辆上并被配置成执行学习动作；位置确定单元,该位置确定单元被配置成确定混合动力车辆是否位于内燃机的运转应该受限制的低排放区域中；以及学习控制单元,该学习控制单元被配置成：当确定混合动力车辆位于低排放区域中时,至少部分地停止车载学习单元的学习动作。(The invention relates to a control system and a control method for a hybrid vehicle. A control system for a hybrid vehicle that includes an internal combustion engine and an electric motor and whose drive mode is switchable between an electric vehicle mode and a hybrid vehicle mode, comprising: an in-vehicle learning unit mounted on the hybrid vehicle and configured to perform a learning action; a position determination unit configured to determine whether the hybrid vehicle is located in a low emission region in which operation of the internal combustion engine should be restricted; and a learning control unit configured to: when it is determined that the hybrid vehicle is located in the low emission region, the learning action of the in-vehicle learning unit is at least partially stopped.)

1. A control system for a hybrid vehicle, characterized by comprising:

an on-board learning unit mounted on the hybrid vehicle and configured to perform a learning action;

a position determination unit configured to determine whether the hybrid vehicle is located in a low emission region in which operation of an internal combustion engine should be restricted; and

a learning control unit configured to: at least partially stopping the learning action of the on-board learning unit when it is determined that the hybrid vehicle is located in the low emission region, wherein:

the hybrid vehicle includes the internal combustion engine and an electric motor; and is

The drive mode of the hybrid vehicle is switchable between an electric vehicle mode and a hybrid vehicle mode, the electric vehicle mode being a mode in which the internal combustion engine is stopped and the electric motor is operated, and the hybrid vehicle mode being a mode in which the internal combustion engine and the electric motor are operated.

2. The control system according to claim 1, wherein the learning control unit is configured to: completely stopping the learning action of the on-board learning unit when it is determined that the hybrid vehicle is located in the low emission region.

3. The control system according to claim 1 or 2, characterized in that, in a case where it is determined that the hybrid vehicle is located in the low emission region, the learning control unit is configured to: when it is determined that the state of charge of the battery of the hybrid vehicle is below a predetermined threshold, at least partially stopping the learning action of the on-board learning unit, and configured to: when it is determined that the state of charge of the battery is equal to or higher than the threshold value, the learning action of the in-vehicle learning unit is not stopped.

4. The control system according to claim 3, wherein the learning control unit is configured to: when it is determined that the hybrid vehicle is located in the low emission region and it is determined that the state of charge of the battery is lower than the threshold value, the proportion of the learning action of the on-board learning unit that is stopped is increased as the state of charge of the battery decreases.

5. The control system according to any one of claims 1 to 4, characterized by further comprising a server learning unit that is mounted on a server located outside the hybrid vehicle and is configured to perform a learning action, wherein the server learning unit is configured to, when the learning action of the on-vehicle learning unit is stopped, perform the learning action to be performed by the on-vehicle learning unit using data transmitted from the hybrid vehicle to the server and transmit a learning result of the server learning unit to the hybrid vehicle.

6. The control system according to claim 5, wherein the learning control unit is configured to: transmitting the data from the hybrid vehicle to the server when it is determined that the hybrid vehicle is located outside the low emission region.

7. The control system according to claim 6, characterized in that, in a case where it is determined that the hybrid vehicle is located outside the low emission region, the learning control unit is configured to: when it is determined that the hybrid vehicle is located in a non-adjacent area that is not adjacent to the low-emission area, not transmitting the data from the hybrid vehicle to the server, and configured to: transmitting the data from the hybrid vehicle to the server when it is determined that the hybrid vehicle is located in an adjacent area adjacent to the low emission area.

8. The control system according to claim 6, wherein the learning control unit is configured to: repeatedly transmitting the data from the hybrid vehicle to the server when it is determined that the hybrid vehicle is located outside the low emission region.

9. A control method for a hybrid vehicle, the control method characterized by comprising:

performing a learning action by an on-board learning unit mounted on the hybrid vehicle;

determining whether the hybrid vehicle is located in a low emission region in which operation of an internal combustion engine should be restricted; and

at least partially stopping a learning action of the on-board learning unit when it is determined that the hybrid vehicle is located in the low emission region, wherein the hybrid vehicle includes the internal combustion engine and an electric motor, and a driving mode of the hybrid vehicle is switchable between an electric vehicle mode and a hybrid vehicle mode, the electric vehicle mode is a mode in which the internal combustion engine is stopped and the electric motor is operated, and the hybrid vehicle mode is a mode in which the internal combustion engine and the electric motor are operated.

Technical Field

The present disclosure relates to a control system and a control method for a hybrid vehicle.

Background

Hybrid vehicles are known in the art, which include an internal combustion engine and an electric motor, and whose driving mode is switchable between an Electric Vehicle (EV) mode and a Hybrid Vehicle (HV) mode. In the EV mode, the internal combustion engine is stopped and the electric motor is operated. In the HV mode, the internal combustion engine and the motor operate.

In view of exhaust emission and noise, it is preferable to set the driving mode to the EV mode in a specific region such as a residential region. However, continuing the EV mode in a specific area requires electric power. A hybrid vehicle is known in which electric power is generated by regenerative control during deceleration operation to keep the state of charge (SOC) of a battery as high as possible before the hybrid vehicle enters a specific region (see, for example, japanese unexamined patent application publication No.2012-111369(JP2012-111369 a)).

Disclosure of Invention

However, there is a limit to increase the SOC of the battery in view of the battery capacity and the frequency of regeneration control. Therefore, the SOC of the battery may become too low in a certain region, and the EV mode may not be able to be continued. In this case, it is necessary to operate the internal combustion engine in order to keep the vehicle running in a specific region.

The present disclosure provides a control system and a control method for a hybrid vehicle.

A first aspect of the present disclosure relates to a control system for a hybrid vehicle. The control system for a hybrid vehicle includes: an in-vehicle learning unit mounted on the hybrid vehicle and configured to perform a learning action; a position determination unit configured to determine whether the hybrid vehicle is located in a low emission region in which operation of the internal combustion engine should be restricted; and a learning control unit configured to: the learning action of the on-board learning unit is at least partially stopped when it is determined that the hybrid vehicle is located in the low emission region. The hybrid vehicle includes an internal combustion engine and an electric motor. The drive mode of the hybrid vehicle is switchable between an electric vehicle mode and a hybrid vehicle mode. The electric vehicle mode is a mode in which the internal combustion engine is stopped and the electric motor is operated, and the hybrid vehicle mode is a mode in which the internal combustion engine and the electric motor are operated.

In the first aspect, the learning control unit may be configured to: when it is determined that the hybrid vehicle is located in the low emission region, the learning action of the in-vehicle learning unit is completely stopped.

In the above aspect, in a case where it is determined that the hybrid vehicle is located in the low emission region, the learning control unit may be configured to: when it is determined that the SOC of the battery of the hybrid vehicle is lower than a predetermined threshold value, the learning action of the in-vehicle learning unit is at least partially stopped, and may be configured to: when it is determined that the SOC of the battery is equal to or higher than the threshold value, the learning action of the in-vehicle learning unit is not stopped.

In the above aspect, the learning control unit may be configured to: when it is determined that the hybrid vehicle is located in the low emission region and it is determined that the SOC of the battery is lower than the threshold value, the proportion of the learning action of the stopped on-board learning unit is increased as the SOC of the battery decreases.

In the above aspect, the control system may further include a server learning unit that is mounted on a server located outside the hybrid vehicle and is configured to perform the learning action. The server learning unit may be configured to: when the learning action of the in-vehicle learning unit is stopped, the learning action to be performed by the in-vehicle learning unit is performed using data transmitted from the hybrid vehicle to the server, and the learning result of the server learning unit is transmitted to the hybrid vehicle.

In the above aspect, the learning control unit may be configured to: when it is determined that the hybrid vehicle is located outside the low emission region, data is transmitted from the hybrid vehicle to the server.

In the above aspect, in a case where it is determined that the hybrid vehicle is located outside the low emission region, the learning control unit may be configured to: when it is determined that the hybrid vehicle is located in a non-adjacent area that is not adjacent to the low emission area, data is not transmitted from the hybrid vehicle to the server, and may be configured to: when it is determined that the hybrid vehicle is located in an adjacent area adjacent to the low emission area, data is transmitted from the hybrid vehicle to the server.

In the above aspect, the learning control unit may be configured to: when it is determined that the hybrid vehicle is located outside the low emission region, data is repeatedly transmitted from the hybrid vehicle to the server.

A second aspect of the disclosure relates to a control method for a hybrid vehicle. The control method for a hybrid vehicle includes: performing a learning action by an on-board learning unit mounted on the hybrid vehicle; determining whether the hybrid vehicle is located in a low emission region in which operation of the internal combustion engine should be restricted; and at least partially stopping the learning action of the in-vehicle learning unit when it is determined that the hybrid vehicle is located in the low emission region. The hybrid vehicle includes an internal combustion engine and an electric motor. The drive mode of the hybrid vehicle is switchable between an electric vehicle mode and a hybrid vehicle mode. The electric vehicle mode is a mode in which the internal combustion engine is stopped and the electric motor is operated, and the hybrid vehicle mode is a mode in which the internal combustion engine and the electric motor are operated.

According to each aspect of the present disclosure, the EV mode of the hybrid vehicle is reliably continued in the low emission region where the operation of the internal combustion engine should be restricted.

Drawings

Features, advantages, and technical and industrial significance of exemplary embodiments of the present invention will be described below with reference to the accompanying drawings, in which like reference numerals represent like elements, and wherein:

fig. 1 is a schematic overall view of a control system according to a first embodiment of the present disclosure;

fig. 2 schematically illustrates a low emission area according to a first embodiment of the present disclosure;

FIG. 3 is a functional block diagram of a vehicle in a first embodiment according to the present disclosure;

FIG. 4 is a functional block diagram of a server in a first embodiment according to the present disclosure;

fig. 5 is a timing diagram illustrating a first embodiment according to the present disclosure;

FIG. 6 is a flow chart of a vehicle control routine according to a first embodiment of the present disclosure;

fig. 7 is a flowchart of a server control routine according to a first embodiment of the present disclosure;

FIG. 8 is a functional block diagram of a vehicle in a second embodiment according to the present disclosure;

fig. 9 is a graph illustrating an example of the proportion of a stopped learning action in the second embodiment according to the present disclosure;

fig. 10 is a graph illustrating another example of the proportion of a learning action that is stopped in the second embodiment according to the present disclosure;

fig. 11 is a flowchart of a vehicle control routine according to a second embodiment of the present disclosure;

fig. 12 is a functional block diagram of a server in a third embodiment according to the present disclosure;

fig. 13 is a timing diagram illustrating a third embodiment according to the present disclosure;

fig. 14 is a flowchart of a vehicle control routine according to a third embodiment of the present disclosure;

fig. 15 is a flowchart of a server control routine according to a third embodiment of the present disclosure;

FIG. 16 schematically illustrates a low emission area and an adjacent area according to a fourth embodiment of the present disclosure;

fig. 17 is a timing diagram illustrating a fourth embodiment according to the present disclosure; and

fig. 18 is a flowchart of a server control routine according to a fourth embodiment of the present disclosure.

Detailed Description

A first embodiment according to the present disclosure will be described with reference to fig. 1 to 7. Referring to fig. 1, a control system 1 for a hybrid vehicle according to a first embodiment of the present disclosure includes a hybrid vehicle 10 and a server 30 external to the hybrid vehicle 10.

The hybrid vehicle 10 according to the first embodiment of the present disclosure includes an internal combustion engine 11, a motor generator (M/G)12, a battery 13, at least one sensor 14, a Global Positioning System (GPS) receiver 15, a storage device 16, a communication device 17, and an electronic control unit 20. The internal combustion engine 11 is, for example, a spark ignition engine or a compression ignition engine. The internal combustion engine 11 (e.g., a fuel injection valve, an ignition plug, a throttle valve, etc.) is controlled based on a signal from the electronic control unit 20. The motor generator 12 operates as a motor or a generator. The motor generator 12 is controlled based on a signal from the electronic control unit 20.

In the first embodiment according to the present disclosure, the drive mode of the hybrid vehicle 10 is switchable between the EV mode and the HV mode. In the EV mode according to the first embodiment of the present disclosure, the internal combustion engine 11 is stopped and the motor generator 12 is operated as a motor. In this case, the output of the motor generator 12 is transmitted to the axle. In the HV mode according to the first embodiment of the present disclosure, the internal combustion engine 11 is operated and the motor generator 12 is operated as a motor. In this case, in one example, the output of the internal combustion engine 11 and the output of the motor generator 12 are transmitted to the axle. In another example, the output of the motor generator 12 is transmitted to the axle, and the output of the internal combustion engine 11 is transmitted to a generator (not shown) to operate the generator. The electric power generated by the generator is sent to the motor generator 12 or the battery 13. In still another example, a part of the output of the internal combustion engine 11 and the output of the motor generator 12 are transmitted to the axle, and the remaining part of the output of the internal combustion engine 11 is transmitted to the generator. The electric power generated by the generator is sent to the motor generator 12 or the battery 13. In the first embodiment according to the present disclosure, in the EV mode and the HV mode, the regenerative control using the motor generator 12 as a generator is performed during, for example, deceleration operation. The electric power generated by the regeneration control is transmitted to the battery 13.

The battery 13 according to the first embodiment of the present disclosure is charged by electric power from the motor generator 12 operating as a generator or from a generator (not shown). In another embodiment (not shown), the battery 13 can also be charged by an external power source. In the first embodiment according to the present disclosure, electric power is supplied from the battery 13 to the motor generator 12 that operates as a motor, the electronic control unit 20, and other vehicle-mounted devices.

The sensor 14 according to the first embodiment of the present disclosure detects various raw data. Examples of the sensor 14 according to the first embodiment of the present disclosure include: a load sensor for detecting a required vehicle load indicated by a depression amount of an accelerator pedal; a throttle opening sensor for detecting a throttle opening of the internal combustion engine 11; an NOx sensor for detecting the NOx concentration in the exhaust gas of the internal combustion engine 11; a rotational speed sensor for detecting a rotational speed of the internal combustion engine 11; a voltmeter for detecting the voltage of the battery 13; and an ammeter for detecting the current of the battery 13. The output signals of these sensors 14 are input to an electronic control unit 20.

The GPS receiver 15 according to the first embodiment of the present disclosure receives signals from GPS satellites and detects information indicating an absolute position (e.g., latitude and longitude) of the vehicle 10 from the received signals. The positional information of the vehicle 10 is input to the electronic control unit 20.

Various data are stored in advance in the storage device 16 according to the first embodiment of the present disclosure. The communication device 17 according to the first embodiment of the present disclosure is capable of connecting to a communication network N such as the internet.

The electronic control unit 20 of the vehicle 10 according to the first embodiment of the present disclosure includes one or more processors 21, one or more memories 22, and input and output (I/O) ports 23. The one or more processors 21, the one or more memories 22 and the I/O ports 23 are connected by a bidirectional bus so that they can communicate with each other. The memory 22 includes, for example, a Read Only Memory (ROM), a Random Access Memory (RAM), and the like. The memory 22 has various programs stored therein, and various functions are realized by the execution of the programs by the processor 21. The internal combustion engine 11, the motor generator 12, the sensor 14, the GPS receiver 15, the storage device 16, and the communication device 17 are connected to the I/O port 23 according to the first embodiment of the present disclosure so that they can communicate with the I/O port 23. In the processor 21 according to the first embodiment of the present disclosure, the state of charge (SOC) of the battery 13 is calculated based on, for example, the voltage and current of the battery 13.

Referring to fig. 1, a server 30 according to a first embodiment of the present disclosure includes a storage device 31, a communication device 32, and an electronic control unit 40.

The storage device 31 according to the first embodiment of the present disclosure has stored therein the position information (for example, latitude and longitude) of the low emission region in which the operation of the internal combustion engine 11 should be restricted. Fig. 2 schematically illustrates an example of the low emission region LEZ according to the first embodiment of the present disclosure. The low emission area LEZ according to the first embodiment of the present disclosure is surrounded by a closed border or geofence GF. For example, the low emission area LEZ is set in an urban area.

The communication device 32 according to the first embodiment of the present disclosure is capable of connecting to the communication network N. The vehicle 10 and the server 30 can thus be connected to each other via the communication network N.

Like the electronic control unit 20 of the vehicle 10, the electronic control unit 40 of the server 30 according to the first embodiment of the present disclosure includes one or more processors 41, one or more memories 42, and I/O ports 43, and the one or more processors 41, the one or more memories 42, and the I/O ports 43 are connected by a bidirectional bus so that they can communicate with each other. The storage device 31 and the communication device 32 are connected to the I/O port 43 according to the first embodiment of the present disclosure so that they can communicate with the I/O port 43.

Fig. 3 is a functional block diagram of the vehicle 10 according to the first embodiment of the present disclosure. Referring to fig. 3, the electronic control unit 20 of the vehicle 10 includes a positional information acquisition unit 20a, an in-vehicle learning unit 20b, a learning result utilization unit 20c, a drive mode control unit 20d, and a learning control unit 20 e.

The positional information acquisition unit 20a according to the first embodiment of the present disclosure acquires the positional information of the vehicle 10 from the GPS receiver 15. The position information acquisition unit 20a transmits this position information to the server 30.

The in-vehicle learning unit 20b according to the first embodiment of the present disclosure performs a learning action. The in-vehicle learning unit 20b includes a raw data acquisition unit 20b1, a data preprocessing unit 20b2, and a learning calculation unit 20b 3.

The raw data acquisition unit 20b1 according to the first embodiment of the present disclosure acquires raw data necessary for learning. The raw data includes, for example, the output of the sensor 14, the calculation result of the processor 21, and the like.

The data preprocessing unit 20b2 according to the first embodiment of the present disclosure preprocesses the raw data acquired by the raw data acquisition unit 20b1 to generate a data set suitable for learning. Such pre-processing includes filtering, cleaning, normalization, etc. Examples of the data set include a data set suitable for supervised learning, a data set suitable for unsupervised learning, and a data set suitable for reinforcement learning.

The learning calculation unit 20b3 according to the first embodiment of the present disclosure performs learning using the data set generated by the data preprocessing unit 20b 2. In one example, supervised learning using a neural network is performed. That is, the weights of the neural network are repeatedly calculated until the difference between the output of the neural network and the training data corresponding to a certain value becomes smaller than the convergence value when the certain value is input. In another example, learning using random forests, learning using a support vector machine, ensemble learning using multiple computational models in parallel or in series, or the like is performed.

In one example, the learning result of the learning calculation unit 20b3 or the in-vehicle learning unit 20b represents a calculation model. In other words, the calculation model is created or updated by learning the learning action of the calculation unit 20b3 or the in-vehicle learning unit 20 b. An example of the calculation model is a calculation model that outputs the NOx emission amount of the internal combustion engine 11 in accordance with the throttle opening, the engine speed, and the ignition timing. In this example, the raw data acquisition unit 20b1 acquires raw data necessary for learning, such as throttle opening, engine speed, and ignition timing. Another example of the calculation model is a calculation model that outputs the degree of deterioration of the battery 13 according to the air temperature, the temperature of the battery 13, the discharge time of the battery 13, and the discharge energy of the battery 13 per unit time.

Referring to fig. 3, the learning result utilization unit 20c according to the first embodiment of the present disclosure performs a predetermined process by using the learning result of the learning calculation unit 20b3 or the in-vehicle learning unit 20 b. In one example, the vehicle 10, such as the internal combustion engine 11, the motor generator 12, and an in-vehicle infotainment system (not shown), is controlled using a computational model created or updated by the in-vehicle learning unit 20 b.

The learning action of the in-vehicle learning unit 20b according to the first embodiment of the present disclosure includes at least one of the functions of the in-vehicle learning unit 20b, that is, at least one of the acquisition of raw data by the raw data acquisition unit 20b1, the preprocessing of data by the data preprocessing unit 20b2, and the learning by the learning calculation unit 20b 3.

Referring to fig. 3, the drive mode control unit 20d according to the first embodiment of the present disclosure switches the drive mode between the EV mode and the HV mode. In one example, the EV mode is selected when the required vehicle load is lower than a predetermined set load, and the drive mode is switched to the HV mode when the required vehicle load becomes higher than the set load. The EV mode is also selected when the SOC of the battery 13 is higher than a predetermined set SOC, and the drive mode is switched to the HV mode when the SOC of the battery 13 becomes lower than the set SOC.

The learning control unit 20e according to the first embodiment of the present disclosure controls whether to execute or stop the learning action of the in-vehicle learning unit 20 b.

Fig. 4 is a functional block diagram of the server 30 according to the first embodiment of the present disclosure. Referring to fig. 4, the electronic control unit 40 of the server 30 includes a position determination unit 40 a.

The position determining unit 40a according to the first embodiment of the present disclosure determines whether the vehicle 10 is located in the low emission region LEZ based on the position information of the vehicle 10 transmitted from the vehicle 10 to the server 30 and the position information of the low emission region LEZ stored in the storage device 31. The position determining unit 40a creates instruction data according to the determination result and transmits the instruction data to the vehicle 10.

In the first embodiment according to the present disclosure, when the vehicle 10 acquires the position information of the vehicle 10, the vehicle 10 transmits the position information of the vehicle 10 to the server 30. When the position determining unit 40a of the server 30 receives the position information of the vehicle 10, the position determining unit 40a determines whether the vehicle 10 is located in the low emission zone LEZ based on the received position information of the vehicle 10 and the position information of the low emission zone LEZ stored in the storage device 31. When the position determining unit 40a determines that the vehicle is located outside the low emission region LEZ, the position determining unit 40a creates instruction data including a learning permission instruction and transmits the instruction data to the vehicle 10. When the position determining unit 40a determines that the vehicle 10 is located in the low emission region LEZ, the position determining unit 40a creates instruction data including a learning stop instruction and transmits the instruction data to the vehicle 10.

When the vehicle 10 receives the instruction data from the server 30, the learning control unit 20e of the vehicle 10 determines whether the received instruction data includes a learning stop instruction. When the learning control unit 20e determines that the instruction data includes the learning permission instruction, the learning control unit 20e permits the learning action of the in-vehicle learning unit 20b or the vehicle 10. As a result, for example, a calculation model is accurately created or updated, and satisfactory control is maintained. When the learning control unit 20e determines that the instruction data includes the learning stop instruction, the learning control unit 20e stops the learning action of the in-vehicle learning unit 20b or the vehicle 10. This configuration limits the power consumption of the vehicle when the vehicle 10 is located in the low emission region LEZ. The SOC of the battery 13 is therefore less likely to fall below the set SOC. The EV mode therefore reliably continues in the low emission region LEZ.

That is, in the example of fig. 5, it is not determined until time ta1 that the vehicle 10 is located outside the low emission region LEZ. The learning action of the vehicle 10 or the in-vehicle learning unit 20b is not permitted until the time ta 1. When it is determined at time ta1 that the vehicle 10 has entered the low emission region LEZ, the learning action of the vehicle 10 is stopped. When it is then determined at time ta2 that the vehicle 10 has left the low emission region LEZ, the learning action of the vehicle 10 is again permitted.

In one example, when the learning action of the in-vehicle learning unit 20b should be stopped, the learning action of the in-vehicle learning unit 20b is completely stopped. This configuration significantly reduces the power consumption of the vehicle 10. In another example, the learning action of the in-vehicle learning unit 20b is partially stopped. In this case, the learning action of the in-vehicle learning unit 20b partially continues while limiting the power consumption of the vehicle 10. For example, in order to partially stop the learning action of the in-vehicle learning unit 20b, at least one of the functions of the in-vehicle learning unit 20b, that is, at least one of acquisition of raw data by the raw data acquisition unit 20b1, preprocessing of data by the data preprocessing unit 20b2, and learning by the learning calculation unit 20b3 is stopped. Alternatively, the frequency at which the in-vehicle learning unit 20b is caused to perform the learning action is lower than the normal frequency. Alternatively, when the neural network is used for learning, the above convergence value is made larger than a normal value. When a random forest is used for learning, the number of decision trees is made smaller than the normal number of decision trees. When the ensemble learning is used for learning, the number of learners to be used for the ensemble learning is made smaller than the normal number of learners. Alternatively, the number of pieces of raw data or the number of pieces of preprocessed data to be used for the learning action is made smaller than the normal number of pieces of raw data or preprocessed data.

The larger the number of functions of the stopped in-vehicle learning unit 20b is, the higher the proportion of the learning operation of the stopped in-vehicle learning unit 20b is. Alternatively, the lower the frequency with which the in-vehicle learning unit 20b performs the learning action, the larger the convergence value, the smaller the number of decision trees, the smaller the number of learners, or the smaller the number of pieces of data to be used for the learning action, the higher the proportion of the learning action of the in-vehicle learning unit 20b that is stopped. For example, the proportion of the learning operation of the stopped in-vehicle learning unit 20b is expressed in the form of a numerical value between 0 and 1. When the ratio is zero, the learning action is not stopped. When the ratio is 1, the learning action is completely stopped.

Fig. 6 illustrates a routine for executing control of the vehicle 10 in the first embodiment according to the present disclosure. This routine is repeated at predetermined set time intervals, for example. Referring to fig. 6, in step 100, position information of the vehicle 10 is acquired. In step 101, the position information of the vehicle 10 is then transmitted to the server 30. Thereafter, in step 102, it is determined whether instruction data has been received from the server 30. Step 102 is repeated until it is determined that instruction data has been received from the server 30. When it is determined that the instruction data has been received from the server 30, the routine proceeds to step 103, and determines whether the instruction data includes a learning permission instruction or a learning stop instruction. When it is determined that the instruction data includes the learning permission instruction, the routine proceeds to step 104, and the learning action of the vehicle 10 is permitted. The routine then proceeds to step 106. When it is determined that the instruction data includes the learning stop instruction, the routine proceeds to step 105, and the learning action of the vehicle 10 is stopped. Processing then proceeds to step 106.

In step 106, the vehicle 10 is controlled using the learning result, for example. When the routine proceeds from step 105 to step 106, the learning result obtained before the learning action is stopped is used to control the vehicle 10.

Fig. 7 illustrates a routine for performing control of the server 30 in the first embodiment according to the present disclosure. This routine is repeated at predetermined set time intervals, for example. Referring to fig. 7, in step 200, it is determined whether position information of the vehicle 10 has been received from the vehicle 10. When it is determined that the position information of the vehicle 10 has not been received, the processing cycle ends. When it is determined that the position information of the vehicle 10 has been received, the routine proceeds to step 201, and it is determined whether the vehicle 10 is located in the low emission region LEZ. When it is determined that the vehicle 10 is located outside the low emission region LEZ, the routine proceeds to step 202, and instruction data including a learning permission instruction is created. The routine then proceeds to step 204. When it is determined that the vehicle 10 is located in the low emission region LEZ, the routine proceeds to step 203, and instruction data including a learning stop instruction is created. The routine then proceeds to step 204. In step 204, the instruction data is transmitted to the vehicle 10.

In the first embodiment according to the present disclosure, as described above, the drive mode is switched to the EV mode or the HV mode based on the required vehicle load and the SOC of the battery 13. Therefore, in order to maintain the EV mode in the low emission region LEZ or in order to prevent the driving mode from being switched to the HV mode in the low emission region LEZ, the driver of the vehicle 10 is required to adjust the required vehicle load (for example, the depression amount of the accelerator pedal), manage the SOC of the battery 13, and the like. In another embodiment (not shown), when it is determined that the vehicle 10 is located in the low emission region LEZ, the driving mode control unit 20d automatically switches the driving mode to the EV mode and maintains the EV mode.

Next, a second embodiment according to the present disclosure will be described with reference to fig. 8 to 11. The second embodiment according to the present disclosure is different from the first embodiment according to the present disclosure in the following points. As shown in fig. 8, the electronic control unit 20 of the vehicle 10 according to the second embodiment of the present disclosure includes an SOC acquisition unit 20 f. The SOC acquisition unit 20f acquires the SOC of the battery 13 from, for example, the processor 21.

In the first embodiment according to the present disclosure, the learning action of the vehicle 10 is at least partially stopped when it is determined that the vehicle 10 is located in the low emission region LEZ. This configuration reduces the power consumption of the vehicle 10 and limits the reduction of the SOC of the battery 13. However, when the SOC of the battery 13 is high, there is little need to limit the power consumption of the vehicle 10.

Therefore, in the second embodiment according to the present disclosure, when it is determined that the vehicle 10 is located in the low emission region LEZ and the SOC of the battery 13 is equal to or higher than the predetermined threshold SOCx, the learning action of the vehicle 10 is not stopped but allowed. However, when it is determined that the vehicle 10 is located in the low emission region LEZ and the SOC of the battery 13 is lower than the threshold SOCx, the learning action of the vehicle 10 is stopped.

In one example, when the SOC of the battery 13 is lower than the threshold SOCx, the learning action of the vehicle 10 is completely stopped regardless of the SOC of the battery 13. When it is expressed using the ratio R of the learning action of the stopped vehicle 10, the ratio R is zero when the SOC of the battery 13 is equal to or greater than the threshold value SOCx, as shown in fig. 9. The ratio R is 1 when the SOC of the battery 13 is lower than the threshold SOCx.

In another example, when the SOC of the battery 13 is lower than the threshold SOCx, the proportion R of the learning action of the stopped vehicle 10 is increased as the SOC of the battery 13 decreases. That is, as shown in fig. 10, when the SOC of the battery 13 is equal to or higher than the threshold value SOCx, the ratio R of the learning action of the stopped vehicle 10 is zero. When the SOC of the battery 13 is lower than the threshold SOCx, the ratio R is increased as the SOC of the battery 13 decreases. In the example shown in fig. 10, when the SOC of the battery 13 is lower than another threshold value SOCy, the ratio R of 1 is maintained, and the learning action is completely stopped. The higher the ratio R, the more the power consumption of the vehicle 10 is limited.

Fig. 11 illustrates a routine for executing control of the vehicle 10 in the second embodiment according to the present disclosure. The routine of fig. 11 is different from the routine of fig. 6 in the following points. In the routine of fig. 11, first, it is determined in step 100a whether the SOC of the battery 13 is lower than the threshold SOCx. When SOC < SOCx, the routine proceeds to step 100. Therefore, when the SOC < SOCx is determined and the vehicle 10 is located in the low emission region LEZ, the learning action of the vehicle 10 is stopped. When SOC ≧ SOCx, the routine proceeds from step 100a to step 104. When the SOC ≧ SOCx, the learning action of the vehicle 10 is therefore permitted regardless of whether the vehicle 10 is located in the low-emission region LEZ.

In the second embodiment according to the present disclosure, when the SOC of the battery 13 is high, the stop of the learning action of the vehicle 10 is restricted. In another embodiment (not shown), the stop of the learning action of the vehicle 10 is restricted when the required load of the vehicle 10 is low or when a large amount of electric power is generated by regenerative control of the vehicle 10. In this case, the SOC of the battery 13 is less likely to become excessively low.

Next, a third embodiment according to the present disclosure will be described with reference to fig. 12 to 15. The third embodiment according to the present disclosure is different from the first embodiment according to the present disclosure in the following points. As shown in fig. 12, the electronic control unit 40 of the server 30 according to the third embodiment of the present disclosure includes a position determination unit 40a, a server learning unit 40b, and a learning result utilization unit 40 c. The server learning unit 40b performs a learning action. The server learning unit 40b includes a data preprocessing unit 40b2 and a learning calculation unit 40b 3.

The data preprocessing unit 40b2, the learning calculation unit 40b3, and the learning result utilization unit 40c according to the third embodiment of the present disclosure are configured similarly to the data preprocessing unit 20b2, the learning calculation unit 20b3, and the learning result utilization unit 20c of the in-vehicle learning unit 20b, respectively.

In the first embodiment according to the present disclosure, the learning action of the vehicle 10 is at least partially stopped when it is determined that the vehicle 10 is located in the low emission region LEZ. However, when the learning action of the vehicle 10 is stopped, satisfactory control may not be able to be performed because, for example, a calculation model is not created or updated.

Therefore, in the third embodiment according to the present disclosure, when the learning action of the vehicle 10 is stopped, the learning action to be performed by the vehicle 10 is performed by the server 30, and the learning result of the server 30 is transmitted to the vehicle 10. In the vehicle 10, for example, the received learning result is used to control the internal combustion engine 11.

In the third embodiment according to the present disclosure, when the position determining unit 40a of the server 30 determines that the vehicle 10 is located outside the low emission region LEZ, the position determining unit 40a creates instruction data including a learning permission instruction and a data transmission instruction and transmits the instruction data to the vehicle 10. When the learning control unit 20e of the vehicle 10 receives the data transmission instruction, the learning control unit 20e of the vehicle 10 transmits data necessary for the learning action to the server 30. In this case, the data transmitted to the server 30 is, for example, raw data acquired by the raw data acquisition unit 20b 1.

When the data preprocessing unit 40b2 of the server learning unit 40b receives the raw data, the data processing unit 40b2 generates a data set suitable for learning from the raw data. The learning calculation unit 40b3 of the server learning unit 40b then performs learning using the data set generated by the data preprocessing unit 40b 2. Thereafter, the learning calculation unit 40b3 transmits the learning result to the vehicle 10.

When the learning result utilizing unit 20c of the vehicle 10 receives the learning result, the learning result utilizing unit 20c uses the learning result to execute a predetermined process, for example, control the internal combustion engine 11. Satisfactory control is continued in the vehicle 10 while limiting the power consumption of the vehicle 10.

In another embodiment (not shown), the data sent from the vehicle 10 to the server 30 is a data set generated by the data pre-processing unit 20b2 of the vehicle 10. In this case, the server 30 need not include the data preprocessing unit 40b 2.

In the example of fig. 13, it is not determined until time tb1 that the vehicle 10 is located outside the low emission region LEZ. The data necessary for learning is not transmitted from the vehicle 10 to the server 30 until the time tb 1. When it is determined at time tb1 that the vehicle 10 has entered the low emission region LEZ, the learning action of the vehicle 10 is stopped and the learning action of the server 30 is started. Subsequently, when the learning action of the server 30 is completed at time tb2, the learning result is transmitted from the server 30 to the vehicle 10. When it is then determined at time tb3 that the vehicle 10 has left the low-emission region LEZ, the learning action of the vehicle 10 is again permitted, and the data transmission from the vehicle 10 to the server is also resumed.

In the third embodiment according to the present disclosure, when it is determined that the vehicle 10 is located outside the low emission region LEZ, data transmission from the vehicle 10 to the server 30 is repeatedly performed. The server 30 performs a learning action using the latest data among the received data.

In another embodiment (not shown), when it is determined that the vehicle 10 is located in the low emission region LEZ, data necessary for the learning action is transmitted from the vehicle 10 to the server 30. However, power is consumed for data transmission. Therefore, in the third embodiment according to the present disclosure, when it is determined that the vehicle 10 is located outside the low emission region LEZ, data is transmitted from the vehicle 10 to the server 30.

Fig. 14 illustrates a routine for executing control of the vehicle 10 in the third embodiment according to the present disclosure. The routine of fig. 14 differs from the routine of fig. 6 in the following points. In the routine of fig. 14, the routine proceeds from step 104 to step 104a, and determines whether the received instruction data includes a data transfer instruction. When the received instruction data does not include a data transfer instruction, the processing loop ends. When the received instruction data includes a data transmission instruction, the routine proceeds to step 104b, and data necessary for the learning action is transmitted from the vehicle 10 to the server 30.

In the routine of fig. 14, the routine proceeds from step 105 to step 105a, and it is determined whether a learning result has been received from the server 30. Step 105a is repeated until it is determined that the learning result has been received. When it is determined that the learning result has been received, the routine proceeds to step 106. When the routine proceeds from step 105a to step 106, the learning result from the server 30 is used.

Fig. 15 illustrates a routine for performing control of the server 30 in the third embodiment according to the present disclosure. The routine of fig. 15 differs from the routine of fig. 7 in the following points. In the routine of fig. 15, the routine proceeds from step 202 to step 202a, and creates a data transfer instruction. Thereafter, in step 202b, instruction data including the learning permission instruction and the data transmission instruction is transmitted to the vehicle 10. Subsequently, in step 202c, it is determined whether data necessary for a learning action has been received from the vehicle 10. Step 202c is repeated until it is determined that data has been received. When it is determined that data has been received, the routine proceeds to step 202d, and stores the data in, for example, the storage device 31. In one example, only the most recent data is stored.

The routine of fig. 15 proceeds from step 203 to step 203a, and transmits instruction data including a learning stop instruction to the vehicle 10. Thereafter, in step 203b, it is determined whether the learning action of the server 30 has not been performed. When it is determined that the learning action of the server 30 has not been performed, the routine proceeds to step 203c, and the learning action is performed. Thereafter, in step 203d, the learning result of the server 30 is transmitted to the vehicle 10. When the learning action of the server 30 has been performed or completed, the processing loop ends. This is because data for performing the learning action has not been newly received.

Next, a fourth embodiment according to the present disclosure will be described with reference to fig. 16 to 18. The fourth embodiment according to the present disclosure is different from the third embodiment according to the present disclosure in the following points. In the fourth embodiment according to the present disclosure, as shown in fig. 16, an adjacent area ADZ adjacent to the low emission area LEZ and a non-adjacent area NADZ located outside the adjacent area ADZ are defined outside the low emission area LEZ. For example, the adjacent area ADZ is an area having a distance shorter than a predetermined value D from the boundary GF of the low discharge area LEZ. The position information of the adjacent area ADZ is stored in the storage device 31 of the server 30, for example.

In the third embodiment according to the present disclosure, when it is determined that the vehicle 10 is located outside the low emission region LEZ, data necessary for the learning action is repeatedly transmitted from the vehicle 10 to the server 30. However, only the most recent data is used for the learning action of the server 30. Further, unless the vehicle 10 enters the low emission region LEZ, the learning action of the server 30 will not be performed.

Therefore, in the fourth embodiment according to the present disclosure, when it is determined that the vehicle 10 is located in the non-adjacent area NADZ, the data necessary for the learning action is not transmitted from the vehicle 10 to the server 30. When it is determined that the vehicle 10 is located in the adjacent area ADZ, data necessary for the learning action is transmitted from the vehicle 10 to the server 30. This configuration limits the number of times data is transmitted and received and limits the power consumption required for data transmission and reception.

In particular, when it is determined that the vehicle 10 has entered the neighborhood zone ADZ from the non-neighborhood zone NADZ, it is expected that the vehicle 10 will subsequently enter the low-emission zone LEZ. Therefore, in the fourth embodiment according to the present disclosure, when it is determined that the vehicle 10 has entered the neighborhood zone ADZ from the non-neighborhood zone NADZ, data is transmitted from the vehicle 10 to the server 30. In this case, when the vehicle 10 is expected to enter the low emission region LEZ, data is transmitted from the vehicle 10 to the server 30.

In the example shown in fig. 17, it is not determined that the vehicle 10 is located in the non-adjacent area NADZ until the time tc 1. The data necessary for the learning action is not transmitted from the vehicle 10 to the server 30 until the time tc 1. When it is determined at the time tc1 that the vehicle 10 has entered the adjacent area ADZ, data is transmitted from the vehicle 10 to the server 30. Subsequently, when it is determined at time tc2 that the vehicle 10 has entered the low emission region LEZ, the learning action of the vehicle 10 is stopped and the learning action of the server 30 is started. When the learning action of the server 30 is then completed at time tc3, the learning result is transmitted from the server 30 to the vehicle 10. When it is then determined at time tc4 that the vehicle 10 has left the low emission region LEZ, the learning action of the vehicle 10 is again permitted.

Fig. 18 illustrates a routine for performing control of the server 30 in the fourth embodiment according to the present disclosure. The routine of fig. 18 is different from the routine of fig. 15 in the following points. In the routine of fig. 18, the routine proceeds from step 202 to step 202x, and determines whether the vehicle 10 has entered the neighborhood ADZ from the non-neighborhood NADZ. When it is determined in step 202x that the vehicle 10 has not entered the neighborhood zone ADZ from the non-neighborhood zone NADZ, the routine proceeds to step 202b, and transmits instruction data to the vehicle 10. In this case, the instruction data does not include a data transfer instruction. When it is determined in step 202x that the vehicle 10 has entered the neighborhood zone ADZ from the non-neighborhood zone NADZ, the routine proceeds to step 202a, and creates a data transmission instruction. Thereafter, in step 202b, instruction data including a data transmission instruction is transmitted to the vehicle 10.

In the third and fourth embodiments according to the present disclosure, when it is determined that the vehicle 10 is located in the low emission region LEZ, the learning result of the server 30 is transmitted to the vehicle 10. In another embodiment (not shown), the learning result of the server 30 is transmitted to the vehicle 10 after the vehicle 10 leaves the low emission region LEZ. This configuration further limits power consumption when the vehicle 10 is located in the low emission region LEZ.

In the above various embodiments according to the present disclosure, the server 30 determines whether the vehicle 10 is located in the low emission region LEZ. In another embodiment (not shown), the electronic control unit 20 of the vehicle 10 includes a position determination unit, and the position determination unit determines whether the vehicle 10 is located in the low emission zone LEZ. In this case, in one example, the position information of the low emission region LEZ is stored in the vehicle 10. In another example, the position information of the low emission area LEZ is stored in the server 30, and the vehicle 10 receives the position information of the low emission area LEZ from the server 30 and determines whether the vehicle 10 is located in the low emission area LEZ.

In yet another embodiment (not shown), at least two of the above various embodiments according to the present disclosure are combined.