Vehicle management system, vehicle, and vehicle driving management method

Abstract

To properly correct a fuel combustion state of an engine even if fuel composition information is not required.SOLUTION: Each of a vehicle 1A and a plurality of vehicles 1B includes sensors 4 for detecting a fuel combustion state of an engine 3. A server 23 includes a memory 232 in which a learnt model related to engine control is stored. In the learnt model, a correction amount for correcting the fuel combustion state of the engine 3 is learnt on the basis of sensor data indicating a detection result of each of the sensors 4 of the plurality of vehicles 1B, and service station data capable of specifying a service station at which each of the plurality of vehicles 1B has received the supply of fuel. A processor 231 calculates the correction amount by imparting the sensor data of the vehicle 1A and the service station data to the learnt model, and transmits the calculated correction amount to the vehicle 1A. The vehicle 1A corrects the fuel combustion state of the engine 3 of the vehicle 1A by using the received correction amount.SELECTED DRAWING: Figure 11

Description

[Technical field]

[0001] The present disclosure relates to a vehicle management system, a vehicle, and a vehicle driving management method, and more particularly, to a technique for managing a vehicle equipped with an engine. [Background technology]

[0002] Japanese Patent Laid-Open Publication No. 2005-113715 (Patent Document 1) discloses a control device that controls the operation of a power plant (specifically, an engine) that uses a specified fuel. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2005-113715 A Summary of the Invention [Problem to be solved by the invention]

[0004] Patent Document 1 describes that when a vehicle is refueled, fuel composition information is acquired based on vehicle position information. The engine control device disclosed in Patent Document 1 is configured to correct the operation of the engine based on the fuel composition information.

[0005] For the engine control device disclosed in Patent Document 1 to be effective, that is, for the engine operation (fuel combustion state in the engine) to be appropriately corrected, it is necessary to obtain information on the composition of the fuel. However, obtaining the information on the composition of the fuel may require complicated processes such as fuel analysis.

[0006] The present disclosure has been made to solve the above-mentioned problems, and an object of the present disclosure is to provide a technology that can appropriately correct the combustion state of fuel in an engine even when fuel composition information is not required. [Means for solving the problem]

[0007] (1) A vehicle management system according to an aspect of the present disclosure includes a target vehicle and a server configured to communicate with the target vehicle and a plurality of vehicles. The target vehicle and each of the plurality of vehicles include at least one sensor that detects a fuel combustion state in the engine. The server includes a memory that stores a trained model related to engine control, and a processor that executes a calculation process using the trained model. In the trained model, a correction amount for correcting the fuel combustion state in the engine is learned based on sensor data indicating the detection result of at least one sensor in each of the plurality of vehicles and gas station data that can identify a gas station from which each of the plurality of vehicles receives a supply of fuel. The sensor data includes at least data on an internal cylinder pressure or a heat release rate of the engine. The correction amount includes at least one of a first correction amount of a control command to an injection system regarding an injection amount or injection timing of a fuel from an injector or an ignition timing of a spark plug, a second correction amount of a control command to an intake system regarding a throttle opening, a wastegate valve opening, or a variable nozzle device opening, and a third correction amount of a control command to an EGR system regarding an EGR valve opening. The processor calculates a correction amount by applying the sensor data and the gas station data of the target vehicle to the trained model, and transmits the calculated correction amount to the target vehicle. The target vehicle uses the received correction amount to correct the fuel combustion state in the engine of the target vehicle.

[0008] (2) The gas station data includes data regarding the location of the gas station and data regarding the timing of refueling at the gas station.

[0009] (3) In the trained model, the correction amount is learned based on the sensor data, the gas station data, and the data on the driving positions of multiple vehicles. The processor calculates the correction amount for the target vehicle by providing the trained model with the data on the driving position of the target vehicle in addition to the sensor data and the gas station data.

[0010] (4) The sensor data includes data regarding at least one of the engine's in-cylinder pressure, the engine's rotational speed, the temperature of exhaust gas from the engine, the pressure difference before and after a filter that captures particulate matter in the exhaust gas, and the concentration of nitrogen oxides in the exhaust gas.

[0011] (5) A vehicle according to another aspect of the present disclosure is a vehicle configured to be able to communicate with a server including a trained model related to engine control. In the trained model, a correction amount for correcting the fuel combustion state in the engine is learned based on sensor data and gas station data collected through communication with a plurality of vehicles each equipped with an engine. The sensor data is data indicating the detection result of the fuel combustion state in each of the engines of the plurality of vehicles. At least data on the engine's internal cylinder pressure or heat release rate is included. The gas station data is data that can identify the gas stations from which multiple vehicles receive fuel. The correction amount includes at least one of a first correction amount of a control command to the injection system regarding the amount or timing of fuel injection from the injector or the ignition timing of the spark plug, a second correction amount of a control command to the intake system regarding the throttle opening, the wastegate valve opening, or the variable nozzle device opening, and a third correction amount of a control command to the EGR system regarding the EGR valve opening. The vehicle includes a communication device and a control device. The communication device transmits sensor data and gas station data of the vehicle to a server, and receives a correction amount calculated by the server applying the sensor data and gas station data from the vehicle to the trained model. The control device corrects the fuel combustion state in the engine of the vehicle using the received correction amount.

[0012] (6) A vehicle driving management method according to yet another aspect of the present disclosure manages vehicle driving using a trained model for engine control. In the trained model, a correction amount for correcting the fuel combustion state in the engine is learned based on sensor data and gas station data collected through communication with multiple vehicles, each of which is equipped with an engine. The sensor data is data indicating the detection results of the fuel combustion state in each of the multiple vehicles' engines. The gas station data is data that can identify the gas stations from which the multiple vehicles received fuel. The correction amount includes at least one of a first correction amount of a control command to the injection system regarding the amount or timing of fuel injection from the injector or the ignition timing of the spark plug, a second correction amount of a control command to the intake system regarding the throttle opening, the wastegate valve opening, or the variable nozzle device opening, and a third correction amount of a control command to the EGR system regarding the EGR valve opening. The driving management method includes a first step and a second step. The first step is a step of calculating a correction amount for correcting the fuel combustion state in the engine of the target vehicle by providing sensor data and gas station data from the target vehicle to the trained model. The second step is a step of correcting the fuel combustion state in the engine of the target vehicle using the correction amount calculated in the first step. Effect of the Invention

[0013] According to the present disclosure, the combustion state of fuel in an engine can be appropriately corrected even if fuel composition information is not required. [Brief description of the drawings]

[0014] [Figure 1] 1 is a diagram illustrating an overall configuration of a vehicle management system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a diagram showing the configuration of a vehicle and a control center in more detail. [Diagram 3] FIG. 2 is a diagram illustrating an example of a configuration of an engine. [Figure 4] FIG. 2 is a diagram illustrating another example of the configuration of an engine. [Diagram 5] FIG. 2 is a diagram showing an example of a configuration of sensors. [Figure 6] FIG. 2 is a functional block diagram showing an example of a prediction model related to the combustion state of the engine in the present embodiment. [Figure 7] 5 is a diagram for explaining an example of a combustion improvement process for correcting the operation of an injection system of an engine. FIG. [Figure 8] 10A to 10C are diagrams for explaining another example of the combustion improvement process for correcting the operation of the injection system of the engine. [Figure 9] FIG. 4 is a diagram for explaining an example of a combustion improvement process for correcting the operation of an EGR system of the engine. [Figure 10] 5 is a diagram for explaining an example of a combustion improvement process for correcting the operation of an intake system of an engine. FIG. [Figure 11] 4 is a flowchart showing a processing procedure of a combustion improvement process in the present embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In the drawings, the same or corresponding parts are denoted by the same reference characters, and the description thereof will not be repeated.

[0016] [Embodiment Mode] <Overall system configuration> Fig. 1 is a diagram showing an outline of the overall configuration of a vehicle management system according to the present embodiment. The vehicle management system 100 includes a vehicle 1A, a plurality of vehicles 1B, and a control center 2. Fig. 1 shows a state in which the vehicle 1A is refueled at a gas station 9. The vehicle 1A corresponds to a "target vehicle" according to the present disclosure.

[0017] Vehicle 1A and the multiple vehicles 1B basically have a common configuration. When vehicle 1A and vehicle 1B are not distinguished from each other, they are also referred to as "vehicle 1." Each vehicle 1 and control center 2 are configured to be capable of two-way communication.

[0018] The vehicle 1 is a vehicle equipped with an engine 3 (see FIG. 3), and specifically, is a so-called conventional vehicle, hybrid vehicle, or plug-in hybrid vehicle. The type of fuel burned by the engine 3 is not particularly limited. The fuel may be, for example, gasoline fuel, diesel fuel, biofuel (ethanol, etc.), or gaseous fuel (propane gas, etc.). The fuel may also be hydrogen, ammonia, e-fuel (a synthetic liquid fuel of carbon dioxide and hydrogen), dimethyl ether (DME), or the like.

[0019] 2 is a diagram showing in more detail the configuration of the vehicle 1 and the control center 2. The vehicle 1 includes a navigation system 11, a DCM (Data Communication Module) 12, an ECU (Electronic Control Unit) 13, an in-vehicle network 14, an engine 3, and sensors 4.

[0020] The navigation system 11 includes a GPS (Global Positioning System) receiver (not shown) and identifies the position of the vehicle 1 based on radio waves from an artificial satellite (not shown). The navigation system executes various navigation processes for the vehicle 1 using the position information of the vehicle 1 identified by the GPS receiver.

[0021] The DCM 12 is configured to enable two-way wireless communication with the control center 2. This enables the control center 2 to manage the driving history of the vehicle 1 by collecting position information of the vehicle 1. Note that, hereinafter, the position information of the vehicle 1 is also referred to as "vehicle position data."

[0022] The ECU 13 includes a processor 131 such as a CPU (Central Processing Unit), a memory 132 such as a ROM (Read Only Memory) and a RAM (Random Access Memory), and an input / output port 133 for inputting and outputting signals. The ECU 13 controls the engine 3 based on input of signals from the sensors 4 and maps and programs stored in the memory 132 so that the vehicle 1 is in a desired state.

[0023] The in-vehicle network 14 is a wired network such as a Controller Area Network (CAN), etc. The in-vehicle network 14 connects the navigation system 11, the DCM 12, and the ECU 13 to one another.

[0024] The engine 3 burns fuel in accordance with a control command from the ECU 13 to output driving force for running the vehicle 1. The sensors 4 comprehensively describe various sensors mounted on the vehicle 1. In this embodiment, the sensors 4 are mainly used to predict the combustion state of the engine 3. The configurations of the engine 3 and the sensors 4 will be described in more detail with reference to Figs. 3 and 5.

[0025] The control center 2 is configured to manage the traveling of a plurality of vehicles 1. The control center 2 includes a vehicle database 21, a traveling history database 22, a server 23, a communication module 24, and an intranet 25.

[0026] The vehicle database 21 stores identification information, manufacturing information, and the like, related to each of the multiple vehicles 1. The identification information includes, for example, the serial number of the vehicle 1 and the communication device ID of the DCM 12. The manufacturing information includes, for example, information related to the manufacturer and vehicle type (model, grade, year, etc.) of the vehicle 1.

[0027] The driving history database 22 stores the driving history of each of the multiple vehicles 1. The driving history includes vehicle position data, as well as data on the fuel combustion state in the engine 3 (also referred to as the combustion state of the engine 3). The driving history database 22 also stores gas station data, which will be described later.

[0028] Like the ECU 13, the server 23 includes a processor 231, a memory 232, and an input / output port 233. The server 23 may be a cloud server. In this embodiment, a main process executed by the server 23 is a process for improving the combustion state of the engine 3. This process is referred to as a "combustion improvement process." The combustion improvement process will be described in detail later.

[0029] The communication module 24 is configured to be capable of wireless two-way communication with the DCM 12 mounted on the vehicle 1 .

[0030] The intranet 25 connects the vehicle database 21, the driving history database 22, the server 23, and the communication module 24 to one another.

[0031] <Engine configuration> 3 is a diagram showing an example of the configuration of engine 3. Engine 3 is, for example, an in-line four-cylinder spark ignition internal combustion engine. Engine 3 includes an engine body 31. Engine body 31 includes four cylinders 311-314 aligned in one direction. Since each of cylinders 311-314 has the same configuration, the configuration of cylinder 311 will be representatively described below.

[0032] The cylinder 311 is provided with two intake valves 321, two exhaust valves 322, an injector 323, and a spark plug 324. An intake passage 33 and an exhaust passage 34 are connected to the cylinder 311. The intake passage 33 is opened and closed by the intake valve 321. The exhaust passage 34 is opened and closed by the exhaust valve 322. A mixture of air and fuel is generated by adding fuel to air supplied to the engine body 31 through the intake passage 33. The fuel is injected into the cylinder 311 by the injector 323, and a mixture is generated in the cylinder 311. Then, the spark plug 324 ignites the mixture in the cylinder 311. In this way, the mixture is burned in the cylinder 311. The combustion energy generated when the mixture is burned in the cylinder 311 is converted into kinetic energy by a piston (not shown) in the cylinder 311 and is output. The fuel supply system for the engine 3 is not limited to in-cylinder injection, but may be port injection, or a combination of in-cylinder injection and port injection.

[0033] The engine 3 further includes a turbocharger 35, a waste gate valve (WGV) device 36, and an EGR device 37. The turbocharger 35 is configured to supercharge the intake air by utilizing exhaust energy. More specifically, the turbocharger 35 includes a compressor 351, a turbine 352, and a shaft 353. The compressor 351 is disposed in the intake passage 33, and the turbine 352 is disposed in the exhaust passage 34. The compressor 351 and the turbine 352 are configured to be connected to each other via the shaft 353 and rotate integrally. The turbine 352 rotates by receiving the flow of exhaust gas discharged from the engine body 31. The rotational force of the turbine 352 is transmitted to the compressor 351 via the shaft 353 to rotate the compressor 351. The intake air heading to the engine body 31 is compressed by the rotation of the compressor 351, and the compressed air is supplied to the engine body 31.

[0034] An air flow meter 405 (described later) is provided in the intake passage 33 at a position upstream of the compressor 351. An intercooler 331 is provided in the intake passage 33 at a position downstream of the compressor 351. A throttle valve 332 is provided in the intake passage 33 at a position downstream of the intercooler 331. Air (intake air) flowing into the intake passage 33 is supplied to each cylinder 311-314 of the engine body 31 through the compressor 351, the intercooler 331, and the throttle valve 332. The intercooler 331 cools the intake air compressed by the compressor 351. The throttle valve 332 is configured to be able to adjust the flow rate of the intake air flowing through the intake passage 33.

[0035] The exhaust passage 34 is provided with a catalytic device 341 and an aftertreatment device 342. The catalytic device 341 includes, for example, a three-way catalytic converter. The catalytic device 341 oxidizes unburned components (for example, hydrocarbons (HC) or carbon monoxide (CO)) contained in the exhaust gas discharged from the engine 3, and reduces oxidized components (for example, nitrogen oxides (NOx)). The aftertreatment device 342 is provided at a position downstream of the catalytic device 341. The aftertreatment device 342 includes a filter such as a DPF (Diesel Particulate Filter), and collects particulate matter (PM) discharged from the engine 3.

[0036] The WGV device 36 is provided in the exhaust passage 34 at a position upstream of the catalytic device 341. The WGV device 36 is configured to allow the exhaust gas discharged from the engine body 31 to bypass the turbine 352 and to adjust the amount of exhaust gas to be bypassed. The WGV device 36 includes a bypass passage 361, a WGV 362, and a WGV actuator 363.

[0037] The bypass passage 361 is connected to the exhaust passage 34, and allows the exhaust gas to flow around the turbine 352. Specifically, the bypass passage 361 branches off from a portion of the exhaust passage 34 upstream of the turbine 352 (for example, between the engine body 31 and the turbine 352) and merges with a portion of the exhaust passage 34 downstream of the turbine 352 (for example, between the turbine 352 and the catalytic device 341).

[0038] The WGV 362 is disposed in the bypass passage 361. The WGV 362 is a negative pressure type valve that is driven by a WGV actuator 363. The WGV 362 is configured to be able to adjust the flow rate of exhaust gas guided from the engine body 31 to the bypass passage 361 by changing the opening degree thereof. As the WGV 362 is closed, the flow rate of exhaust gas guided from the engine body 31 to the bypass passage 361 decreases while the flow rate of exhaust gas flowing into the turbine 352 increases, and the pressure of the intake air (supercharging pressure) increases.

[0039] The EGR device 37 is provided in the exhaust passage 34 and causes the exhaust gas to flow into the intake passage 33. The EGR device 37 includes an EGR passage 371, an EGR valve 372, and an EGR cooler 373. The EGR passage 371 connects a portion between the catalytic device 341 and the aftertreatment device 342 in the exhaust passage 34 and a portion between the compressor 351 and the air flow meter 405 in the intake passage 33, thereby extracting a part of the exhaust gas from the exhaust passage 34 as EGR gas and directing it to the intake passage 33. The EGR valve 372 is configured to be able to adjust the flow rate of the EGR gas flowing through the EGR passage 371. The EGR cooler 373 cools the EGR gas flowing through the EGR passage 371.

[0040] 4 is a diagram showing another example of the configuration of the engine 3A. The engine 3A differs from the engine 3 shown in FIG.

[0041] The variable nozzle device 38 includes a plurality of variable nozzles (nozzle vanes) provided on the outer periphery of the turbine wheel. The variable nozzles are configured so that their opening (VN opening) can be changed within a range from the fully closed position to the fully open position in response to a control command from the ECU 13. When the nozzle opening of the variable nozzle is reduced, the opening area of ​​the region through which the exhaust gas passes is reduced, and the flow velocity of the exhaust gas introduced into the turbine 352 is increased. As a result, the recovered energy of the turbine wheel is increased, and the boost pressure is increased. On the other hand, when the variable nozzle opening is increased, the opening area of ​​the region through which the exhaust gas passes is increased, and the flow velocity of the exhaust gas is decreased. As a result, the recovered energy of the turbine wheel is reduced, and the boost pressure is reduced.

[0042] <Sensor configuration> 5 is a diagram showing an example of the configuration of the sensors 4. The sensors 4 include a vehicle speed sensor 401, an accelerator opening sensor 402, an engine rotation speed sensor 403, a knock sensor 404, an air flow meter 405, a throttle opening sensor 406, an in-cylinder pressure sensor 407, a cooling water temperature sensor 408, a supercharging pressure sensor 409, a supercharging temperature sensor 410, a turbine rotation speed sensor 411, an exhaust temperature sensor 412, an air-fuel ratio sensor 413, a NOx sensor 414, and a differential pressure sensor 415.

[0043] The vehicle speed sensor 401 detects the speed of the vehicle 1. The accelerator opening sensor 402 detects the amount of depression of the accelerator pedal (not shown) by the driver (accelerator opening). The engine rotation speed sensor 403 detects the rotation angle (crank angle) of the crankshaft (not shown) and the rotation speed of the engine 3. The knock sensor 404 detects the occurrence of knocking in the engine 3 (vibration of the engine body 31). The air flow meter 405 detects the amount of intake air into the intake passage 33.

[0044] The throttle opening sensor 406 detects the opening of the throttle valve 332 (throttle opening). The in-cylinder pressure sensor 407 detects the pressure inside a combustion chamber (not shown). The coolant temperature sensor 408 detects the temperature of the coolant (coolant temperature) circulating through a water jacket (not shown) provided in the engine body 31. The supercharging pressure sensor 409 detects the supercharging pressure by the supercharger 35 (pressure downstream of the compressor 351). The supercharging temperature sensor 410 detects the temperature of the intake air cooled by the intercooler 331 (supercharging temperature).

[0045] The turbine rotation speed sensor 411 detects the rotation speed of the turbine 352 of the turbocharger 35. The exhaust temperature sensor 412 detects the temperature of the exhaust gas. The air-fuel ratio sensor 413 detects the oxygen concentration in the exhaust gas. The NOx sensor 414 detects the nitrogen oxide (NOx) concentration in the exhaust gas. The differential pressure sensor 415 detects the pressure difference between before and after a filter (not shown) included in the aftertreatment device 342. Each sensor outputs a signal indicative of the detection result to the ECU 13.

[0046] <Data Collection> In order to improve the fuel economy and drivability of the vehicle 1A, it is desirable to improve the combustion state of the engine 3. It is also conceivable that the vehicle 1A acquires fuel composition information and improves the combustion state of the engine 3 based on the composition information (see, for example, Patent Document 1). However, obtaining the fuel composition information may require complicated processes such as fuel analysis. Therefore, in this embodiment, instead of a configuration that utilizes the fuel composition information, a configuration described below is adopted.

[0047] The vehicle 1 (ECU 13) transmits data acquired by signals from each sensor included in the sensors 4 to the control center 2 (server 23). This allows the control center 2 to acquire or estimate the fuel combustion state in the engine 3 (cylinders 311-314). Specifically, the control center 2 can acquire the fuel combustion state in the cylinders 311-314 based on a signal (waveform signal of the cylinder pressure) detected by the cylinder pressure sensor 407. The control center 2 can also estimate the combustion state of the engine 3 based on a signal (signal representing sound or vibration generated in the cylinders 311-314) detected by the knock sensor 404. Furthermore, the control center 2 can also estimate the combustion state of the engine 3 based on signals detected by the exhaust temperature sensor 412, the NOx sensor 414, and / or the differential pressure sensor 415. Hereinafter, the data transmitted from the vehicle 1 to the control center 2 and collected by the control center 2 will be collectively referred to as "sensor data".

[0048] It should be noted that the sensors included in the sensors 4 shown in FIG. 5 are merely examples. In other words, the sensor data is not limited to data acquired from these sensors. The sensor data may be data acquired from some of these sensors, or may include data acquired from other sensors not shown in FIG. 5.

[0049] In addition to the sensor data, the vehicles 1 (vehicles 1A and 1B) also transmit data for identifying the gas station that refueled the vehicle 1 to the server 23. Hereinafter, data that can identify a gas station is also referred to as "gas station data." The gas station data specifically includes vehicle position data at the time of refueling the vehicle 1. Since the locations of the gas stations are known to the control center 2 from map information, the gas stations can be identified from the vehicle position data at the time of refueling.

[0050] Furthermore, even at the same gas station, the properties of the fuel supplied may change depending on the time of refueling (e.g., season). Therefore, the gas station data preferably includes data on the time of refueling of the vehicle 1 in addition to vehicle position data at the time of refueling of the vehicle 1. By including data on the time of refueling (e.g., time data) in the gas station data, the properties of the fuel supplied can also be associated with time. However, the gas station data does not have to include data on the time of refueling.

[0051] The memory 232 of the server 23 installed in the control center 2 stores prediction models built by machine learning and / or data mining regarding the combustion state of various fuels. The prediction models are built for each vehicle type (model, grade, year, etc.). It is desirable for the control center 2 to update each prediction model so as to correspond to the latest fuel properties by continuing to learn each prediction model using the sensor data and gas station data collected from the vehicle 1B. When the control center 2 receives the sensor data and gas station data from the vehicle 1A, the control center 2 inputs the data into a prediction model corresponding to the vehicle type of the vehicle 1A and obtains an output from the prediction model. This makes it possible to improve the combustion state of the engine 3 of the vehicle 1A without using specific fuel composition information.

[0052] <Combustion prediction model> 6 is a functional block diagram showing an example of a prediction model (combustion prediction model) related to the combustion state of the engine 3 in this embodiment. Upon receiving sensor data and gas station data, the combustion prediction model outputs a correction amount according to a calculation rule obtained by machine learning, using indices indicated by the sensor data and the gas station data as feature amounts.

[0053] The combustion prediction model is a trained model, for example, a neural network model constructed by unsupervised learning or reinforcement learning. The neural network model includes an input layer, a hidden layer, and an output layer. The input variable to the input layer is y i (i is a natural number). The output variables from the hidden layer to the output layer are written as θ j(j is a natural number). The output variables taken out from the output layer are written as Z p The weight from the i-th node in the input layer to the j-th node in the hidden layer is W ji The weight from the jth node in the hidden layer to the node in the output layer is W j ' should be written.

[0054] Input variable y i is the sensor data and gas station data collected from the vehicle 1. In the example shown in FIG. 6, the position information (vehicle position data) of the vehicle 1B acquired by the navigation system 11 is also input to the input variable y i Included in the output variable Z p is a correction amount of a control command to the engine 3. Machine learning is performed using this correction amount as training data.

[0055] The correction amount can be classified into, for example, a correction amount of a control command to the injection system, a correction amount of a control command to the intake system, and a correction amount of a control command to the EGR system. More specifically, the correction amount of the control command to the injection system is a change amount of the fuel injection amount from the injector 323 from a reference amount, a change amount of the fuel injection timing from the injector 323 from a reference timing, a change amount of the ignition timing of the spark plug 324 from a reference timing, etc. The correction amount of the control command to the intake system is a change amount of the throttle opening from a reference amount, a change amount of the opening of the WGV 262 (or the variable nozzle device 38) from a reference amount, etc. The correction amount of the control command to the EGR system is a change amount of the opening of the EGR valve 372 from a reference amount, etc. These correction amounts are transmitted to the vehicle 1A by the communication module 24 provided in the control center 2.

[0056] In addition to the sensor data and the gas station data, it is desirable to use vehicle position data for training the prediction model. The vehicle position data reflects various information about the driving location of the vehicle 1B (information about the weather, temperature, amount of precipitation, gradient, speed limit, presence or absence of traffic jams, etc.). Therefore, by using the vehicle position data, it becomes possible to build a trained prediction model with higher accuracy.

[0057] Note that the neural network model is merely one example of a method that can be adopted for machine learning of the combustion state of the engine 3, and the machine learning method is not limited to this. The server 23 may use other machine learning models, such as a deep learning model, a logistic regression model, and a support vector machine.

[0058] The server 23 may also analyze the sensor data and the gas station data collected in the control center 2 by a so-called data mining technique for big data. As the data mining technique, for example, the following known techniques can be adopted. The server 23 uses, for example, the fuel injection timing from the injector 323 as an objective variable and other parameters as explanatory variables, and selects multiple explanatory variables to be used for correcting the fuel injection timing by finding the relationship between the explanatory variables, for example, by clustering. Then, in order to predict how the objective variable (fuel injection timing in this example) changes when the selected explanatory variable changes, the server 23 extracts regularities that hold between the explanatory variables and the objective variable. The extracted regularities are expressed as a prediction model or a relational expression of the objective variable (statistical modeling). As an example, when performing a regression analysis (for example, multiple regression analysis) using multiple explanatory variables, the server 23 can calculate the parameters of the prediction model used in the regression analysis by parameter fitting.

[0059] <Improvement of combustion conditions> Fig. 7 is a diagram for explaining an example of a combustion improvement process for correcting the operation of the injection system of the engine 3. In Fig. 7 and Figs. 8 to 10 described later, the horizontal axis represents the crank angle of the engine 3. The vertical axis represents the internal pressure of the cylinders 311 to 314 of the engine 3.

[0060] Depending on the properties of the fuel, the in-cylinder pressure may deviate from the target in-cylinder pressure (target in-cylinder pressure) (see the in-cylinder pressure before correction in the figure). In such a case, for example, the operation of the injection system of the engine 3 can be corrected using a correction amount to bring the in-cylinder pressure closer to the target in-cylinder pressure (see the in-cylinder pressure after correction). FIG. 7 shows an example of retarding the fuel injection timing. In this example, the combustion prediction model can be constructed (model learning) using the intake amount, the exhaust amount (the difference between the target value and the actual value of the exhaust amount), the concentration of unburned components (such as hydrocarbons) and / or nitrogen oxides in the exhaust gas, the ignition timing of the mixture, the combustion sound, etc.

[0061] FIG. 8 is a diagram for explaining another example of the combustion improvement process for correcting the operation of the injection system of the engine 3. When the ignition quality of the fuel supplied to the engine 3 is better or worse than that of a typical fuel, the in-cylinder pressure may deviate from the target in-cylinder pressure. The amount of fuel injected from the injector 323 is adjusted by changing the size (pulse height and pulse width) of the pulse output from the ECU 13 to the injector 323, and the in-cylinder pressure can be brought closer to the target in-cylinder pressure by correcting the size of the pulse using a correction amount. In addition, in the case of multi-injection, it is desirable to correct the amount of fuel injected for the main combustion.

[0062] 9 is a diagram for explaining an example of a combustion improvement process for correcting the operation of the intake system of the engine 3. Another factor that may cause the in-cylinder pressure to deviate from the target in-cylinder pressure is the amount of intake air to the engine 3. In such a case, the in-cylinder pressure can be brought closer to the target in-cylinder pressure by correcting the amount of intake air by adjusting the opening of the throttle valve 332 and / or the WGV 362 (variable nozzle device 38) using the correction amount.

[0063] 10 is a diagram for explaining an example of a combustion improvement process for correcting the operation of the EGR system of the engine 3. The amount of EGR gas can also be a factor in the deviation of the in-cylinder pressure from the target in-cylinder pressure. In such a case, the in-cylinder pressure can be brought closer to the target in-cylinder pressure by correcting the amount of EGR gas by adjusting the opening degree of the EGR valve 372 using a correction amount.

[0064] Although an example of bringing the in-cylinder pressure closer to the target in-cylinder pressure has been described in Figures 7 to 10, the combustion state of engine 3 may be improved using a correction amount so that other parameters (for example, the heat release rate of engine 3) approach target values.

[0065] <Processing flow> 11 is a flowchart showing the procedure of the combustion improvement process in this embodiment. This flowchart is executed when a predetermined condition is satisfied (for example, at a predetermined control period while the engine 3 is operating, such as while the vehicle 1A is traveling). The left side of the figure shows the process executed in the vehicle 1A, and the right side shows the process executed in the control center 2. Each step is realized by software processing by the vehicle 1A (ECU 13) or the control center 2 (server 23), but may also be realized by hardware (electrical circuitry) arranged in the ECU 13 or server 23. Steps are abbreviated as S.

[0066] In this example, the ECU 13 uses a flag to manage the control of transmission of sensor data, vehicle position data, and gas station data to the control center 2. This flag will be referred to as a "data transmission flag."

[0067] In S11, the ECU 13 determines whether or not the vehicle 1A has been refueled. The ECU 13 can determine that refueling has occurred when an increase in fuel in a fuel tank (not shown) is detected by the fuel gauge. If refueling has occurred (YES in S11), the ECU 23 turns on the data transmission flag (S12). Then, the ECU 23 transmits the gas station data to the control center 2 (S13). The gas station data is stored in the travel history database 22. Note that if the vehicle 1A has not been refueled (NO in S11), the processes of S12 and S13 are skipped and the data transmission flag is maintained off.

[0068] In S14, the ECU 13 determines whether the data transmission flag is on. If the data transmission flag is on (YES in S14), the ECU 13 transmits the sensor data and the vehicle position data to the control center 2 (S15). The process shown on the left side of the figure is executed every time a predetermined condition is satisfied (for example, every control period), so the process of S15 is executed repeatedly. That is, the sensor data and the vehicle position data are continuously transmitted until the required amount of data is collected (described later). The sensor data and the vehicle position data are stored in the travel history database 22 in association with the gas station data 13 collected in S13. If the data transmission flag is off (NO in S14), the sensor data and the vehicle position data are not transmitted from the vehicle 1A to the control center 2.

[0069] In S21, the server 23 determines whether or not a necessary amount of data for calculating the correction amount using the combustion prediction model has been collected. When the collection of the necessary data has been completed (YES in S21), the server 23 applies the collected data (sensor data, vehicle position data, and gas station data) to the combustion prediction model to calculate the correction amount (S22). Then, the server 23 transmits the calculated correction amount to the vehicle 1A (S23). Note that if the correction amount is outside a normally expected range, there is a possibility that inappropriate fuel (e.g., non-standard fuel) has been refueled. In this case, the server 23 may transmit a warning to the vehicle 1A instead of or in addition to the correction amount.

[0070] In S16, the ECU 13 determines whether or not a correction amount has been received from the control center 2. When the correction amount has been received (YES in S16), the ECU 13 switches the data transmission flag from ON to OFF. Furthermore, as described with reference to Figs. 7 to 10, the ECU 13 corrects the operation of the injection system, the EGR system, and / or the intake system of the engine 3 using the correction amount (S18). This improves the fuel state of the engine 3.

[0071] As described above, in this embodiment, by using a combustion prediction model that is a prediction model related to the combustion state of fuel, a correction amount for correcting the combustion state of engine 3 of vehicle 1A is calculated from sensor data, vehicle position data, and gas station data of vehicle 1A. The gas station data is data for identifying a gas station, and is not data related to the analysis result of the composition of the fuel that was supplied. According to this embodiment, the combustion state of engine 3 can be appropriately corrected even if fuel composition information is not required. In addition, the occurrence of combustion problems in engine 3 (for example, misfires or abnormal combustion sounds) can also be suppressed.

[0072] The properties of the fuel in the fuel tank may change every time refueling is performed. However, the combustion prediction model is constructed using big data representing the detection results of the combustion states of various fuels collected from a large number of vehicles 1B. Therefore, according to this embodiment, it is possible to appropriately correct the combustion state of the engine 3 for not only a specific fuel but also a wide variety of fuels.

[0073] In addition, the computational processing capacity of an in-vehicle ECU is generally limited. By using the server 23 installed in the control center 2, it is possible to easily ensure high computational processing capacity and reduce the computational load of the ECU 13. In addition, the computational load of the server 23 can be reduced by having the server 23 learn the correction amount.

[0074] The embodiments disclosed herein should be considered to be illustrative and not restrictive in all respects. The scope of the present disclosure is defined by the claims, not by the description of the embodiments described above, and is intended to include all modifications within the meaning and scope of the claims. [Explanation of symbols]

[0075] 100 vehicle management system, 1 (1A, 1B) vehicle, 11 navigation system, 111 GPS receiver, 13 ECU, 131 processor, 132 memory, 133 input / output port, 14 vehicle network, 2 control center, 21 vehicle database, 22 driving history database, 23 server, 231 processor, 232 memory, 233 input / output port, 24 communication module, 25 intranet, 3, 3A engine, 31 engine body, 311 to 314 cylinder, 321 intake valve, 322 exhaust valve, 323 injector, 324 spark plug, 33 intake passage, 331 intercooler, 332 throttle valve, 34 exhaust passage, 341 catalytic converter, 342 aftertreatment device, 35 turbocharger, 351 compressor, 352 turbine, 353 shaft, 36 WGV device, 361 bypass passage, 362 WGV, 363 WGV actuator, 37 EGR device, 371 EGR passage, 372 EGR valve, 373 EGR cooler, 38 variable noise device, 4 sensors, 401 vehicle speed sensor, 402 accelerator opening sensor, 403 engine speed sensor, 404 knock sensor, 405 air flow meter, 406 throttle opening sensor, 407 cylinder pressure sensor, 408 coolant temperature sensor, 409 boost pressure sensor, 410 boost temperature sensor, 411 turbine speed sensor, 412 exhaust temperature sensor, 413 air-fuel ratio sensor, 414 sensor, 415 differential pressure sensor.

Claims

1. The target vehicle, a server configured to communicate with the target vehicle and a plurality of vehicles; each of the target vehicle and the plurality of vehicles includes at least one sensor that detects a fuel combustion state in an engine including an injection system, an intake system, and an EGR (Exhaust Gas Recirculation) system; The server, A memory in which a learned model relating to engine control is stored; A processor that executes a calculation process using the trained model, In the trained model, a correction amount for correcting the combustion state of fuel in the engine is learned based on sensor data indicating the detection result of the at least one sensor of each of the plurality of vehicles and gas station data indicating the installation location of a gas station from which each of the plurality of vehicles receives fuel but not indicating the composition of the fuel supplied at the gas station, the sensor data includes at least data related to an in-cylinder pressure or a heat release rate of the engine; The correction amount is a first correction amount of a control command to the injection system, which is related to the amount or timing of fuel injection from the injector or the ignition timing of the spark plug; a second correction amount of a control command to the intake system, which is related to a throttle opening, a wastegate valve opening, or a variable nozzle device opening; a third correction amount of a control command to the EGR system regarding an EGR valve opening degree, The processor calculates the correction amount by providing the sensor data and the gas station data of the target vehicle to the trained model, and transmits the calculated correction amount to the target vehicle; The target vehicle corrects the fuel combustion state in the engine of the target vehicle using the received correction amount.

2. The vehicle management system of claim 1 , wherein the gas station data further includes data regarding the timing of refueling at the gas station.

3. In the trained model, the correction amount is trained based on the sensor data, the gas station data, and data related to the traveling positions of the plurality of vehicles, The vehicle management system of claim 1 , wherein the processor calculates the correction amount for the target vehicle by providing the learned model with data regarding the driving position of the target vehicle in addition to the sensor data and the gas station data.

4. A vehicle management system as described in any one of claims 1 to 3, wherein the sensor data further includes, in addition to data regarding the engine's in-cylinder pressure or heat release rate, data regarding at least one of the following: the engine rotation speed, the temperature of the exhaust gas from the engine, the pressure difference before and after a filter that collects particulate matter in the exhaust gas, and the nitrogen oxide concentration in the exhaust gas.

5. A vehicle configured to be able to communicate with a server including a trained model for engine control, In the trained model, a correction amount for correcting a fuel combustion state in the engine is learned based on sensor data and gas station data collected through communication with a plurality of vehicles each equipped with an engine including an injection system, an intake system, and an EGR system, the sensor data is data indicating a detection result of a fuel combustion state in the engine of each of the plurality of vehicles, and includes at least data related to an in-cylinder pressure or a heat release rate of the engine; The gas station data indicates locations of gas stations from which the plurality of vehicles receive fuel, but does not indicate the composition of fuel supplied at the gas stations; The correction amount is a first correction amount of a control command to the injection system, which is related to the amount or timing of fuel injection from the injector or the ignition timing of the spark plug; a second correction amount of a control command to the intake system, which is related to a throttle opening, a wastegate valve opening, or a variable nozzle device opening; a third correction amount of a control command to the EGR system regarding an EGR valve opening degree, The vehicle is A communicator that transmits the sensor data and the gas station data of the vehicle to the server and receives the correction amount calculated by the server providing the sensor data and the gas station data from the vehicle to the trained model; a control device that corrects a fuel combustion state in the engine of the vehicle using the received correction amount.

6. The vehicle described in claim 5, wherein the sensor data further includes, in addition to data regarding the engine's in-cylinder pressure or heat release rate, data regarding at least one of the engine's rotational speed, the temperature of the exhaust gas from the engine, the pressure difference before and after a filter that captures particulate matter in the exhaust gas, and the nitrogen oxide concentration in the exhaust gas.

7. A vehicle driving management method for managing vehicle driving using a trained model related to engine control, comprising: In the trained model, a correction amount for correcting a fuel combustion state in the engine is learned based on sensor data and gas station data collected through communication with a plurality of vehicles each equipped with an engine including an injection system, an intake system, and an EGR system, the sensor data is data indicating a detection result of a fuel combustion state in the engine of each of the plurality of vehicles, and includes at least data related to an in-cylinder pressure or a heat release rate of the engine; The gas station data indicates locations of gas stations from which the plurality of vehicles receive fuel, but does not indicate the composition of fuel supplied at the gas stations; The correction amount is a first correction amount of a control command to the injection system, which is related to the amount or timing of fuel injection from the injector or the ignition timing of the spark plug; a second correction amount of a control command to the intake system, which is related to a throttle opening, a wastegate valve opening, or a variable nozzle device opening; a third correction amount of a control command to the EGR system regarding an EGR valve opening degree, The traveling management method includes: A step of calculating the correction amount for correcting the combustion state of fuel in the engine of the target vehicle by providing the sensor data and the gas station data from the target vehicle to the trained model; and correcting a fuel combustion state in the engine of the target vehicle using the correction amount.

8. The vehicle driving management method described in claim 7, wherein the sensor data further includes, in addition to data regarding the engine's in-cylinder pressure or heat generation rate, data regarding at least one of the engine rotation speed, the temperature of the exhaust gas from the engine, the pressure difference before and after a filter that collects particulate matter in the exhaust gas, and the nitrogen oxide concentration in the exhaust gas.

Images