Exhaust detection system and exhaust detection method

Abstract

This exhaust detection system comprises: a specific sensor that detects a part of an exhaust component of an internal combustion engine; a simulated sensor that estimates the part of the exhaust component as estimated exhaust information; a processing unit that calculates actual exhaust information of an own vehicle under a predetermined driving condition by using the specific sensor, and calculates index information related to deterioration of a catalyst by using driving state information of the own vehicle; and a determination unit that determines the validity of the actual exhaust information of the own vehicle by collating database information in which the index information and the actual exhaust information derived from a vehicle of the same type as the own vehicle are stored in association with each other, and the calculated actual exhaust information and the calculated index information of the own vehicle with the actual exhaust information and the index information of the database information, the processing unit correcting the estimated exhaust information on the basis of the actual exhaust information when it is determined that the actual exhaust information of the own vehicle is valid.

Description

Exhaust Detection System and Exhaust Detection Method

[0001] The present invention relates to an exhaust detection system and an exhaust detection method.

[0002] As an OBM (On-Board Monitoring) measure for monitoring exhaust during vehicle use, when configuring a nitrogen oxide (NOx) monitoring system that combines a NOx sensor and a virtual sensor, the virtual sensor requires a NOx calculation function that can cope with environmental changes and aging changes. The virtual sensor is used for the purpose of monitoring NOx before the NOx sensor becomes active using sensors other than the NOx sensor, or diagnosing the failure of the NOx sensor.

[0003] As a countermeasure against environmental changes and aging changes of the NOx sensor, for example, the virtual sensor needs to be able to handle catalyst deterioration and fuel properties. In order for the virtual sensor to handle calculations related to these changes, inputs of various factors related to the changes are required. However, in order to ensure a certain level of accuracy in the virtual sensor, a huge amount of causal relationship analysis is necessary, and it is difficult to configure the virtual sensor to accurately reproduce these causal relationships.

[0004] Also, as a countermeasure against environmental changes and aging changes, it is desired to correct the NOx estimated value of the virtual sensor based on the NOx sensor value detected by the NOx sensor. However, when the NOx sensor is not in good condition, there is a possibility that the NOx sensor value contains an excessive NOx sensor error.

[0005] For example, for the purpose of diagnosing system defects, a configuration is disclosed in which a state indicator related to a failure is compared with a reference value detected from statistical characteristic values in a plurality of other systems (see, for example, Patent Document 1).

[0006] Japanese Patent Application Laid-Open No. 2023-155219

[0007] However, the technology described in Patent Document 1 is a technology related to system fault diagnosis and does not address the exhaust monitoring function in OBM or the correction technology for related virtual sensors. For example, if a sensor error is included in the actual exhaust information calculated using a specific sensor, such as when a specific sensor is not functioning properly, the output value of the virtual sensor cannot be correctly corrected.

[0008] Given the above situation, there was a need for a method that ensures the validity of the actual exhaust information of the vehicle itself, while correcting the estimated exhaust information from a simulated sensor.

[0009] To solve the above problems, one aspect of the present invention provides an exhaust detection system comprising: a specific sensor that detects a portion of the exhaust components downstream of a catalyst disposed in the exhaust passage of the internal combustion engine of the vehicle; and a simulated sensor that estimates at least a portion of the exhaust components as estimated exhaust information. This exhaust detection system comprises: a processing unit that uses the specific sensor to calculate the actual exhaust information of the vehicle under predetermined operating conditions and uses the vehicle's operating state information to calculate index information related to catalyst deterioration; a data storage unit that stores database information by associating index information and actual exhaust information originating from vehicles of the same type as the vehicle; and a determination unit that compares the calculated actual exhaust information and index information of the vehicle with the exhaust information and index information in the database to determine the validity of the actual exhaust information of the vehicle. If the processing unit determines that the actual exhaust information of the vehicle is valid, it corrects the estimated exhaust information using the actual exhaust information of the vehicle.

[0010] According to at least one aspect of the present invention, actual exhaust information obtained from a specific sensor is compared with database information and then used to correct estimated exhaust information. This embodiment ensures the validity of the vehicle's actual exhaust information while simultaneously correcting the estimated exhaust information from a simulated sensor. Other issues, configurations, and effects will be clarified by the following description of embodiments for carrying out the invention.

[0011] This is a schematic diagram showing an example of the overall system configuration including the exhaust detection device according to the first embodiment of the present invention. This is a schematic diagram showing an example of the engine configuration according to the first embodiment of the present invention. This is a block diagram showing an example of the hardware configuration of the exhaust detection device (processing unit) according to the first embodiment of the present invention. This is a block diagram showing an example of the functional configuration of the exhaust detection device (processing unit) according to the first embodiment of the present invention. This is a diagram showing an example of a machine learning model used in the estimated exhaust information calculation unit according to the first embodiment of the present invention. This is a flowchart showing an example of the processing of the exhaust detection device according to the first embodiment of the present invention. This is a conceptual diagram showing an example of actual exhaust information and estimated exhaust information calculated by the exhaust detection device when the vehicle is new. This is a conceptual diagram showing an example of actual exhaust information and estimated exhaust information calculated by the exhaust detection device when the catalyst deteriorates. This is a conceptual diagram showing an example of estimated exhaust information correction by the exhaust detection device when the catalyst deteriorates. This is a conceptual diagram showing an example of estimated exhaust information correction by the exhaust detection device when the catalyst deteriorates and when a specific sensor deteriorates. This is a graph showing an example of the relationship between actual exhaust-related index information and the actual exhaust information increase coefficient. This is a block diagram showing an example of the functional configuration of the exhaust detection device (processing unit) according to the second embodiment of the present invention. This is a flowchart showing an example of the processing of the exhaust detection device according to the second embodiment of the present invention. This is a block diagram showing an example of the functional configuration of the exhaust detection device (processing unit) according to the third embodiment of the present invention. This is a flowchart showing an example of processing by an exhaust detection device according to a third embodiment of the present invention. This is a block diagram showing an example of the hardware configuration of a computer provided by a cloud server and a driver terminal device.

[0012] Hereinafter, examples of embodiments for carrying out the present invention (hereinafter referred to as "embodiments") will be described with reference to the accompanying drawings. In this specification and the accompanying drawings, common or similar components are assigned the same reference numeral, and redundant descriptions are omitted. Furthermore, if there are multiple identical or similar components, different subscripts may be assigned to the same reference numeral in the description. However, if it is not necessary to distinguish between these multiple components, the subscript may be omitted in the description. Unless otherwise specified, the number of each component may be singular or plural.

[0013] <First Embodiment> First, an exhaust gas detection device according to the first embodiment of the present invention will be described with reference to Figures 1 to 11.

[0014] [System Configuration Including Exhaust Detection Device] Figure 1 is a schematic diagram showing an example of the overall system configuration including an exhaust detection device according to the first embodiment of the present invention. The vehicle 1000 shown in Figure 1 is equipped with an exhaust detection device 110 that detects the exhaust information of the automobile. The exhaust detection device 110 can be, for example, a microcontroller such as an electronic control unit (ECU). The exhaust detection device 110 comprises a processing unit 120, a data storage unit 130 inside the processing unit 120, and a communication IF 140.

[0015] The processing unit 120 performs exhaust detection based on data acquired from sensors 150, actuators 160, and other ECUs (not shown) while the vehicle 1000 is running or stopped. The processing unit 120 then transmits the exhaust detection result to the cloud server 200 via the communication interface 140. Note that the processing unit 120 may communicate with the cloud server 200 via a terminal unit 210 or a driver terminal device 400 (described later), rather than communicating directly between the communication interface 140 and the cloud server 200, as shown in Figure 1. The terminal unit 210 is a small diagnostic device used in a repair shop.

[0016] Vehicle 1000 is equipped with multiple ECUs, including an ECU for engine control (not shown) and an ECU for advanced driver assistance systems (ADAS ECU).

[0017] The communication IF 140 is comprised of a communication device that controls communication between the cloud server 200 or other devices via a wide-area network such as the Internet. The communication IF 140 is also configured to communicate with other ECUs (not shown) via an in-vehicle network (not shown) within the vehicle. The communication IF 140 is equipped with well-known wireless communication means such as a wireless LAN (Local Area Network) to perform wireless bidirectional communication with the cloud server 200. The communication IF 140 is also equipped with well-known wired communication means such as a CAN (Controller Area Network) to perform CAN bidirectional communication with ECUs and sensors within the vehicle. In other words, the communication IF 140 has the function of transmitting information received from the processing unit 120 to the cloud server 200 and transmitting information received from the cloud server 200 to the processing unit 120.

[0018] The MIL (Malfunction Indicator Lamp) 170 is a malfunction warning light located on the instrument panel and is an example of the driver terminal device 400 (driver interface unit) shown in Figure 4, which will be described later.

[0019] [Engine Configuration] Figure 2 is a schematic diagram showing an example of the configuration of an engine according to the first embodiment of the present invention. The engine 100 shown in Figure 2 is an example of an internal combustion engine. The combustion chamber of the engine 100 is formed by the engine head, cylinder 5, piston 10, intake valve 7, and exhaust valve 8. A spark plug 6 is also installed in the engine head. Air taken in from outside the engine 100 passes through the compressor 2, intercooler 3, throttle valve 4, and intake port 20, and when the intake valve 7 opens, it is taken into the combustion chamber. Fuel is injected by a fuel injection valve 9 provided in the intake port 20, and when the intake valve 7 opens, it is taken into the combustion chamber together with the air taken in from outside. Then, in the combustion chamber, a discharge occurs between the electrodes of the discharge gap of the spark plug 6 at a predetermined combustion timing, and the mixture of air and fuel burns. The mixture after combustion in the combustion chamber is exhausted as exhaust gas when the exhaust valve 8 opens.

[0020] This exhaust gas is discharged to the outside of the engine 100 through the exhaust port 21, turbine 14, and catalyst 15. The engine 100 is equipped with an intake flow sensor 1 for measuring the amount of air taken into the combustion chamber, a throttle sensor 19 for detecting the opening degree of the throttle valve 4, a water temperature sensor 12 for measuring the temperature of the coolant, an upstream air-fuel ratio (LAF) sensor 16, a downstream O2 sensor 17, and a NOx sensor 18.

[0021] Furthermore, a signal rotor 13 is provided on the shaft portion of the crankshaft 22. A crank angle sensor 11 positioned on the signal rotor 13 detects the signal from the signal rotor 13. The crank angle sensor 11 detects the time difference Δt between adjacent signal teeth 13a passing through the detection section of the crank angle sensor 11. The crank angle sensor 11 then calculates the crank rotation speed ω = Δθ / Δt (rad / s). Based on this rotation speed calculation principle, the crank angle sensor 11 calculates the crank rotation speed for each rotation angle Δθ.

[0022] [Hardware Configuration of Exhaust Detection Device (Arithmetic Processing Unit)] Figure 3 is a block diagram showing an example of the hardware configuration of the exhaust detection device 110 (arithmetic processing unit 120). As shown in Figure 3, the arithmetic processing unit 120 includes an input circuit 191, an A / D conversion unit 192, a central processing unit CPU (Central Processing Unit) 193, a ROM (Read Only Memory) 194, a RAM (Random Access Memory) 195, and an output circuit 196. For example, the exhaust detection device 110 is configured using an arithmetic processing unit 120 that includes an input circuit 191, an A / D conversion unit 192, a CPU 193, a ROM 194, a RAM 195, and an output circuit 196.

[0023] The CPU 193 loads a program stored in ROM 194 (an example of a memory unit) into RAM 195 and executes it, thereby realizing each function according to the embodiment of the present invention. The CPU 193 is an example of a processing unit. Alternatively, a processing unit such as an MPU (Micro-Processing Unit) may be used instead of the CPU 193. Furthermore, in this embodiment, a non-volatile memory such as an EEPROM (Electrically Erasable and Programmable Read Only Memory) whose contents can be rewritten may be used as ROM 194. For example, a program containing algorithms for realizing each function according to the embodiment of the present invention may be stored in ROM 194.

[0024] The input circuit 191 takes in the signals output from the sensors 150 as input signals 190. The sensors 150 include, for example, the intake air flow sensor 1, throttle sensor 19, water temperature sensor 12, crank angle sensor 11, air-fuel ratio sensor 16, O2 sensor 17, and NOx sensor 18. In addition to these sensors, the sensors 150 may also include, although not shown, an intake cam angle sensor or exhaust cam angle sensor for a variable valve timing mechanism, a knock sensor for detecting engine knocking, an in-cylinder pressure sensor for detecting combustion chamber pressure, an outside air temperature sensor for measuring the outside air temperature, an exhaust temperature sensor for measuring the exhaust temperature, etc. When the input signal 190 is an analog signal, the input circuit 191 removes noise components from the input signal 190 and outputs the noise-removed signal to the A / D conversion unit 192.

[0025] The A / D conversion unit 192 converts the analog signal into a digital signal and outputs it to the CPU 193. The CPU 193 receives the digital signal output from the A / D conversion unit 192 and executes control logic (programs) stored in a storage medium such as ROM 194, thereby performing a wide variety of calculations, diagnoses, and controls.

[0026] The calculation results from the CPU 193 and the conversion results from the A / D conversion unit 192 are temporarily stored in the RAM 195.

[0027] The calculation results from the CPU 193 are output as a control signal 197 from the output circuit 196 and used to control the actuators 160 that are to be controlled. Examples of controlled objects include intake valve drive units, exhaust valve drive units, fuel injection units, spark plugs, steering units, brake units, power conversion circuits, etc.

[0028] If the input signal 190 is a digital signal, the input signal 190 is sent from the input circuit 191 to the CPU 193 via a signal line 198 that bypasses the A / D conversion unit 192, and the CPU 193 performs the necessary calculations and control.

[0029] If the input signal 190 is a digital signal, the input signal 190 may be transmitted to the CPU 193 via the communication IF 140. In this case, the digital input signal 190 output from the sensors 150 is sent to the CPU 193 via communication through the communication IF 140, and the CPU 193 performs the necessary calculations and control.

[0030] The arithmetic processing unit 120 includes a communication circuit (not shown) which communicates with the communication interface 140 via a CAN or the like. The communication circuit of the arithmetic processing unit 120 has the function of transmitting information such as the calculation results of the CPU 193 to the communication interface 140, and transmitting information received from the communication interface 140 to the CPU 193.

[0031] [Functional Configuration of Exhaust Detection Device (Calculation Processing Unit)] Next, the functional configuration of the exhaust detection device 110 (calculation processing unit 120) according to the first embodiment of the present invention will be described with reference to Figure 4. Figure 4 is a block diagram showing an example of the functional configuration of the exhaust detection device 110. In Figure 4, the input circuit 191, output circuit 196, and communication IF 140 (see Figures 1 and 3), which perform communication processing between the exhaust detection device 110 and other devices (sensors, ECU, server, etc.), are omitted from the description.

[0032] The exhaust detection device 110 includes a data acquisition unit 300, an actual exhaust information calculation unit 310, an actual exhaust-related indicator information calculation unit 320, a predetermined operating condition determination unit 330, an actual exhaust information increase coefficient calculation unit 350, an actual exhaust information validity determination unit 360, an estimated exhaust information correction amount calculation unit 370, an estimated exhaust information calculation unit 380, and a sensor fault diagnosis unit 390.

[0033] The data acquisition unit 300 acquires data from sensors 150 inside the vehicle and from multiple ECUs that control the vehicle 1000 while the vehicle 1000 is in motion or stopped. The data obtained from the ECUs includes sensor output values ​​based on input signals 190 transmitted to the CPU 193 and control parameters calculated by the CPU 193 when performing control operations. This data is periodically collected by the exhaust detection device 110 and stored in the exhaust detection device 110's storage (not shown).

[0034] The actual exhaust information calculation unit 310 calculates actual exhaust information using multiple data acquired by the data acquisition unit 300. Actual exhaust information is exhaust information calculated using output information from a sensor capable of directly detecting exhaust, i.e., a specific sensor. For example, actual exhaust information is the concentration or amount of components contained in the exhaust gas, such as nitrogen oxides (NOx), particulate matter (PN), and ammonia. As actual exhaust information, oxygen (O ２ Examples include hydrocarbons (HC) or carbon monoxide (CO). In this embodiment, a NOx sensor 18 is provided as a specific sensor.

[0035] The actual exhaust-related indicator information calculation unit 320 calculates actual exhaust-related indicator information using multiple data acquired by the data acquisition unit 300. The actual exhaust-related indicator information calculation unit 320 outputs the actual exhaust-related indicator information to the actual exhaust information validity determination unit 360. The actual exhaust-related indicator information is information about indicators related to catalyst degradation. Examples of actual exhaust-related indicator information include catalyst usage time information, catalyst thermal history information, catalyst aging degradation information, engine cumulative operating time information, and vehicle cumulative mileage information.

[0036] The catalyst usage time information is the usage time since the catalyst 15 was put into use (from its new condition). For example, as catalyst usage time information, the cumulative value of the time that exhaust gas has been flowing through the exhaust purification section of the catalyst 15 since the catalyst 15 was installed in the vehicle in its new condition can be used.

[0037] The thermal history information of the catalyst can be, for example, the cumulative value of the time during which the temperature of the catalyst 15 was above a predetermined temperature (e.g., 500°C) out of the cumulative usage time of the catalyst 15 from its new state. The catalyst temperature can be an estimated value obtained from a physical model, mathematical model, or machine learning model, or the catalyst temperature directly measured by a catalyst temperature sensor.

[0038] The information regarding the aging degradation of a catalyst refers to the time elapsed since the catalyst was first put into use. For example, the start time of aging degradation might be the time when the car was produced at the factory.

[0039] The cumulative operating time information for the engine is the time the engine 100 has been in use since it was new. For example, as the cumulative operating time information for the engine, it is possible to determine whether the engine is running based on information from the crank angle sensor, cylinder pressure sensor, air-fuel ratio sensor, etc., from the time the engine was determined to be running since the engine 100 was installed in the vehicle in a new condition, and then use the cumulative value of the time the engine was determined to be running.

[0040] The vehicle's cumulative mileage information is the total distance traveled from the vehicle's new condition (new car condition), as indicated by the odometer (range measuring meter). For example, the vehicle's cumulative mileage can be obtained by calculating the vehicle's mileage from the output of the vehicle speed sensor and accumulating the total distance. In the case of hybrid vehicles that can run even when the engine is stopped, the cumulative value of the mileage traveled during the period when the engine was running can be used. The above-mentioned actual exhaust-related indicator information is reset to zero if the catalytic converter 15 is replaced with a new one during the vehicle's use.

[0041] The predetermined operating condition determination unit 330 uses multiple data acquired by the data acquisition unit 300 to determine whether the operating state of the vehicle 1000 conforms to predetermined operating conditions. The predetermined operating conditions refer to conditions in which the operation of the engine 100 is stable, such as whether the rotational speed and torque of the engine 100 are within a predetermined range (idling, power generation mode in a hybrid vehicle, etc.) or whether the speed of the vehicle 1000 is stable (high-speed constant driving). If the predetermined operating condition determination unit 330 determines that the predetermined operating conditions are met, the calculation processing unit 120 executes the calculation and determination processing of the actual exhaust information increase coefficient calculation unit 350, the actual exhaust information validity determination unit 360, and the estimated exhaust information correction amount calculation unit 370 within the predetermined operating condition time 340 shown by the dashed line in Figure 4.

[0042] The actual exhaust information increase coefficient calculation unit 350 calculates the actual exhaust information increase coefficient using the calculation result of the actual exhaust information calculation unit 310 under predetermined operating conditions and reference exhaust information, such as exhaust information equivalent to that of a new vehicle. The actual exhaust information increase coefficient calculation unit 350 outputs the calculated actual exhaust information increase coefficient to the actual exhaust information validity determination unit 360 and the estimated exhaust information correction amount calculation unit 370.

[0043] The actual exhaust information increase coefficient is, for example, the ratio of the actual exhaust information of the vehicle detected by a specific sensor (NOx sensor 18) to the reference exhaust information under the same predetermined operating conditions. As an example, under the same predetermined operating conditions, if the ratio of the actual exhaust information of the vehicle input from the actual exhaust information calculation unit 310 to the reference exhaust information is taken and the actual exhaust information increase coefficient of the vehicle exceeds 1, it can be read that the actual exhaust information of the vehicle has increased compared to when it was new. Alternatively, the increase rate of the actual exhaust information may be used instead of the actual exhaust information increase coefficient. The increase rate of the actual exhaust information is an index expressed as a percentage of how much the actual exhaust information of the vehicle detected by the specific sensor has increased from the reference exhaust information.

[0044] The actual exhaust information validity determination unit 360 determines whether the actual exhaust information increase coefficient is appropriate by using the database information that associates and stores the actual exhaust-related index information and the actual exhaust information increase coefficient, the calculation result of the actual exhaust-related index information calculation unit 320, and the calculation result of the actual exhaust information increase coefficient calculation unit 350. In the data storage unit 130 (for example, ROM 194), the actual exhaust-related index information obtained in advance by an acceleration durability test or the like and the actual exhaust information increase coefficient corresponding to the actual exhaust-related index information are stored as database information. In the present embodiment, the data storage unit 130 is disposed inside the arithmetic processing unit 120, but it is not limited thereto, and the data storage unit 130 may be configured by a storage device (not shown) disposed at an appropriate location in the vehicle.

[0045] Thus, when the database information is saved and aggregated in the data storage unit 130 of the host vehicle, the validity of the actual exhaust information of the host vehicle can be determined based on the database information that can be referred to within the host vehicle. For example, it can operate even when the host vehicle is newly released and thus database information derived from other vehicles cannot be obtained, or when the vehicle exists in an area where it is difficult to establish communication with the outside of the vehicle, that is, so-called stand-alone operation is possible.

[0046] The actual exhaust information validity determination unit 360 determines the validity of the actual exhaust information increase coefficient of the host vehicle by comparing the actual exhaust-related index information of the host vehicle calculated by the actual exhaust-related index information calculation unit 320 with the actual exhaust information increase coefficient of the host vehicle calculated by the actual exhaust information increase coefficient calculation unit 350 against the database information in the data storage unit 130. Here, based on the database information in the data storage unit 130, the actual exhaust information validity determination unit 360 calculates the standard range (the upper limit value and the lower limit value of the actual exhaust information increase coefficient) of the exhaust information in the database information corresponding to the actual exhaust-related index information of the host vehicle, and compares this standard range of the exhaust information in the database information with the actual exhaust information increase coefficient of the host vehicle. When the actual exhaust information increase coefficient of the host vehicle is within the standard range of the database information, the actual exhaust information validity determination unit 360 determines that the actual exhaust information increase coefficient of the host vehicle is valid. The standard range of the database information will be described in detail with reference to FIG. 11, which will be described later. The actual exhaust information validity determination unit 360 outputs the result of the validity determination to the estimated exhaust information correction amount calculation unit 370.

[0047] In addition, the data storage unit 130 may further store the actual exhaust-related index information calculated by the actual exhaust-related index information calculation unit 320 and the actual exhaust information increase coefficient (the change amount of the actual exhaust information) calculated by the actual exhaust information increase coefficient calculation unit 350 in an updatable manner. Further, instead of the actual exhaust-related index information and the actual exhaust information increase coefficient obtained by an acceleration durability test or the like, the data storage unit 130 may store database information in which the actual exhaust-related index information and the actual exhaust information increase coefficient of a plurality of vehicles including other vehicles are accumulated. In this way, the data storage unit 130 stores database information about vehicles of the same type as the host vehicle, including the host vehicle itself or at least a plurality of vehicles including other vehicles.

[0048] For example, by communicating with the cloud server 200 via the communication IF 140, data exchange can be performed between the database information of the cloud server 200 and the database information within the vehicle. For instance, new database information can be obtained from the cloud server 200 via the communication IF 140, or conversely, database information from the vehicle's data storage unit 130 can be provided to the cloud server. This enriches the database information and improves the objectivity of judging the validity of the actual exhaust information increase coefficient.

[0049] The estimated exhaust information correction amount calculation unit 370 calculates an estimated exhaust information correction amount to correct the estimated exhaust information when the actual exhaust information validity determination unit 360 determines that the actual exhaust information increase coefficient of the vehicle is valid. The estimated exhaust information correction amount may be determined, for example, using the actual exhaust information increase coefficient of the vehicle calculated by the actual exhaust information increase coefficient calculation unit 350. For example, if the actual exhaust information increase coefficient of the vehicle determined to be valid by the actual exhaust information validity determination unit 360 is 1.2, the estimated exhaust information correction amount is set to 1.2.

[0050] The estimated exhaust information calculation unit 380 is a virtual sensor (simulated sensor) composed of a physical model, mathematical model, or machine learning model. The estimated exhaust information calculation unit 380 calculates estimated exhaust information using multiple data acquired by the data acquisition unit 300, excluding specific sensor information (NOx sensor 18 information) that directly detects actual exhaust information, and an estimated exhaust information correction amount calculated by the estimated exhaust information correction amount calculation unit 370. The estimated exhaust information calculation unit 380 is an example of a virtual sensor (simulated sensor). The estimated exhaust information correction amount corrects the model parameters of the physical model, mathematical model, or machine learning model that constitutes the estimated exhaust information calculation unit 380, or is incorporated into the calculation result of the estimated exhaust information (calculation result of the physical model, mathematical model, or machine learning model). The estimated exhaust information correction amount is the last updated value applied until the next update.

[0051] Here, correction was performed during the internal calculation process (calculating the estimated exhaust information correction amount), but the output value (estimated value) of the estimated exhaust information calculation unit 380 may also be corrected directly. That is, the correction of the estimated exhaust information estimated using the estimated exhaust information calculation unit 380 (simulated sensor) is performed by correcting the parameters of the physical model, mathematical model, or machine learning model that constitutes the estimated exhaust information calculation unit 380, or by correcting the output value of the estimated exhaust information calculation unit 380.

[0052] The sensor fault diagnosis unit 390 (an example of a specific sensor fault diagnosis unit) uses the actual exhaust information of the vehicle, which is the result of calculation by the actual exhaust information calculation unit 310, the standard range of the actual exhaust information in the database information mentioned above, which is one of the results of calculation by the actual exhaust information validity determination unit 360, and the estimated exhaust information, which is the result of calculation by the estimated exhaust information calculation unit 380, to diagnose whether or not a specific sensor that directly detects the actual exhaust information of the vehicle is faulty. The sensor fault diagnosis unit 390 then transmits the determination result (fault diagnosis result) regarding whether or not the specific sensor is faulty to the driver terminal device 400.

[0053] For example, if the actual exhaust information validity determination unit 360 determines that the vehicle's actual exhaust information increase coefficient is not valid when compared with the standard range of the database information, the sensor fault diagnosis unit 390 calculates the amount of deviation of the vehicle's actual exhaust information from the standard range of the database information. If the amount of deviation exceeds a preset threshold, it diagnoses that a specific sensor is faulty. If the actual exhaust information validity determination unit 360 diagnoses that a specific sensor is faulty, the fault information (fault code) corresponding to the faulty specific sensor is recorded in the data storage unit 130.

[0054] Furthermore, if fault information is recorded in the data storage unit 130, the update of the estimated exhaust information correction amount in the estimated exhaust information correction amount calculation unit 370 is stopped. In other words, the catalyst degradation correction amount retains the value of the estimated exhaust information correction amount before the specific sensor fault information was recorded in the data storage unit 130. To put it another way, the update of the estimated exhaust information correction amount remains stopped until the fault determination of the specific sensor in the sensor fault diagnosis unit 390 is resolved and the fault information in the data storage unit 130 is reset to normal.

[0055] The sensor fault diagnosis unit 390 illuminates a fault warning light (MIL 170) located on the instrument panel if any fault information is recorded in the data storage unit 130. The driver terminal device 400 receives the fault information recorded in the data storage unit 130 from the sensor fault diagnosis unit 390 and manages the sensor fault status of its own vehicle. The driver terminal device 400 also transmits the fault information to the cloud server 200. The cloud server 200 receives the fault information from the driver terminal device 400 and manages the fault status of each vehicle.

[0056] Vehicle 1000 (see Figure 1) is a so-called connected vehicle, configured to communicate wirelessly with a cloud server 200. Vehicle 1000 transmits information it possesses to the cloud server 200 at predetermined intervals (for example, every few seconds).

[0057] The information transmitted by each vehicle 1000 to the cloud server 200 includes, in addition to the actual exhaust-related indicator information, actual exhaust information increase coefficient, and fault information related to the database information mentioned above, various information concerning the vehicle 1000's driving, environment, and control. For example, information concerning the vehicle's driving, environment, and control includes the vehicle's current position such as latitude and longitude, accelerator pedal operation amount, brake pedal operation amount, driving load (driving power, etc.), ambient temperature (atmospheric temperature), cumulative engine operating time information, cumulative vehicle mileage, and cranking failure rate. The cranking failure rate is the ratio of the number of times the engine 100 did not start to the number of times the engine 100 was cranked.

[0058] The cloud server 200 stores information received from multiple vehicles 1000, including its own vehicle and other vehicles, along with the time of receipt of that information, stratified for each vehicle 1000. The cloud server 200 is also configured to transmit data requested by each vehicle 1000 in response to requests from that vehicle 1000.

[0059] [Machine Learning Model] Figure 5 shows an example of a machine learning model used in the estimated exhaust information calculation unit 380. The estimated exhaust information calculation unit 380 calculates estimated exhaust information based on multiple data obtained by the data acquisition unit 300, excluding specific sensor information (NOx sensor 18 information) that directly detects actual exhaust information, namely control parameters and other sensor information. Control parameters are parameters related to exhaust information, such as fuel injection amount and torque. Other sensor information is sensor information related to exhaust information, such as engine rotation speed, exhaust temperature, and water temperature. When calculating estimated exhaust information, specific sensor information that can directly detect actual exhaust information is not used. A physical model, mathematical model, or machine learning model can be used to calculate estimated exhaust information.

[0060] A neural network model, an example of a mathematical or machine learning model, is a mathematical model that mimics the structure of the human brain's neural circuits. Each neuron in the model has weights and biases assigned to it. Furthermore, each neuron has a defined activation function, such as the logistic function or ramp function, which are used as appropriate. Multiple neurons form a single layer, with hidden layers between the input and output layers. By increasing the number of neurons and hidden layers, more complex input-output relationships can be approximated. There is a trade-off between approximation accuracy and model size, and a balance point that satisfies both requirements is selected. By setting parameters related to exhaust information (engine speed, torque, ignition timing, exhaust air-fuel ratio, etc.) in the input layer and actual exhaust information in the output layer, and using machine learning (supervised) to assign weights and biases to each neuron, the input-output relationship can be approximated.

[0061] As described above, in this embodiment, the estimated exhaust information calculation unit 380 of the arithmetic processing unit 120 includes a neural network model. The neural network model has parameters related to exhaust information in the input layer and estimated exhaust information set in each unit of the output layer.

[0062] [Processing of Exhaust Detection Device] Next, the processing of the exhaust detection device 110 according to the first embodiment of the present invention will be described with reference to Figure 6. Figure 6 is a flowchart showing an example of the processing of the exhaust detection device 110. First, the actual exhaust information calculation unit 310 of the exhaust detection device 110 calculates the actual exhaust information using the data from a specific sensor that directly detects the actual exhaust information acquired by the data acquisition unit 300 (step S1).

[0063] Next, the actual exhaust-related indicator information calculation unit 320 calculates actual exhaust-related indicator information using the acquired data (step S2). The actual exhaust-related indicator information includes, for example, the thermal history information of the catalyst, the aging degradation information of the catalyst, the cumulative operating time information of the engine, or the cumulative mileage of the vehicle.

[0064] Next, the predetermined driving condition determination unit 330 performs a process to determine whether or not the vehicle's driving conditions are within the predetermined driving conditions (step S3).

[0065] Then, the predetermined operating condition determination unit 330 determines whether the vehicle's operating conditions are within the predetermined operating conditions based on the result of executing the process in step S3 (step S4). If the vehicle's operating conditions are within the predetermined operating conditions (YES determination), proceed to step S5. If the vehicle's operating conditions are not within the predetermined operating conditions (NO determination), proceed to step S9.

[0066] If the determination in step S4 is YES, the actual exhaust information increase coefficient calculation unit 350 calculates the actual exhaust information increase coefficient from the actual exhaust information under the current predetermined operating conditions of the vehicle and the reference exhaust information (step S5).

[0067] Next, the actual exhaust information validity determination unit 360 compares the calculated actual exhaust information increase coefficient and the actual exhaust information related indicator information with the database information stored in the data storage unit 130, and performs a process to determine whether the calculated actual exhaust information increase coefficient is valid or not (step S6).

[0068] Then, the actual exhaust information validity determination unit 360 determines whether the actual exhaust information increase coefficient is valid or not based on the result of the processing in step S6 (step S7). If the actual exhaust information increase coefficient is valid (YES determination), proceed to step S8. If the actual exhaust information increase coefficient is not valid (NO determination), proceed to step S9.

[0069] If the determination in step S7 is YES, the estimated exhaust information correction amount calculation unit 370 calculates an estimated exhaust information correction amount to correct the estimated exhaust information (step S8).

[0070] Next, after processing in step S8, or if a NO determination is made in step S4 or step S7, the estimated exhaust information calculation unit 380 calculates the estimated exhaust information using multiple data excluding the specific sensor information and the estimated exhaust information correction amount (step S9).

[0071] Next, the sensor fault diagnosis unit 390 performs a process to diagnose a fault in a specific sensor based on the estimated exhaust information (step S10).

[0072] Then, the sensor fault diagnosis unit 390 determines whether or not the specific sensor is faulty based on the result of the process in step S10 (step S11). If the specific sensor is faulty (YES determination), proceed to step S12. If the specific sensor is not faulty (NO determination), proceed to step S1.

[0073] If the determination in step S11 is YES, the sensor fault diagnosis unit 390 records the fault diagnosis result (fault information) in the data storage unit 130. The sensor fault diagnosis unit 390 also transmits the fault information recorded in the data storage unit 130 to the driver terminal device 400. Furthermore, the sensor fault diagnosis unit 390 illuminates or flashes the MIL 170 (fault warning light) located on the instrument panel according to the fault information recorded in the data storage unit 130. The driver terminal device 400 also transmits the fault information to the cloud server 200 (step S12).

[0074] If the result in step S11 is NO, or after processing in step S12, the process returns to the calculation of actual exhaust information in step S1. The exhaust detection device 110 then periodically acquires multiple data points using the data acquisition unit 300 and repeats the processing in steps S1 to S12 described above.

[0075] Next, the actual exhaust information and estimated exhaust information calculated by the exhaust detection device 110 will be explained with reference to Figures 7 to 11.

[0076] [Actual Exhaust Information and Estimated Exhaust Information at the Time of New Vehicle] Figure 7 is a conceptual diagram showing examples of actual exhaust information and estimated exhaust information from a specific sensor that can be calculated by the exhaust detection device 110. The vertical axis indicates the magnitude of the amount of exhaust information, for example, the exhaust information increase coefficient, i.e., the value obtained by dividing the target exhaust information by the reference exhaust information. If this exhaust information increase coefficient exceeds 1, it can be interpreted that the target exhaust information has increased compared to the reference exhaust information. The horizontal axis shows the actual exhaust information, the reference exhaust information (standard range), and the estimated exhaust information.

[0077] In Figure 7, the vehicle's actual exhaust information increase coefficient 500 is the value obtained by dividing the vehicle's actual exhaust information by the reference exhaust information, i.e., the exhaust information equivalent to that of a new vehicle, 600. The estimated exhaust information increase coefficient 510 is the value obtained by dividing the estimated exhaust information, calculated using multiple data points excluding specific sensor information (NOx sensor 18 information) that directly detects the actual exhaust information, by the reference exhaust information equivalent to that of a new vehicle.

[0078] In the case of a new vehicle, both the actual exhaust information and the estimated exhaust information are almost identical to the exhaust information of a new vehicle, so the values ​​of the actual exhaust information increase coefficient 500 and the estimated exhaust information increase coefficient 510 are both 1. Here, "new vehicle" means that the entire vehicle, including the engine 100 and sensors, is new, but it is sufficient if the specific sensor (NOx sensor 18) and catalytic converter 15 are like new with no deterioration, and the vehicle has undergone regular inspections and maintenance at appropriate intervals. Therefore, in a broad sense, "new vehicle" also includes the case when the specific sensor (NOx sensor 18) and catalytic converter 15 have been replaced with new ones shortly thereafter.

[0079] [Actual exhaust information and estimated exhaust information during catalyst degradation] Figure 8 is a conceptual diagram showing examples of the increase coefficient of actual exhaust information and estimated exhaust information for the vehicle, which are calculated by the exhaust detection device 110 when the catalyst is degraded.

[0080] In Figure 8, the vehicle's actual exhaust information increase coefficient 500A is the value obtained by dividing the vehicle's actual exhaust information, which has deteriorated to some extent due to normal wear during actual driving, by the reference exhaust information equivalent to that of a new vehicle. In other words, the vehicle's actual exhaust information increase coefficient 500A shown in Figure 8 includes the exhaust information equivalent to that of a new vehicle 600, plus the exhaust information 610 due to catalyst deterioration. Therefore, the vehicle's actual exhaust information increase coefficient 500A will be a value greater than 1.

[0081] The estimated exhaust information increase coefficient 510 is the value obtained by dividing the estimated exhaust information, calculated using multiple data points excluding specific sensor information (NOx sensor 18 information) that directly detects actual exhaust information, by the reference exhaust information 600 equivalent to that of a new vehicle. Note that the estimated exhaust information increase coefficient 510 does not include the exhaust information 610 due to catalyst degradation, so even when catalyst degradation has progressed to some extent due to driving, the estimated exhaust information will almost match the exhaust information equivalent to that of a new vehicle. Therefore, the value of the estimated exhaust information increase coefficient 510 is 1 in Figure 8 as well. In other words, as shown in Figure 8, in vehicles where catalyst degradation has progressed to some extent due to actual driving, the actual exhaust information increase coefficient 500A and the estimated exhaust information increase coefficient 510 will no longer match. In order to make such estimated exhaust information match the actual exhaust information, it is necessary to determine whether the vehicle's exhaust information increase coefficient 500A is valid in light of the database information and to correct the estimated exhaust information, as will be described later.

[0082] [Correction for Degradation During Catalyst Degradation] Figure 9 is a conceptual diagram showing an example of the correction of estimated exhaust information by the exhaust detection device 110 during catalyst degradation.

[0083] As shown in Figure 9, the actual exhaust information increase coefficient 500A for a vehicle whose catalyst has deteriorated to some extent through actual driving includes exhaust information 610 due to catalyst deterioration, in addition to exhaust information 600 equivalent to that of a new vehicle. Therefore, as described above, the actual exhaust information increase coefficient 500A for the vehicle is greater than 1. Also, as described above, the estimated exhaust information increase coefficient 510 does not include exhaust information 610 due to catalyst deterioration. For this reason, the value of the estimated exhaust information increase coefficient 510 is 1 in Figure 9 as well.

[0084] The database 710 receives the actual exhaust information increase coefficient 500A for the vehicle itself, calculated by the exhaust detection device 110, and actual exhaust-related index information corresponding to this actual exhaust information increase coefficient 500A for the vehicle itself. Note that the database 710 shown in Figure 9 and Figure 10 (described later) corresponds to the data storage unit 130 and the actual exhaust information validity determination unit 360 in Figure 4. In other words, the database 710 holds database information that has been pre-recorded with actual exhaust information increase coefficients originating from multiple vehicles, including the vehicle itself.

[0085] First, the database 710 calculates the standard range of database information corresponding to the actual exhaust-related indicator information of the vehicle calculated by the exhaust detection device 110. Next, it compares the calculated standard range of database information with the actual exhaust information increase coefficient 500A of the vehicle. For example, if the actual exhaust information increase coefficient 500A of the vehicle is within the standard range of database information (upper and lower limits of the actual exhaust information increase coefficient), the database 710 determines that the value of the actual exhaust information increase coefficient 500A of the vehicle calculated by the exhaust detection device 110 is valid. Conversely, if the actual exhaust information increase coefficient 500A of the vehicle is outside the standard range of database information, the database 710 determines that the value of the actual exhaust information increase coefficient 500A of the vehicle calculated by the exhaust detection device 110 is abnormal.

[0086] If the database 710 determines that the vehicle's actual exhaust information increase coefficient 500A is valid, the estimated exhaust information correction amount calculation unit 370 (Figure 4) calculates an estimated exhaust information correction amount to correct the estimated exhaust information. The estimated exhaust information correction amount is set, for example, according to the vehicle's actual exhaust information increase coefficient 500A. As an example, the estimated exhaust information correction amount may be a representative value of the vehicle's actual exhaust information increase coefficient 500A, i.e., the time average, median, or mode of the vehicle's actual exhaust information increase coefficient 500A. If the database 710 determines that the vehicle's actual exhaust information increase coefficient 500A is abnormal, the estimated exhaust information correction amount calculation unit 370 (Figure 4) stops updating the estimated exhaust information correction amount to correct the estimated exhaust information.

[0087] [Degradation Correction During Catalyst and Sensor Degradation] Figure 10 is a conceptual diagram showing an example of estimated exhaust information correction by the exhaust detection device 110 during catalyst degradation and sensor degradation.

[0088] The actual exhaust information increase coefficient 500B for the vehicle shown in Figure 10 includes exhaust information 600 equivalent to that of a new vehicle, as well as exhaust information 610 due to catalyst degradation and exhaust information 800 due to specific sensor degradation. Therefore, the actual exhaust information increase coefficient 500B for the vehicle is the actual exhaust information increase coefficient 500A for the vehicle shown in Figure 8 plus the exhaust information 800 due to specific sensor degradation. As mentioned above, the estimated exhaust information does not include exhaust information 610 due to catalyst degradation and exhaust information 800 due to specific sensor degradation, so the value of the estimated exhaust information increase coefficient 500B is 1 in Figure 10 as well.

[0089] The database 710 receives the vehicle's actual exhaust information increase coefficient 500B calculated by the exhaust detection device 110, and the vehicle's actual exhaust-related index information corresponding to this actual exhaust information increase coefficient 500B. First, the database 710 calculates the standard range of database information corresponding to the vehicle's actual exhaust-related index information calculated by the exhaust detection device 110. Next, it compares the calculated standard range of database information with the vehicle's actual exhaust information increase coefficient 500B. For example, if the vehicle's actual exhaust information increase coefficient 500B is outside the standard range of database information (upper and lower limits of the actual exhaust information increase coefficient), the database 710 determines that the value of the vehicle's actual exhaust information increase coefficient 500B calculated by the exhaust detection device 110 is abnormal. Conversely, if the vehicle's actual exhaust information increase coefficient 500B is within the standard range of database information, the database 710 determines that the value of the vehicle's actual exhaust information increase coefficient 500B calculated by the exhaust detection device 110 is valid.

[0090] If the database 710 determines that the vehicle's actual exhaust information increase coefficient 500B is valid, the estimated exhaust information correction amount calculation unit 370 (Figure 4) calculates an estimated exhaust information correction amount to correct the estimated exhaust information. The estimated exhaust information correction amount is set, for example, according to the vehicle's actual exhaust information increase coefficient 500A. As an example, the estimated exhaust information correction amount may be a representative value of the vehicle's actual exhaust information increase coefficient 500A, i.e., the time average, median, or mode of the vehicle's actual exhaust information increase coefficient 500A. If the database 710 determines that the vehicle's actual exhaust information increase coefficient 500A is abnormal, the estimated exhaust information correction amount calculation unit 370 (Figure 4) stops updating the estimated exhaust information correction amount to correct the estimated exhaust information.

[0091] [Actual Exhaust-Related Indicators and Actual Exhaust-Related Information Increase Coefficient] Figure 11 is a graph showing an example of the standard range of database information. In Figure 11, the vertical axis is the actual exhaust-related information increase coefficient. The horizontal axis is the actual exhaust-related indicator information, such as catalyst thermal history information, catalyst cumulative usage time information, engine cumulative operating time information, or vehicle cumulative mileage information.

[0092] The catalytic converter, installed to purify exhaust gases, is a component that normally wears out during the regular use of a vehicle. Even if there are no particular malfunctions in the vehicle's engine itself, catalyst degradation progresses in proportion to the increase in actual exhaust-related indicators. Therefore, in the vast majority of vehicles, the actual exhaust information increase coefficient exceeds 1.0 in proportion to the increase in actual exhaust-related indicators.

[0093] As an example, based on database information containing actual exhaust information increase coefficients, the actual exhaust information increase coefficients of numerous other vehicles are plotted at square points and a distribution analysis is performed. As shown in Figure 11, based on the numerous square points, the range between the upper limit 1101 and the lower limit 1102 of the standard range, and the median of the standard range shown by the dashed line in Figure 11 become clear. Furthermore, as shown in Figure 11, when the actual exhaust information increase coefficient is plotted at circular points based on the vehicle's most recent actual exhaust information and actual exhaust-related indicator information, if the vehicle's actual exhaust information increase coefficient falls within the range between the upper limit 1101 and the lower limit 1102 of the standard range, it can be determined that the vehicle's actual exhaust information increase coefficient is within the range of standard (normal wear) catalyst degradation. In this case, it can be determined that the vehicle's actual exhaust information is valid.

[0094] On the other hand, if the actual exhaust information increase coefficient of the vehicle falls outside the range between the upper limit 1101 and the lower limit 1102 of the standard range, that is, if the actual exhaust information increase coefficient is outside the standard (normal wear) range, it can be determined that the cause of the increase in the actual exhaust information increase coefficient includes factors other than standard (normal wear) catalyst degradation. In this case, it is thought that the actual exhaust information has changed significantly due to a cause other than catalyst degradation, such as a failure of sensors 150 (for example, NOx sensor 18). In this case, the actual exhaust information of the vehicle can be determined to be abnormal.

[0095] Furthermore, the sensor fault diagnosis unit 390 may determine, for example, that a specific sensor such as the NOx sensor 18 is faulty when the actual exhaust information increase coefficient of the vehicle deviates significantly from the upper limit 1101 and the lower limit 1102 of the standard range.

[0096] As described above, the exhaust detection system according to this embodiment (a system including the exhaust detection device 110) is an exhaust detection system comprising a specific sensor (e.g., NOx sensor 18) that detects a portion of the exhaust components downstream of the catalyst disposed in the exhaust passage of the internal combustion engine of the vehicle, and a simulated sensor (e.g., estimated exhaust information calculation unit 380) that estimates at least a portion of the exhaust components. This exhaust detection system comprises a processing unit (e.g., CPU 193) that uses the specific sensor to calculate the actual exhaust information of the vehicle under predetermined operating conditions (e.g., actual exhaust information increase coefficient) and calculates index information related to catalyst deterioration using the operating state information of the vehicle, a data storage unit (e.g., data storage unit 130) that forms a database information which stores actual exhaust information and index information originating from vehicles of the same type as the vehicle in association with each other, and a determination unit (e.g., actual exhaust information validity determination unit 360) that compares the calculated actual exhaust information and index information of the vehicle with the actual exhaust information and index information in the database information to determine the validity of the vehicle's actual exhaust information. If the processing unit determines that the actual exhaust information of the vehicle is valid, it corrects the estimated exhaust information, which is estimated using a simulated sensor based on the actual exhaust information of the vehicle.

[0097] This allows the present embodiment to ensure the validity of the actual exhaust information of the vehicle itself, while also enabling correction of estimated exhaust information from simulated sensors and diagnosis of specific sensors.

[0098] Furthermore, in the exhaust detection system according to this embodiment, the determination unit calculates a standard range (standard range upper limit 1101 and standard range lower limit 1102) of the database information corresponding to the indicator information of the vehicle, based on the database information stored in the data storage unit, and further compares the actual exhaust information of the vehicle with the standard range. If the determination unit determines that the actual exhaust information of the vehicle is within the standard range of the database information, the processing unit corrects the estimated exhaust information estimated using a simulated sensor based on the value of the actual exhaust information of the vehicle.

[0099] In this embodiment, the estimated exhaust information of the simulated sensor (estimated exhaust information calculation unit 380) can be accurately corrected by correcting it using only the actual exhaust information that has been determined to be valid.

[0100] For example, when correcting the sensor value of a simulated sensor (corresponding to the estimated exhaust information calculation unit 380) based on the NOx value detected by the NOx sensor 18, there is a possibility that the NOx sensor 18 is not functioning properly and the NOx value contains NOx sensor errors, making it impossible to perform appropriate correction. Therefore, in this embodiment, a comparison between actual exhaust information and database information is made to determine whether or not the NOx value detected by the NOx sensor 18 contains NOx sensor errors. If the NOx value does not contain NOx sensor errors, the output value of the simulated sensor based on the NOx value is corrected.

[0101] According to this embodiment, for example, in an OBM system that uses both a specific sensor (NOx sensor) and a simulated sensor, estimated exhaust information correction is performed on the simulated sensor to respond to environmental changes and aging. At this time, it is confirmed that the NOx value detected by the NOx sensor 18 does not contain NOx sensor errors, and the output value of the simulated sensor can be accurately corrected using that NOx value. This makes it possible to improve the accuracy of the exhaust monitor in OBM, for example.

[0102] <Second Embodiment> Next, the configuration of the exhaust gas detection device according to the second embodiment of the present invention will be described with reference to Figure 12.

[0103] [Functional Configuration of Exhaust Detection Device (Calculation Processing Unit)] Figure 12 is a block diagram showing an example of the functional configuration of the exhaust detection device 110A according to the second embodiment of the present invention. Figure 12 will be explained focusing on the differences from Figure 4. In this embodiment, the exhaust detection device 110A is provided instead of the exhaust detection device 110 according to the first embodiment. In Figure 12, the input circuit 191, output circuit 196, and communication IF 140 (see Figure 3) that perform communication processing between the exhaust detection device 110A and other devices (sensors, ECU, server, etc.) are omitted from the description.

[0104] The configuration of the exhaust detection device 110A is the same as that of the exhaust detection device 110 in Figure 4, except that database information accumulating actual exhaust-related indicator information and actual exhaust information increase coefficients is stored in the cloud server 200A. That is, the exhaust detection device 110A comprises a data acquisition unit 300, an actual exhaust information calculation unit 310, an actual exhaust-related indicator information calculation unit 320, a predetermined operating condition determination unit 330, an actual exhaust information increase coefficient calculation unit 350, an actual exhaust information validity determination unit 360, an estimated exhaust information correction amount calculation unit 370, an estimated exhaust information calculation unit 380, and a sensor fault diagnosis unit 390. The actual exhaust information increase coefficient calculation unit 350, the actual exhaust information validity determination unit 360, and the estimated exhaust information correction amount calculation unit 370 are configured to perform calculation and determination processing when predetermined operating conditions are met 340.

[0105] The cloud server 200A stores database information that accumulates actual exhaust-related indicator information and actual exhaust information increase coefficients for multiple vehicles, including other vehicles. The cloud server 200A receives information on sensor failures from the driver terminal device 400 and manages the sensor failure status of each vehicle.

[0106] The actual exhaust information validity determination unit 360 uses the database information received from the cloud server 200, the calculation results of the actual exhaust-related index information calculation unit 320, and the calculation results of the actual exhaust information increase coefficient calculation unit 350 to determine whether the actual exhaust information increase coefficient is valid. The actual exhaust information validity determination unit 360 outputs the result of the validity determination to the estimated exhaust information correction amount calculation unit 370.

[0107] [Processing of the exhaust detection device] Next, the processing of the exhaust detection device 110A according to the second embodiment of the present invention will be described with reference to Figure 13.

[0108] Figure 13 is a flowchart showing a processing example of the exhaust gas detection device 110A according to a second embodiment of the present invention. The difference between Figure 13 and Figure 6 is that it includes step S20.

[0109] In Figure 13, the actual exhaust information calculation unit 310, the actual exhaust-related indicator information calculation unit 320, the predetermined operating condition determination unit 330, and the actual exhaust information increase coefficient calculation unit 350 of the exhaust detection device 110A each execute the processes in steps S1 to S5.

[0110] After processing in step S5, the exhaust detection device 110A receives database information from the cloud server 200A via the communication IF 140, which contains actual exhaust-related index information and actual exhaust information increase coefficients for multiple vehicles, including other vehicles (step S20).

[0111] After the processing in step S20, the actual exhaust information validity determination unit 360, the estimated exhaust information correction amount calculation unit 370, the estimated exhaust information calculation unit 380, and the sensor fault diagnosis unit 390 execute the processes in steps S6 to S12.

[0112] The exhaust detection device 110A periodically acquires multiple data points using the data acquisition unit 300 and repeats the processes described in steps S1 to S5, S20, S6 to S12.

[0113] In this embodiment, data on actual exhaust-related indicators and actual exhaust-related increase coefficients for multiple general vehicles are aggregated by an external device (such as a cloud server in a data center), and the validity of the vehicle's actual exhaust-related information can be determined based on this vast database information. Furthermore, by using this vast database information, the objectivity of the validity determination can be improved.

[0114] <Third Embodiment> Next, the configuration of the exhaust gas detection device according to the third embodiment of the present invention will be described with reference to Figure 14.

[0115] [Functional Configuration of Exhaust Detection Device (Calculation Processing Unit)] Figure 14 is a block diagram showing an example of the functional configuration of the exhaust detection device 110B according to the third embodiment of the present invention. Figure 14 will be explained focusing on the differences from Figure 4. In this embodiment, the exhaust detection device 110B is provided instead of the exhaust detection device 110 according to the first embodiment. In Figure 14, the input circuit 191, output circuit 196, and communication IF 140 (see Figure 3) that perform communication processing between the exhaust detection device 110B and other devices (sensors, ECU, server, etc.) are omitted from the description.

[0116] The configuration of the exhaust detection device 110B is the same as that of the exhaust detection device 110 in Figure 4, except that the cloud server 200B has the functions of a database that stores actual exhaust-related indicator information and actual exhaust information increase coefficient, and an actual exhaust information validity determination unit 360. That is, the exhaust detection device 110B comprises a data acquisition unit 300, an actual exhaust information calculation unit 310, an actual exhaust-related indicator information calculation unit 320, a predetermined operating condition determination unit 330, an actual exhaust information increase coefficient calculation unit 350, an estimated exhaust information correction amount calculation unit 370, an estimated exhaust information calculation unit 380, and a sensor fault diagnosis unit 390. The actual exhaust information increase coefficient calculation unit 350 and the estimated exhaust information correction amount calculation unit 370 are configured to perform calculation and determination processing when predetermined operating conditions are met 340.

[0117] The actual exhaust-related indicator information calculation unit 320 calculates actual exhaust-related indicator information using multiple data acquired by the data acquisition unit 300. The actual exhaust-related indicator information calculation unit 320 outputs the actual exhaust-related indicator information to the cloud server 200B.

[0118] The actual exhaust information increase coefficient calculation unit 350 calculates the actual exhaust information increase coefficient using the calculation results of the actual exhaust information calculation unit 310 under predetermined operating conditions and standard actual exhaust information such as the actual exhaust information of a new vehicle under the same predetermined operating conditions. The actual exhaust information increase coefficient calculation unit 350 outputs the actual exhaust information increase coefficient to the cloud server 200B and the estimated exhaust information correction amount calculation unit 370.

[0119] The cloud server 200B stores database information containing actual exhaust-related indicator information and actual exhaust information increase coefficients for multiple vehicles, including other vehicles. The cloud server 200B also receives the calculation results of the actual exhaust-related indicator information calculation unit 320 and the calculation results of the actual exhaust information increase coefficient calculation unit 350 from the exhaust detection device 110B. The cloud server 200B then uses the database information, the received actual exhaust-related indicator information, and the actual exhaust information increase coefficient to determine whether the actual exhaust information increase coefficient is valid.

[0120] The estimated exhaust information correction amount calculation unit 370 calculates the estimated exhaust information correction amount using the validity judgment results received from the cloud server 200.

[0121] [Processing of the exhaust detection device] Next, the processing of the exhaust detection device 110B according to the third embodiment of the present invention will be described with reference to Figure 15.

[0122] Figure 15 is a flowchart showing a processing example of the exhaust gas detection device 110B according to a third embodiment of the present invention. The main difference between Figure 15 and Figure 6 is the inclusion of step S30.

[0123] First, the actual exhaust information calculation unit 310, the actual exhaust-related indicator information calculation unit 320, the predetermined operating condition determination unit 330, and the actual exhaust information increase coefficient calculation unit 350 of the exhaust detection device 110B each execute the processes in steps S1 to S5.

[0124] After processing in step S5, the exhaust detection device 110B transmits the calculated actual exhaust-related indicator information and the actual exhaust information increase coefficient to the cloud server 200B via the communication IF 140 (step S30).

[0125] Next, the cloud server 200B compares the actual exhaust information increase coefficient and the actual exhaust information increase coefficient received from the exhaust detection device 110B with the database information which contains actual exhaust-related index information and actual exhaust information increase coefficient for multiple vehicles, including other vehicles, and performs a process to determine whether the actual exhaust information increase coefficient is valid (step S6).

[0126] Next, the cloud server 200B determines whether the actual exhaust information increase coefficient is valid based on the results of the processing in step S6 (step S7). The exhaust detection device 110B then obtains the result of the validity determination from the cloud server 200B. If the actual exhaust information increase coefficient is valid (YES determination), the process proceeds to step S8. If the actual exhaust information increase coefficient is not valid (NO determination), the process proceeds to step S9.

[0127] If the cloud server 200B determines that the actual exhaust information increase coefficient is appropriate (YES determination in step S7), the estimated exhaust information correction amount calculation unit 370 calculates the estimated exhaust information correction amount (step S8).

[0128] After the processing in step S8, the estimated exhaust information calculation unit 380 and the sensor fault diagnosis unit 390 execute the processes in steps S9 to S12.

[0129] The arithmetic processing unit 120B periodically acquires multiple data points using the data acquisition unit 300 and repeats the processes described in steps S1 to S5, S30, S6 to S12.

[0130] In this third embodiment, the detection of sensor data from a specific sensor is performed on the exhaust detection device 110B side, but the storage of database information and the calculation of standard range data are performed on the cloud server 200B side. This makes it possible to accurately correct the simulated sensor (estimated exhaust information calculation unit 380) after confirming the validity of the actual exhaust information of the vehicle, while saving resources of the exhaust detection device 110B.

[0131] [Hardware Configuration of Cloud Server and Driver Terminal Device] Next, the hardware configuration of the cloud servers 200, 200A, 200B and the driver terminal device 400 according to the first to third embodiments described above will be explained with reference to Figure 16.

[0132] Figure 16 is a block diagram showing an example of the computer hardware configuration of the cloud servers 200, 200A, 200B and the driver terminal device 400. It can be assumed that the terminal unit 210 (small diagnostic device) shown in Figure 1 also has a similar hardware configuration.

[0133] Computer 1600 is an example of hardware used as a computer capable of operating as cloud servers 200, 200A, 200B and driver terminal device 400 (e.g., MIL170). Computer 1600 comprises a CPU (Central Processing Unit) 1601, ROM (Read Only Memory) 1602, RAM (Random Access Memory) 1603, display unit 1605, and operation unit 1606, each connected to a bus. Furthermore, computer 1600 includes non-volatile storage 1607 and network interface 1608.

[0134] Each block may be selected or omitted according to the function and purpose of use of each device and server. For example, in cloud servers 200, 200A, and 200B, the computer 1600 may be configured without the display unit 1605 or the operation unit 1606 connected.

[0135] The CPU 1601 reads the program code of the software that implements each of the functions according to the above embodiment from the ROM 1602, loads it into the RAM 1603, and executes it. Alternatively, the CPU 1601 may directly read the program code from the ROM 1602 and execute it as is. The computer 1600 may also be equipped with a processing unit such as an MPU (Micro-Processing Unit) instead of the CPU 1601. Variables and parameters that occur during the calculation processing by the CPU 1601 are temporarily written to the RAM 1603.

[0136] As the non-volatile storage 1607, for example, an HDD (Hard Disk Drive), SSD (Solid State Drive), flexible disk, optical disk, magneto-optical disk, CD-ROM, CD-R, non-volatile memory card, etc., can be used. In addition to the OS (Operating System) and various parameters, programs for operating the computer 1600 are recorded in this non-volatile storage 1607. Programs that realize the functions of the cloud servers 200, 200A, 200B and the driver terminal device 400 may be stored in their respective non-volatile storage 1607s.

[0137] The functions of the cloud servers 200, 200A, 200B and the driver terminal device 400 are realized by the CPU 1601 executing programs corresponding to each function stored in the ROM 1602 or non-volatile storage 1607. The programs are stored in the form of computer-readable program code, and the CPU 1601 sequentially executes operations according to the program code. In other words, the ROM 1602 or non-volatile storage 1607 is used as an example of a computer-readable, non-transient recording medium that stores programs executed by a computer.

[0138] The network IF1608 consists of communication devices and the like that control communication between it and the exhaust detection device 110 and the like.

[0139] The present invention is not limited to the embodiments described above, and various other modifications and applications are possible as long as they do not depart from the gist of the invention as described in the claims. For example, the embodiments described above are detailed and specific in order to explain the present invention in an easy-to-understand manner, and are not necessarily limited to those comprising all the components described. Furthermore, it is possible to replace parts of the configuration of one embodiment with components of another embodiment. It is also possible to add components of another embodiment to the configuration of one embodiment. Furthermore, it is possible to add, replace, or delete other components for parts of the configuration of each embodiment.

[0140] Furthermore, some or all of the above configurations, functions, and processing units may be implemented in hardware, for example, by designing them as integrated circuits. Broadly defined processor devices such as FPGAs (Field Programmable Gate Arrays) and ASICs (Application Specific Integrated Circuits) may be used as hardware.

[0141] Furthermore, each component of the exhaust detection device (processing unit) according to the above embodiment may be implemented on any hardware, as long as the respective hardware can send and receive information from each other via a network. Also, the processing performed by a certain processing unit may be implemented by a single piece of hardware, or by distributed processing by multiple pieces of hardware.

[0142] Furthermore, in the embodiments described above, the control lines and information lines shown are those deemed necessary for explanatory purposes, and not all control lines and information lines are necessarily shown in the actual product. In practice, it can be assumed that almost all components are interconnected.

[0143] Furthermore, in this specification, processing steps describing chronological processing include not only processing performed chronologically in the order described, but also processing that is not necessarily performed chronologically but is executed in parallel or individually (for example, processing by objects). In addition, the processing order of processing steps describing chronological processing may be changed to the extent that it does not affect the processing result.

[0144] 15...Catalyst, 18...NOx sensor, 100...Engine, 110...Exhaust detection device, 120, 120A, 120B...Calculation processing unit, 130...Data storage unit, 150...Sensors, 160...Actuators, 170...MIL, 193...CPU, 194...ROM, 195...RAM, 200, 200A, 200B...Cloud server, 210...Terminal unit, 300...Data acquisition unit, 310...Actual exhaust information calculation unit, 320...Actual exhaust related indicator information calculation unit, 330...Determined operating condition determination unit, 340...When predetermined operating conditions are met, 350...Actual exhaust information increase coefficient calculation unit, 360...Actual exhaust information validity determination unit, 370...Estimated exhaust information correction amount calculation unit, 380...Estimated exhaust information calculation unit, 390...Sensor fault diagnosis unit, 400... Driver terminal device, 1000... Vehicle

Claims

1. An exhaust detection system comprising: a specific sensor for detecting a portion of the exhaust components downstream of a catalyst disposed in the exhaust passage of the internal combustion engine of the vehicle; and a simulated sensor for estimating at least a portion of the exhaust components as estimated exhaust information, wherein the system comprises: a processing unit that uses the specific sensor to calculate actual exhaust information under predetermined operating conditions and uses the vehicle's operating state information to calculate index information related to catalyst deterioration; a data storage unit for which database information is formed, which stores the actual exhaust information and index information originating from vehicles of the same type as the vehicle in association with each other; and a determination unit that compares the calculated actual exhaust information and index information of the vehicle with the database information to determine the validity of the vehicle's actual exhaust information, wherein the processing unit corrects the estimated exhaust information based on the actual exhaust information if it determines that the vehicle's actual exhaust information is valid.

2. The exhaust detection system according to claim 1, wherein the determination unit calculates a standard range of actual exhaust information corresponding to the indicator information of the vehicle based on the database information stored in the data storage unit, compares the actual exhaust information of the vehicle with the standard range of actual exhaust information, and the processing unit corrects the estimated exhaust information based on the value of the actual exhaust information when the determination unit determines that the actual exhaust information of the vehicle is within the standard range of actual exhaust information.

3. The exhaust detection system according to claim 1, wherein the processing unit calculates the thermal history information of the catalyst in the vehicle and other vehicles, information on the aging deterioration of the catalyst, information on the cumulative operating time of the internal combustion engine, or the cumulative mileage of the vehicle as the indicator information for the vehicle.

4. The exhaust detection system according to claim 1, wherein the processing unit transmits the calculated actual exhaust information and index information of the vehicle to the data storage unit for storage.

5. The exhaust detection system according to claim 1, wherein the vehicle of the same type as the vehicle itself is the vehicle itself, or a plurality of vehicles including at least other vehicles.

6. The exhaust detection system according to claim 2, wherein the correction of the estimated exhaust information estimated using the simulated sensor is performed by correcting the parameters of the physical model, mathematical model, or machine learning model constituting the simulated sensor, or by correcting the output value of the simulated sensor.

7. The exhaust detection system according to claim 1, wherein the determination unit calculates a standard range of the actual exhaust information corresponding to the indicator information of the vehicle based on the database information stored in the data storage unit, compares the actual exhaust information of the vehicle with the standard range of the actual exhaust information, and the specific sensor fault diagnosis unit diagnoses a fault of the specific sensor using data of the deviation amount from the standard range of the database information of the actual exhaust information of the vehicle when the determination unit determines that the actual exhaust information of the vehicle is outside the standard range of the actual exhaust information.

8. The exhaust detection system according to claim 1, wherein the data storage unit is configured as a storage device within the vehicle.

9. The exhaust detection system according to claim 1, wherein the data storage unit is located outside the vehicle.

10. An exhaust detection method using an exhaust detection system comprising: a specific sensor for detecting a portion of the exhaust components downstream of a catalyst disposed in the exhaust passage of the internal combustion engine of the vehicle; and a simulated sensor for estimating at least a portion of the exhaust components as estimated exhaust information, the exhaust detection method comprising: a process for calculating actual exhaust information under predetermined operating conditions using the specific sensor and calculating index information related to catalyst deterioration using the operating state information of the vehicle; a process for determining the validity of the actual exhaust information of the vehicle by comparing the calculated actual exhaust information and index information of the vehicle with database information that stores the actual exhaust information and index information originating from vehicles of the same type as the vehicle in association; and a process for correcting the estimated exhaust information based on the actual exhaust information if it is determined that the actual exhaust information of the vehicle is valid.

Images