PROCEDURES FOR IN-VEHICLE DATA PROCESSING

Abstract

Method for a vehicle incorporating an engine (10), comprising: adapting (218) a function to one or more segments of a diagnostic data set for an engine component within the vehicle; including: selecting (304) a first set of curves and adapting (306) the first set of curves to the one or more segments; and transferring (220; 320) parameters of the function, and not of the one or more segments of the data set, to a location outside the vehicle; in response to a curve-fitting coefficient for the first set of curves exceeding a threshold, transferring (220; 320) the curve-fitting coefficient for the first set of curves to the location outside the vehicle.

Description

REGIONThe present description relates generally to methods for processing diagnostic data within a vehicle.GENERAL STATE OF THE ART / SUMMARYVehicles may be equipped with evaporative emission control systems (EVAP) to reduce the release of fuel vapors to the atmosphere. For example, an adsorbent-filled fuel vapor canister may adsorb and store refueling vapors, loss vapors during vehicle operation, and daily fuel vapors. At a later time when the engine is operating, the evaporative emissions control system allows the vapors to be purged into the engine intake manifold for use as fuel. To meet stringent federal emissions regulations, it may be necessary to intermittently diagnose emissions control systems for the presence of undesirable evaporative emissions (leaks) that could release fuel vapors to the atmosphere. The data generated during each diagnostic test can be used to understand the results of the tests and the overall health of the EVAP system.Accordingly, various approaches have been developed for transmitting on-board diagnostics (OBD) data to an off-board location. An example approach shown by Wang et al. in US 2013 / 0 246 135 A1 includes transmitting diagnostic data from in-vehicle diagnostic tests to a remote server. The vehicle OBD unit may transmit the OBD data of the vehicle electronic control units, which may then transmit the data to a remote server either directly or via a smart device with a wireless communication module. The data may be analyzed at the remote location and a signal may be sent to the vehicle operator to notify if there is a request for maintenance of one or more vehicle components.Furthermore, the document DE 10 2004 035 793 A1 shows a diagnostic device in which the data volume with respect to the data communication between the vehicle and the external control center is to be reduced. In this case, a gateway unit determines whether a data volume of malfunction information is greater than a predetermined information volume, wherein, if this is the case, the gateway unit splits the malfunction information into a plurality of pieces of information and transmits it successively in portions. Furthermore, US 2017 / 0022865 A1 describes an exhaust gas aftertreatment system for internal combustion engines, the combustion parameters of which are adapted for the exhaust gas aftertreatment. US 2017 / 0024646 A1 further describes an information processing system having a memory area storing a plurality of documents and computer executable instructions for implementing a user interaction diagnostic engine with corresponding correlation values. Furthermore, the document US 2010 / 0250089 A1 shows a method for using cylinder pressure sensors for indirectly determining the operating conditions of an internal combustion engine.However, the present inventors have recognized potential issues with such a system. For example, in-vehicle diagnostics (OBD) of EVAP and other vehicle systems may generate a large amount of data that may make efficient transmission difficult via available wireless communication. Additionally, a remote location with sufficient data storage capacity (e.g., memory) may be required to store all available OBD data. Thus, a portion of the OBD data, such as the beginning and end points of a test, may be transmitted to and stored in a remote location. However, the start and end points of OBD data, such as EVAP system leak test data, may be affected by vehicle operating conditions, such as an ascent or rough roads, which may lead to sloshing of the fuel. For example, a fuel tank pressure profile analyzed for EVAP system diagnostic may erroneously indicate a leak during a driving condition that results in fuel sloshing. The erroneous diagnostic result may impair vehicle operation, and in the absence of full OBD data, it may be difficult to understand the cause of the leak indication of the EVAP system. In addition, due to access to only a limited portion of the OBD data, the data may not be analyzed efficiently at an off-board location.The present invention is therefore based on the object of permitting reliable diagnosis of engine components within a vehicle which, on the one hand, manages with limited amounts of data and transmission capacities and, on the other hand, avoids misdiagnoses, indicated by specific vehicle operating conditions.According to the invention, the object mentioned is achieved by a method according to claim 1 and a method according to claim 11. Preferred embodiments of the invention are the subject of the dependent claims.In one example, the issues described above may be addressed by a method for a vehicle including an engine, comprising: adjusting a function to one or more segments of a diagnostic dataset for an engine component within the vehicle; and transmitting parameters of the function, and not the one or more segments of the dataset, to an off-board location. In this way, by efficiently adjusting a curve to the OBD data, a smaller amount of data including the curve adjustment parameters and vehicle operating conditions may be transmitted to an off-board location for analysis, storage, and future use.As an example, during a diagnostic test on the EVAP system, a vacuum may be applied to a sealed EVAP system and the increase in pressure observed. If the rate of pressure increase is greater than a threshold rate or the EVAP system pressure is above a threshold pressure after a predefined duration of the test, it may be inferred that there is a leak in the EVAP system. If such a leak is detected, a curve can be fitted to a portion of the data acquired during the pressure increase. The type of expected curve for this data can be retrieved from the control store. If it is possible to fit the data with the expected curve and obtain a curve fit having a determination coefficient (R 2) above a threshold, it can be concluded that the diagnostic test results are reliable. However, if the expected curve does not provide an adjustment above the threshold, one or more other curves are iteratively tried until a curve adjustment with an R 2- value above the threshold is achieved. For example, polynomials of a different order, exponential curves, Gaussian curves, etc. can be used for curve fitting. A curve may be fitted to the entire data, or the data may be divided into sections and a separate curve may be fitted to each section. Once a reliable curve fit has been achieved, the coefficients of the curve(s) and the R 2- value(s) may be transmitted to an off-board location. Additionally, the initial and final data points, as well as vehicle operating conditions, may be transmitted to the off-board location during the test, such as temperature, altitude, vehicle speed, vehicle location (e.g., retrieved from a global positioning satellite), fuel level, engine load, etc. At the off-vehicle location, the entire dataset may be reconstructed using the curve fit coefficients and further analyzed. The controller may receive instructions from the off-board location to update EVAP system leak test results and engine operations based on the data analysis. In addition, during vehicle maintenance, a technician in a workshop can retrieve the entire diagnostic data record from the information available at the location external to the vehicle and can accordingly service the vehicle.In this way, by fitting a best fit curve to diagnostic test data and transmitting the coefficients of the curve to an off-board location, it may be possible to access and analyze the entire diagnostic dataset at the off-board location and at a service station. In the case of fault test results from external conditions (such as fuel slosh during an EVAP system leak test), the in-vehicle results may be updated using instructions received from an out-of-vehicle location and engine operation may be optimized. The technical effect of curve fitting to data captured within the vehicle and transmitting only the coefficients of the fitting adjacent to beginning and end points of the data to an off-board location is that more rapid data transmission to the off-board location can be achieved using a lower bandwidth. In addition, due to the transfer of a smaller, but more relevant portion of the data, a smaller amount of storage space (memory) may be occupied at the off-board location. Overall, by adjusting a curve, transmitting a smaller amount of data, and curve adjusting engine operating parameters, a larger portion of the OBD dataset (e.g., the entire portion) may be rendered and analyzed at the off-board location, thereby improving off-board data processing. By increasing the accuracy and reliability of data processing without increasing the memory or processor requirements, vehicle performance is improved.It should be understood that the summary above is provided to introduce in simplified form a selection of concepts that are further described in the detailed description. It is not intended to identify key or key features of the claimed subject matter, the scope of which is defined uniquely in the claims that follow the detailed description. Further, the claimed subject matter is not limited to implementations that eliminate disadvantages noted above or in any part of the present disclosure.BRIEF DESCRIPTION OF THE DRAWINGSFIG. 1 shows a schematic diagram of a vehicle engine system including a evaporative emissions control system and a wireless communication vehicle system. FIG. 2 is a flow diagram illustrating a method that may be implemented for performing a diagnostic routine of a system for controlling evaporative emissions and processing the diagnostic data. FIG. 3 is a flow diagram illustrating a method that may be implemented for curve fitting the diagnostic data of the evaporative emissions control system. FIG. 4 shows an example plot fit for diagnostic data of a system for controlling evaporative emissions. FIG. 5 illustrates an example diagnostic of a system for controlling evaporative emissions in accordance with the present disclosure.DETAILED DESCRIPTIONThe following description relates to systems and methods for executing on-board diagnostic tests (OBD), processing the OBD data, transmitting components of the processed data to an off-board location, and adjusting engine operating parameters based on a signal received from the off-board location. In the present disclosure, the diagnostic is described with reference to a system for controlling evaporative emissions, such as the system shown in FIG. 1. However, in alternative examples, diagnostics may be performed for other engine systems. An engine controller may be configured to perform a control routine, such as the example routines of FIGS. 2 and 3, for executing diagnostic tests of a system for controlling evaporative emissions and processing the test data to adapt a curve to the data. An example of curve fitting to test data of an evaporative emissions control system is shown in FIG. 4, and an example of conducting a diagnostic of an evaporative emissions control system using data processed outside and inside the vehicle is shown in FIG. 5.FIG. 1 shows a schematic illustration of a vehicle system 6 that may derive motive power from the engine system 8. The engine system 8 may include an engine 10 having a plurality of cylinders 30. The engine 10 includes an engine inlet 23 and an engine outlet 25. the engine inlet 23 includes an air intake throttle 62 fluidly coupled to the engine intake manifold 44 via an intake passage 42. Air may enter intake passage 42 via air filter 52. The engine outlet 25 includes an exhaust manifold 48 leading to an exhaust passage 35 that directs exhaust gas to the atmosphere. Engine outlet 25 may include one or more emission control devices 70 mounted in a short coupled position. The one or more emission control devices may include a three-way catalyst, a lean NOx trap, a diesel particulate filter, an oxidation catalyst, etc. It will be appreciated that other components may be included in the engine, such as a plurality of valves and sensors, as further set forth herein. In some embodiments, where system 8 may be a boosted engine system, the engine system may further include a boosting device, such as a turbocharger (not shown).Engine system 8 may be coupled to a fuel system 18. Fuel system 18 includes a fuel tank 20 coupled to a fuel pump 21 and a fuel vapor canister 22. During a fuel tank refueling event, fuel may be pumped from an external source into the vehicle through a refueling inlet 108. The fuel tank 20 may hold a variety of fuel mixtures, including fuel having a range of alcohol concentrations, such as various gasoline-ethanol mixtures including E10, E85, gasoline, etc., and combinations thereof. A fuel level sensor 106 disposed in the fuel tank 20 may provide an indication of the fuel level ("fuel level input") to the controller 12. As shown, the fuel level sensor 106 may include a float connected to a variable resistor. Alternatively, other types of fuel level sensors may be used.Fuel pump 21 is configured to pressurize fuel supplied to injectors of engine 10, such as example injector 66. While only a single injector 66 is shown, additional injectors are provided for each cylinder. It will be appreciated that the fuel system 18 may be a non-return fuel system, a return fuel system, or various other types of fuel systems. Vapors generated in fuel tank 20 may be directed to fuel vapor canister 22 via conduit 31 before purging to engine intake 23.The fuel vapor canister 22 is filled with an appropriate adsorbent for temporarily trapping fuel vapors (including vaporized hydrocarbons) generated during fuel tank refueling operations as well as daily vapors. In one example, the adsorbent used is activated carbon. When purge conditions are met, such as when the canister is saturated, vapors stored in fuel vapor canister 22 may be purged to engine intake 23 by opening canister purge valve 112. While a single canister 22 is shown, it will be appreciated that the fuel system 18 may include any number of canisters. In one example, canister purge valve 112 may be a solenoid valve, wherein opening and closing of the valve is performed via actuation of a solenoid for canister purge.The canister 22 may include a buffer 22 a(or buffer region), each of the canister and the buffer comprising the adsorbent. As shown, the volume of buffer 22 amay be less than the volume (e.g., a fraction of the volume) of canister 22. The adsorbent in the buffer 22 amay be the same as or different from the adsorbent in the canister (e.g., both may include coal). The buffer 22 amay be disposed within the canister 22 such that during canister loading, fuel vapors are first adsorbed into the buffer and the fuel vapors are adsorbed into the canister when the buffer is saturated. In comparison, fuel vapors are first desorbed from the canister (e.g., up to a threshold amount) during canister purge before being desorbed from the buffer. In other words, loading and unloading of the buffer is non-linear to loading and unloading of the canister. Thus, the effect of the canister buffer is to attenuate fuel vapor spikes flowing from the fuel tank to the canister, thereby reducing the likelihood of fuel vapor spikes reaching the engine.Canister 22 includes a vent 27 for directing gases out of canister 22 to the atmosphere when storing or trapping fuel vapors from fuel tank 20. Vent 27 may also allow fresh air to be drawn into fuel vapor canister 22 when purging stored fuel vapors to engine intake 23 via purge line 28 and purge valve 112. While this example shows vent 27 communicating with unheated fresh air, various modifications may also be used. Vent 27 may include a canister vent valve 114 to adjust a flow of air and vapors between canister 22 and the atmosphere. The canister vent valve may also be used for diagnostic routines. When included, the vent valve may be opened during fuel vapor storage operations (e.g., during fuel tank refueling and while the engine is not running) such that air, from which fuel vapors are purged after flowing through the canister, may be forced out to the atmosphere. Similarly, the vent valve may be opened during purge operations (e.g., during canister regeneration and while the engine is running) to allow a flow of fresh air to expel the fuel vapors stored in the canister. In one example, canister vent valve 114 may be a solenoid valve, wherein opening and closing of the valve is performed via actuation of a canister vent solenoid. In particular, the canister vent valve may be an open valve that is closed upon actuation of the solenoid for canister venting.A fuel tank shut-off valve 110 may optionally be included in conduit 31 such that fuel tank 20 is coupled to canister 22 via the valve. During regular engine operation, the isolation valve 110 may be maintained closed to limit the amount of daily vapors or loss vapors directed from the fuel tank 20 to the canister 22 during vehicle operation. During refueling operations and selected purging conditions, isolation valve 110 may be temporarily opened, e.g., for a duration to route fuel vapors from fuel tank 20 to canister 22. By opening the valve during purging conditions, when fuel tank pressure is above a threshold (e.g., above a fuel tank mechanical pressure threshold, above which mechanical damage may arise to the fuel tank and other fuel system components), the refueling vapors may be released into the canister and fuel tank pressure may be maintained below pressure thresholds. While the illustrated example shows the isolation valve 110 disposed along the conduit 31, in alternative embodiments, the isolation valve may be attached to the fuel tank 20.One or more pressure sensors 120 may be coupled to fuel system 18 to provide an estimate of a fuel system pressure. While the illustrated example shows pressure sensor 120 coupled directly to fuel tank 20, in alternative embodiments, the pressure sensor may be coupled between fuel tank and canister 22, specifically between fuel tank and isolation valve 110. In still further embodiments, a first pressure sensor may be disposed upstream of the isolation valve (between the isolation valve and the canister), while a second pressure sensor is disposed downstream of the isolation valve (between the isolation valve and the fuel tank) to provide an estimate of a pressure differential across the valve. In some examples, a vehicle control system may infer and indicate fuel system leakage based on changes in fuel tank pressure during a leak diagnostic routine.One or more temperature sensors 121 may also be coupled to fuel system 18 to provide an estimate of a fuel system temperature. In one example, fuel system temperature is a fuel tank temperature, and temperature sensor 121 is a fuel tank temperature sensor coupled to fuel tank 20 for estimating a fuel tank temperature. While the illustrated example shows temperature sensor 121 coupled directly to fuel tank 20, in alternative embodiments, the temperature sensor may be coupled between the fuel tank and canister 22.Fuel vapors released from canister 22, for example during a purging operation, may be directed into engine intake manifold 44 via purge line 28. The flow of vapors along purge line 28 may be regulated by canister purge valve 112 coupled between the fuel vapor canister and the engine inlet. The amount and rate of vapors released by the canister purge valve may be determined by the duty cycle of an associated solenoid to the canister purge valve (not shown). Thus, the duty cycle of the solenoid to the canister purge valve may be determined by the powertrain control module (PCM), such as controller 12, responsive to engine operating conditions including, for example, engine speed / load conditions, air-fuel ratio, canister load, etc. By commanding the controller to close the canister purge valve, it may seal the fuel vapor recovery system from engine intake. An optional canister check valve (not shown) may be included in the purge line 28 to prevent intake manifold pressure from flowing gases in the opposite direction of the purge flow. Thus, the check valve may be required if the canister purge valve controller is not accurately clocked or the canister purge valve itself may be opened by the force of high intake manifold pressure. An estimate of manifold absolute pressure (MAP) or manifold vacuum (ManVac) may be obtained from MAP sensor 118 coupled to intake manifold 44 and in communication with controller 12. Alternatively, the MAP may be inferred from alternative engine operating conditions, such as mass air flow (MAF) as measured by a MAF sensor (not shown) coupled to the intake manifold.The fuel system 18 may be operated in a plurality of modes by the controller 12 through selective adjustment of the various valves and solenoids. For example, the fuel system may be operated in a fuel vapor storage mode (e.g., during a fuel tank refueling operation and while the engine is not running), where controller 12 may open isolation valve 110 and canister vent valve 114 while closing canister purge valve (CPV) 112 to direct refueling vapors into canister 22 while preventing the fuel vapors from being directed into the intake manifold.As another example, the fuel system may be operated in a refueling mode (e.g., when refueling of the fuel tank is requested by a vehicle operator), where controller 12 may open shut-off valve 110 and canister vent valve 114 while maintaining canister purge valve 112 closed to decrease the pressure in the fuel tank before allowing fuel to be added. Thus, the isolation valve 110 may be maintained open during the refueling operation to allow refueling vapors to be stored in the canister. After the completion of the refueling, the shut-off valve can be closed.As yet another example, the fuel system may be operated in a canister purge mode (e.g., after an emission control device light-off temperature has been reached and while the engine is running), where controller 12 may open canister purge valve 112 and canister vent valve 114 while closing isolation valve 110. Here, the vacuum generated by the intake manifold of the running engine may be used to draw fresh air through vent 27 and through fuel vapor canister 22 to purge the stored fuel vapors into intake manifold 44. In this mode, the purged fuel vapors from the canister are burned in the engine. Purging may continue until the amount of fuel vapor in the canister is below a threshold. During purging, the determined amount / concentration of vapor may be used to determine the amount of fuel vapors stored in the canister, and then during a later portion of the purging operation (when the canister is sufficiently purged or empty), the determined amount / concentration of vapor may be used to estimate a loading state of the fuel vapor canister. For example, one or more oxygen sensors (not shown) may be coupled to canister 22 (e.g., downstream of the canister) or disposed in the engine intake and / or engine exhaust to provide an estimate of canister loading (i.e., an amount of fuel vapors stored in the canister). Based on canister load and further based on engine operating conditions, such as engine speed / load conditions, a purge flow rate may be determined.An evaporative leak check module (ELCM) 116 may be coupled to the vent 27 between the canister 22 and the vent valve 114. The ELCM 116 may include a vacuum pump configured to apply a vacuum to the fuel system when a leak test is performed. The ELCM 116 may further include a crossover valve (COV), a reference port, and a pressure sensor. After applying vacuum to the fuel system, a change in pressure at the reference orifice (e.g., an absolute change or rate of change) may be observed and compared to a threshold. Based on the comparison, undesired evaporative emissions from the fuel system may be detected. The ELCM vacuum pump may be a reversible vacuum pump and thus configured to apply positive pressure to the fuel system when a bypass circuit is reversed by placing the pump in a second arrangement.The vehicle system 6 may further include the control system 14. Control system 14 is shown receiving information from a plurality of sensors 16 (various examples of which are described in this disclosure) and transmitting control signals to a plurality of actuators 81 (various examples of which are described in this disclosure). For example, sensors 16 may include exhaust gas sensor 126, temperature sensor 128, MAP sensor 118, fuel system pressure sensor 120, exhaust pressure sensor 129, and cabin occupancy sensor located upstream of the emission control device. Other sensors, such as additional pressure, temperature, air-fuel ratio, and composition sensors, may be coupled to various locations in the vehicle system 6. As another example, the actuators may include fuel injector 66, isolation valve 110, purge valve 112, vent valve 114, fuel pump 21, ELCM pump, and throttle 62.A wireless communication device 152 may be coupled to the control system 14 for communicatively coupling the vehicle system 6 to an off-board location 160. In an example, the off-board location 160 may include a network cloud, a television, or an off-board controller. Additionally, a navigation system 154, such as a global positioning system (GPS), may be coupled to the control system 14 to determine the location of the vehicle 6 during a running diagnostic test. The navigation system may also be connected to the off-board location 160 via wireless communication 150.The control system 14 may further receive information regarding the location of the vehicle from the GPS system. Information received from the GPS may include vehicle speed, vehicle height, vehicle location, etc. This information may be used to infer engine operating parameters, such as local atmospheric pressure. The control system 14 may be further configured to receive information over the Internet or other communication networks.The control system 14 may include a controller 12. The controller 12 receives signals from the various sensors of FIG. 1 and employs the various actuators of FIG. 1 to adjust engine operation based on the received signals and instructions stored in a memory of the controller. For example, controller 12 may also be configured to intermittently perform leak detection routines on fuel system 18 (e.g., fuel vapor recovery system) to confirm that the fuel system is not degraded. Thus, various leak detection tests may be performed while the engine is off (engine-off leak test) or while the engine is running (engine-on leak test). Leak tests performed while the engine is running may include applying a vacuum to the fuel system for a duration (e.g., until a desired fuel system vacuum is reached) and then sealing the fuel system. For example, the controller 12 may actuate an actuator coupled to the ELCM pump to operate the pump to generate a vacuum, and then the controller 12 may adjust the COV to apply the vacuum to the fuel system. The controller may observe a change (increase) in fuel tank pressure (e.g., a rate of change in vacuum level or a final pressure value) via pressure sensor 120. Leak tests performed while the engine is not running may include sealing the fuel system after engine shut down and observing a change in fuel tank pressure. This type of leak test is referred to in this disclosure as an engine-off natural vacuum test (EONV). In sealing the fuel system after engine shut-down, a vacuum develops in the fuel tank as the tank cools and fuel vapors are condensed to liquid fuel. The amount of vacuum and / or rate of vacuum development may be compared to the expected values that would occur for a system with no leaks or a system with leaks of a predetermined magnitude.Such leak tests may produce erroneous results during driving conditions where fuel sloshing occurs (such as driving on a hill, driving over a bump, etc.). Fuel sloshing may generally produce additional fuel vapors in the fuel tank, which in turn may result in variations in fuel tank pressure, thereby affecting the pressure increase in the fuel system observed for EVAP system leak detection. In addition to affecting the endpoint of the pressure increase profile, fuel slosh may also generate multiple intermediate pressure peaks between the beginning and endpoint of the pressure increase phase. Adjustments to engine operation that occur due to erroneous diagnostic results may adversely affect engine performance. If a leak is detected in the fuel system, engine operating adjustments such as increasing a frequency of purging a fuel system canister to the engine may be carried out. To reduce issues associated with erroneous data analysis, a best fit curve may be fitted to some or all of the OBD data collected during the diagnostic test, as outlined with reference to FIG. 2. If it is possible to fit an expected curve profile (as retrieved from the control store) to the data and obtain a curve fit having a determination coefficient (R 2) above a threshold, it may be inferred that the diagnostic test results are reliable. However, if the expected curve does not provide an adjustment above the threshold, one or more other curves may be iteratively tried until a curve adjustment with an R 2- value above the threshold is achieved. A curve may be fitted to the entire data, or the data may be divided into sections and a separate curve may be fitted to each section. Once a reliable curve fit has been achieved, the coefficients of the curve(s) and the R 2- value(s) may be transmitted to an off-board location. Additionally, data corresponding to a beginning and an end point of the dataset and vehicle operating conditions during the test, such as temperature, altitude, vehicle speed, vehicle location, fuel level, engine load, etc., may be transmitted to the off-board location. At the off-vehicle location, the entire dataset may be reconstructed using the curve fit coefficients and further analyzed. The controller may receive instructions from the off-board location and accordingly update the EVAP system leak test results and engine operations based on the data analysis. In addition, a technician at a workshop can access the curve adaptation coefficients and reconstruct the entire diagnostic dataset, which can facilitate better vehicle maintenance and repair. This approach of curve fitting, transmitting to an off-board location, and further using on-board diagnostic data may be performed for a variety of vehicle systems, such as emission control system, turbocharger system, exhaust gas recirculation system, etc.In this way, the components of FIG. 1 provide a fuel system for a vehicle, comprising: a fuel tank; an evaporative emissions control (EVAP) system including a fuel vapor canister coupled to the fuel tank via a shut-off valve; a canister purge valve (CPV) disposed in a purge line between the fuel vapor canister and an engine intake manifold; a canister vent valve (CVV) disposed in a vent line between the fuel vapor canister and the atmosphere, and a pressure sensor coupled to the fuel tank; a wireless communication device communicatively coupling the vehicle to an off-vehicle controller; and an on-vehicle controller disposed within the vehicle. The controller may be configured with computer readable instructions stored on non-transitory memory to: perform an EVAP system diagnostic test by applying vacuum to the EVAP system, isolate the EVAP system from the engine and the atmosphere by closing each of the vent valve and the purge valve, and observe an actual pressure increase profile via the pressure sensor; responsive to a rate of the pressure increase above a threshold, indicate degradation of the EVAP system; adjust a frequency of opening of the CPV during engine operation based on the indication; adjusting the actual pressure increase profile using a curve profile having a determination coefficient (R 2) above a threshold, the curve profile selected from a curve profile set based on an expected pressure increase profile; and uploading each of one or more coefficients of the curve profile, the R 2, a beginning point, and an ending point of the actual pressure increase profile to the off-vehicle controller.FIG. 2 illustrates an example method 200 for performing a diagnostic routine for an evaporative emissions (EVAP) system and processing the diagnostic data. Instructions for carrying out method 200 and the remaining methods included herein may be executed by a controller based on instructions stored on a memory of the controller and in conjunction with signals received from sensors of the engine system, such as the sensors described above with reference to FIG. 1. The controller may employ engine actuators of the engine system to adjust engine operation according to methods described below. It will be appreciated that while the routine of FIG. 2 describes onboard processing of data with reference to OBD data collected from the diagnostics of a evaporative emissions system, this is not intended to be limiting and, in other examples, diagnostic data from other engine systems may be similarly processed.At 202, engine and vehicle conditions may be estimated by the controller based on inputs from a plurality of sensors. The estimated engine operating conditions may include, for example, driver demand, engine load, engine temperature, engine speed, air-fuel ratio, ambient temperature, humidity, atmospheric pressure, etc. Vehicle conditions may include vehicle occupancy, vehicle speed, etc. Fuel system conditions such as fuel level, fuel type, fuel octane content, fuel temperature, etc., and various evaporative emissions system conditions such as fuel vapor canister load, fuel tank pressure, etc., may also be determined.At 204, the routine includes determining if input conditions are met for conducting a diagnostic test of the evaporative emissions system. The entry conditions for a evaporative emissions diagnostic test may be met if a threshold time or distance of vehicle operation has elapsed since a last iteration of the diagnostic routine. For example, if the time elapsed since the last iteration of the diagnostic test is below a threshold time, a new diagnostic test may not be desired. In still further examples, the entry conditions for the diagnostic test may be deemed unfulfilled if any other diagnostic test that may affect the EVAP system diagnostic test is in progress. Additionally, the entry conditions for a diagnostic evaporative emissions test may be deemed met if the vehicle is unoccupied, as inferred based on sensor output from a cabin occupancy sensor coupled to a cabin of the vehicle and / or in-vehicle cameras. The controller may confirm that the vehicle is unoccupied before the diagnostic is initiated, as movement of passengers within the passenger compartment and / or sudden opening of a vehicle door may falsify the diagnostic routine results.If it is determined that the entry conditions for executing the EVAP system diagnostic test are not currently met, control may wait for optimal conditions at 206 before initiating an EVAP system diagnostic test. If it is determined that the input conditions for executing the EVAP system diagnostic test are met, an EVAP system leak detection test may be executed at 208. At 209, an evaporative leak check module (ELCM) pump may be operated to generate a vacuum (pressure bleed) in the EVAP system. During operation of the pump, the ELCM unit diverter valve (COV) may be actuated to a first position to allow air to be drawn out of the EVAP system to the atmosphere. The canister vent valve (CVV) may be actuated to an open position to fluidly couple the EVAP system to the atmosphere via the ELCM pump. Additionally, the canister purge valve (CPV) may be maintained in a closed position to maintain the fuel system isolated from the intake manifold. A fuel system pressure sensor (such as pressure sensor 120 in FIG. 1 ) may be used to estimate the pressure drop in the EVAP system.At 210, when the vacuum in the EVAP system has reached a desired vacuum level, the controller may isolate the EVAP system from the ELCM system and the atmosphere by operating the COV to the second position and theCV to a closed position. Once the EVAP system has been isolated, a vacuum EVAP system leak test may be performed. During the test, at 211, a change (increase) in pressure in the EVAP system via the fuel system pressure sensor may be observed. The rate of pressure increase and the final pressure at the end of a predetermined test duration may be observed.At 212, the routine includes determining if a leak has been detected in the EVAP system. In one example, a leak may be inferred based on a pressure increase rate above a threshold during the vacuum EVAP system leak test. In another example, a leak may be inferred if the final fuel system pressure is higher than an upper threshold pressure at the end of the predetermined test duration. In yet another example, a leak may be inferred if the desired vacuum level is not reached during vacuum generation (depressurization) (e.g., the EVAP system does not reach a threshold lower pressure). A leak in the EVAP system may also be inferred based on other diagnostic tests, such as vacuum tests using natural engine off vacuum (EONV).If it is determined that no leak is detected in the EVAP system, at 214, the absence of leaks in the EVAP system may be indicated and current engine operations may be maintained. If it is inferred that a leak is present in the EVAP system, at 216, a diagnostic code may be set indicating the presence of a leak and degradation of an engine component. An initial state of the engine component (such as a component of the EVAP system) may be inferred based on the diagnostic data generated within the vehicle. In response to detecting a leak in the EVAP system, engine operation may be discontinued. In one example, the canister purge schedule may be updated by scheduling canister purges more frequently, regardless of canister loading, so that fuel vapor in the evaporative emissions fuel system and / or system may be efficiently directed to the engine for combustion. In another example, the purges may be suspended until it is indicated that the source of undesired evaporative emissions has been attenuated. Additionally, responsive to the indication of a leak in the EVAP system, a shut-off valve (fuel tank shut-off valve) coupling the canister of the evaporative emissions system to a fuel tank may be closed.At 218, a curve may be fitted to at least a portion of the diagnostic data. To the actual pressure increase profile, one or more curves such as a polynomial curve, an exponential curve, and a Gaussian curve may be fitted. A function may be used to adjust the entire data set, or separate functions may be adjusted to portions of the data set corresponding to the actual pressure increase profile. The curve fitting may be iteratively continued until a coefficient of curve fitting, such as the coefficient of determination (R 2) is above a threshold. For example, an expected curve profile may be used first for curve fitting, and in response to the curve fitting coefficient for the first set of curves being less than the threshold, a second set of curves may be selected based on the expected profile of the diagnostic data. A detailed description of the curve fitting process is discussed in FIG. 3. Additionally, if it is detected that there is no leak in the EVAP system at 214, the routine may proceed to step 218 and a curve may be adjusted to the diagnostic data.Once reliable curve fitting of the EVAP system diagnostic data has been achieved, at 220, the curve fitting parameters may be transmitted to an off-board location, such as one of a remote server, an off-board controller, and a network cloud that is communicatively coupled to the vehicle. In one example, parameters of a polynomial curve that are transmitted include one or more coefficients of a polynomial of the polynomial curve and a coefficient of determination (R 2) of the polynomial curve. In addition, a form of the function may be transmitted to the off-board location in addition to the parameters of the function. Additionally, a beginning and end point of the diagnostic dataset and vehicle conditions at a time of execution of the diagnostic routine, including engine temperature, engine load, vehicle speed, ambient temperature, altitude, road grade, and vehicle location, may also be transmitted outside the vehicle. Additionally, during conditions when no leak is detected in the EVAP system, curve adjustment parameters may be transmitted to the off-board location for further analysis and future use.At 222, the controller may receive data from the off-board location via wireless communication. The received data may include an updated diagnostic state of the vehicle components. The updated diagnostic state may be based on a reconstructed dataset reconstructed outside the vehicle using the start point, the end point, and the curve fit coefficient or coefficients, and vehicle operating conditions previously transmitted to the off-vehicle location. Updating the diagnostic state may include updating that a previous indication of fuel system degradation (generated within the vehicle) is false and confirming that the fuel system is not degraded. Additionally, instructions may be received from the off-board location to adjust one or more engine operating parameters to reduce the likelihood of a future leak in the EVAP system. The settings to reduce the likelihood of future leaks in the EVAP system may be based on the reconstructed OBD dataset from tests where no leak is detected in the EVAP system.At 224, within the vehicle, the indication of an EVAP system leak and one or more operating parameters of the vehicle may be adjusted based on the updated diagnostic state. In one example, based on the off-board data analysis, it may be inferred that the leak was erroneously indicated due to driving conditions (such as driving on a hill, driving over a bump, etc.) that may have caused fuel sloshing. An indication of fuel sloshing in a fuel tank may be based on the diagnostic routine dataset and may be further based on the updated diagnostic state received from outside the vehicle. Fuel sloshing may generally produce additional fuel vapors in the fuel tank, which in turn may result in variations in fuel tank pressure, thereby affecting the pressure increase in the fuel system observed for EVAP system leak detection. Based on the updated diagnostic condition (input received from the off-board location), the initial indication of degradation may be updated, and further the frequency of canister purge may be adjusted by opening the CPV based on the received input. In another example, a form of curve fit function may be received from the off-board location and it may be suggested that the diagnostic routine be repeated. A new (second) diagnostic dataset may then be generated by repeating the diagnostic routine for the vehicle component (such as the EVAP system). A curve may be adjusted with the received shape of the curve adjustment function to at least one segment of the second dataset, the updated curve adjustment coefficient may be transmitted to the location outside the vehicle, and an updated diagnostic state of the vehicle component may be determined based on the second dataset.The off-board data may also be retrieved during vehicle maintenance, and the entire OBD dataset may be reconstructed and used for further diagnosis and maintenance. Due to the transfer of a smaller (more relevant) portion of the data, a smaller amount of storage space (memory) may be occupied at the off-board location to store the transferred data.In this way, an in-vehicle diagnostic routine may be executed at an engine component, the data may be adapted to one or more functions, parameters of the function and start and end points of the data may be transmitted to an out-of-vehicle location, the OBD data may be reconstructed and analyzed at the out-of-vehicle location, and OBD test results may be updated based on a signal received from the out-of-vehicle location.FIG. 3 illustrates an example method 300 for efficiently adjusting a curve to on-vehicle diagnostic (OBD) data associated with an evaporative emissions control (EVAP) system. The expected curve profile may correspond to a curve fit profile for OBD data collected during a test period without interfering influence by external factors.At 302, the routine includes retrieving all or a portion of the OBD data from the controller memory once an EVAP system diagnostic test is completed and the presence of a leak has been inferred from the data. In one example, the pressure increase phase of the vacuum EVAP system diagnostic test may be used for processing. During conditions when a leak is not detected from the OBD data, the data may not be further processed and thus not retrieved from the controller's memory.At 304, an expected curve profile and set of parameters for EVAP leak test gain data may be retrieved from the control memory. In one example, the expected curve profile may be a polynomial function of a particular order. In another example, the expected curve profile may be an exponential function. The expected curve profile may be based on an expected pressure profile of the EVAP leak test, which in turn is based on engine operating conditions at the time of the EVAP leak test. At 306, the expected curve profile with an expected set of parameters may be used to adapt a first curve set to the increase phase of the EVAP system diagnostic data. A value for the determination coefficient (R 2) of the curve fit may be calculated from the fit(s).At 308, the routine includes determining if the R 2- value of a current curve fit is above a threshold. The R 2- value indicates the quality of the adjustment, and an R 2- value above the threshold confirms that a reliable adjustment has been achieved for the data. Alternatively, to understand the quality of the adjustment, a standard optimization method of minimizing the sum of a square error may be used. The routine may include determining whether the sum of the square error is below a threshold. The sum of the square error is represented by:Where Min(E) is the sum of the square error representing the fitting quality, and a Min(E) value below a threshold confirms that reliable fitting has been achieved for the data. In equation (1), f(x,y) represents time-based data samples and g(x,y) represents the fit curve analytical representation.If it is confirmed that the R 2- value is above the threshold or the sum of the square error is below a threshold, it may be inferred that the EVAP system diagnostic result is correct and has not been affected by external factors such as fuel slosh during unusual road conditions.Therefore, at 310, the detected EVAP system leak may be confirmed, and in response to the curve fit coefficient for the first set of curves being above a threshold, the curve fit parameters and the coefficient for the first set of curves may be transmitted to an off-board location. Additionally, a beginning and end point of the diagnostic dataset and vehicle conditions may be transmitted to the exterior of the vehicle at a time of execution of the diagnostic routine, including engine temperature, engine load, vehicle speed, ambient temperature, altitude, and vehicle location. The entire OBD pressure increase data set of the EVAP system may be reconstructed at the off-board location and used for future diagnosis and maintenance.If it is determined that the R 2- value is below the threshold for R 2 or the sum of the square error is above the threshold, it may be inferred that the expected curve profile did not match the dataset. Thus, at 312, unexpected curve profiles may also be adjusted to the OBD data that may not correspond to the expected pressure increase data during EVAP system leak tests. It may be inferred that vehicle operating conditions (such as an upward ramp or a knock) may have resulted in fuel sloshing, which may have resulted in failures in the diagnostic test. Specifically, fuel sloshing generates additional fuel vapors in the fuel tank, which in turn may result in variations in fuel tank pressure, such variations may affect the pressure increase estimated from outputs of the fuel system pressure sensor. The functions used to adjust the data may include polynomials (different orders), exponential, and Gaussian functions. In one example, the controller may iteratively increase the order of the function, adjust the curve, calculate the R 2- value, and compare it to the threshold until a curve adjustment is achieved with an R 2- value above the threshold.At 313, a single function may be used to fit a single curve to the total pressure increase data of the EVAP system leak test. However, at 314, the gain data may be split into a plurality of segments, and a separate function with a separate parameter set may be used to fit a curve to each segment. The R 2- value may be calculated for each segment and individually compared to the threshold for R 2. An example of a curve fit to pressure increase data of an EVAP system leak test is shown in FIG. 4.At 316, the routine includes determining whether the R 2- value of the curve fit(s) is above the threshold for R 2 or whether the sum of the square error is below a threshold. During conditions when multiple functions are used to fit curves to separate portions of the data, the R 2- value and the sum of the square error values of each curve fit may be compared to the respective thresholds. If it is determined that the R 2- values of one or more of the curve adjustments are below the threshold for R 2 or the sum of the square errors is above the corresponding threshold, at 318, the curve adjustment parameters and curve adjustment function may be updated and the curve adjustment flow continued.At 320, if it is determined that the R 2- values of each of the curve adjustments are above the threshold for R 2 or the sum of the square errors is below the corresponding threshold, it may be inferred that a reliable curve adjustment has been achieved. The curve adjustment parameters, the type of curve adjustment, the beginning and end points of the data may be transmitted to the off-board location where they may be further analyzed, among relevant vehicle operating conditions (such as engine temperature, engine load, vehicle speed, ambient temperature, altitude, and vehicle location). The details of data transfer and further processing have been previously described in FIG. 2 (at 220, 222, and 224).In this way, in response to the curve fit coefficient for a first set of expected curves being below the threshold, one or more further curve sets based on the expected and / or unexpected profile of the diagnostic data may be iteratively selected and the one or more additional curve sets may be fitted to the one or more segments until the curve fit coefficient for one of the one or more further curve sets is above the threshold. Thereafter, the curve fitting coefficient for another set of curves may be transmitted to the off-vehicle location.FIG. 4 shows an example plot fit for diagnostic data of a system for controlling evaporative emissions. The x-axis denotes time and the y-axis denotes pressure in the fuel system as measured by a pressure sensor coupled to the fuel tank. The vertical markers t0-t4 indicate significant times during soot accumulation and regeneration of the PM sensor.Prior to time t0, plot 401 denotes a drop in fuel system pressure (pressure bleed phase) as air is drawn from the fuel system (to atmosphere) via a pump of an evaporative leak check module (ELCM). A switching valve (COV) coupled to the ELCM may be maintained in a first position and the pump may be actuated until the lower pressure in the fuel system reaches the initial point pressure value designated by point 402. Once the fuel system pressure reaches the desired low pressure value, the fuel system may be isolated at time t 0 by closing the canister vent valve (canister purge valve already in closed position) and moving the position of the diverter valve to a second position. The pressure increase in the fuel system may be observed between time t 1 and t 4, and if the final pressure is below a threshold pressure (as indicated by dashed line 415), it may be inferred that the EVAP system is robust and no leak has been detected.After isolation of the fuel system, a pressure build-up may be observed during the vacuum EVAP system leak detection test. Plot 403 shows the pressure increase profile during the test. Between time t 0 and t 1, the pressure increase may continue linearly following an expected tendency. However, at time t 1, an unexpected change in vehicle operating conditions (such as a maneuver) may occur, resulting in fuel sloshing. Fuel may slosh during vehicle maneuvers such as rapidly taken left or right turns (e.g., when the vehicle is turning at speeds above a threshold speed and / or at turn speeds above a threshold), vehicle upward travel (e.g., when the vehicle is traveling along an incline that is above a threshold level), and rough road travel (e.g., when the vehicle is traveling along a route that has a flatness below a threshold). Still other maneuvers that may result in fuel sloshing include motion of the vehicle along undulating road surfaces, aggressive braking maneuvers, and vehicle acceleration along any axis. Fuel slosh may be inferred based on vehicle motion as inferred by a vehicle motion sensor and / or changes in fuel tank pressure. Specifically, fuel sloshing may generate additional fuel vapors in the fuel tank, which in turn may result in fluctuations in fuel tank pressure determined from the output of a fuel system pressure sensor. Due to such variations in fuel tank pressure, a spike in the pressure increase profile may occur between time t 1 and t 3.Due to the variations in fuel system pressure and the consequent peak, the pressure increase profile may not accurately reflect the expected pressure profile for an EVAP system diagnostic test. The pressure may continue to be monitored until time t 4, and the final endpoint pressure value at time t 4 (shown by point 416) may be recorded and compared to the threshold pressure level (line 415). In this example, based on the final fuel system pressure above the threshold (endpoint pressure 416), it may be inferred that there is a leak in the EVAP system at the end of the test period. However, this result may be erroneous and may be caused by fuel slosh (between time t 1 and t 3) leading to variations in fuel system pressure. The pressure data captured between time t 0 and t 1 may be extrapolated to time t 4 (as shown by dashed line 414) and it may be inferred that in the absence of fluctuations due to external sources, the final pressure would have reached the pressure level shown by the expected endpoint pressure 417 that is below the threshold.In one example, a single function can be adapted to the entire pressure increase dataset acquired between time t 0 and t 1. An expected curve profile (function) and expected parameters may be used first to adjust the data. If the expected function and expected parameters do not provide a reliable adaptation to the data, further functions and different parameter sets can be tried iteratively. Based on the profile of the data, a Gaussian curve may be selected to fit the entire dataset. The parameters of the Gaussian curve can be iteratively changed until the value of the determination coefficient (R 2) of the adjustment is above a threshold value. Dashed line 412 shows the Gaussian fit to the pressure increase profile. Dashed line 412 may be denoted by the following function:The constants a, b, and c represent the Gaussian function, and the curve can be reconstructed by using the values of the constants.In another example, the entire pressure increase dataset acquired between time t 0 and t 1 may be divided into a plurality of separate segments, and a separate function may be used to adjust each of the segments. Plot 403 may be divided into four segments, the first segment includes data captured between time t 0 and t 1, the second segment includes data captured between time t 1 and t 2, the third segment includes data captured between time t 2 and t 3, and the fourth segment includes data captured between time t 3 and t 4. Four separate second order polynomial functions having different sets of constants may be used to fit the four segments. The parameters of each of the polynomials may be iteratively changed until the R 2- value of each of the adjustments is above a threshold. A first polynomial shown by line 404 may be denoted by:A second polynomial shown by line 406 may be denoted by:A third polynomial shown by line 408 may be denoted by:A fourth polynomial shown by line 410 may be denoted by:The constants m 1, b 1, m 2, b 2, m 3, b 3, m 4 and b 4 represent the second-order polynomial functions, and the entire pressure increase data set can be reconstructed by using the values of the constants.Once a reliable adjustment of the pressure increase profile has been achieved, the curve adjustment parameters may be transmitted to an off-board location, such as one of a remote server, an off-board controller, and a network cloud that is mutually coupled to the vehicle. In one example, parameters of a polynomial curve that are transmitted include the shape of the curve (Gaussian curve and second order polynomial in this example), one or more coefficients (constants) of the function used, and R 2- value(s) of the curve fit. Further, a beginning point and ending point of the diagnostic dataset, i.e., a pressure corresponding to beginning point 402 and ending point 416, and vehicle conditions at a time of execution of the diagnostic routine, including engine temperature, engine load, vehicle speed, ambient temperature, altitude, and vehicle location, may also be transmitted outside the vehicle.The entire dataset may be reconstructed at the off-board location and further analyzed with reference to vehicle operating conditions. After data analysis at the off-board location, a signal may be received (from the off-board location) at the on-board controller to update the result of the test and the corresponding engine operating conditions. The stored data set may also be accessed (from the off-board location) by technicians during future vehicle maintenance.In this way, a function can be efficiently matched to OBD data, the parameters of the function can be transmitted to an off-board location, and the data can be later reconstructed and used for analysis of the diagnosis. Thus, a similar method of curve fitting and data processing may be employed for other EVAP system tests, such as a positive pressure test, and for in-vehicle diagnostics (OBD) of any vehicle component, such as the exhaust aftertreatment system, the turbocharger system, the exhaust gas recirculation system, etc.FIG. 5 shows an example operating sequence 500 illustrating a diagnostic routine of an evaporative emissions control (EVAP) system. The diagnostic routine may be executed using an evaporative leak check module coupled to the engine EVAP system. The horizontal (x-axis) denotes time and the vertical markers t0-t6 indicate important points in time during the diagnostic routine.The first plot, line 502, shows operation of an ELCM pump. The second plot, line 504, shows a position of the diverter valve (COV) coupled to the ELCM system. The third plot, line 506, shows a variation in EVAP system pressure over time as estimated via a pressure sensor coupled to the fuel system. The first dashed line 507 shows a lower pressure threshold corresponding to a start point for a pressure increase test after applying a vacuum to the fuel vapor system. The second dashed line 508 shows an upper pressure threshold corresponding to a completion point of the pressure increase test. The fourth plot, line 510, represents an indicator that may be set in response to detecting a leak in the EVAP system.Prior to time t 1, the ELCM pump may be inactive because the EVAP system diagnostic test is not performed during this period. The COV may be in a first position and decouple communication between the pump and the EVAP system. During this period, the EVAP system may also not be fluidly connected to the engine (via a canister purge valve) and to the atmosphere (via a canister vent valve). The EVAP system pressure may be maintained at a level above the upper threshold.At time t 1, an EVAP system diagnostic test may be initiated. Initiation of the test may occur if a threshold time has elapsed since the last iteration of the diagnostic routine and the passenger compartment is unoccupied. The test may be performed periodically and / or based on the availability of favorable conditions (such as natural vacuum availability with the engine off). In response to initiation of the test, the COV may be moved to a second position to couple the EVAP system to the atmosphere via the ELCM pump. The pump may be activated (turned on) and air may be drawn from the EVAP system to the atmosphere. Between time t 1 and t 2, pressure in the EVAP system may steadily decrease as air is drawn from the EVAP system.At time t 2, the EVAP system pressure may decrease to the lower threshold pressure. The vacuum EVAP system diagnostic test may be initiated using this lower EVAP system pressure. Therefore, at this time, the ELCM pump may be deactivated (deactivated) and the COV may be moved to the first position to decouple the pump from the EVAP system. Additionally, the canister vent valve may be closed (and the canister purge valve maintained in the closed position) to isolate the EVAP system. Once the EVAP system has been isolated, the gain profile of the EVAP system may be observed for a predetermined duration (time between t2and t3).At time t 3, after the predetermined amount of time has elapsed, the final EVAP system pressure may be recorded. The final fuel system pressure may be above the upper threshold, and a leak in the EVAP system may be inferred based on the EVAP system pressure above the upper threshold. In response to detecting the leak in the EVAP system, a flag may be set to indicate the presence of a leak. Additionally, engine operation may be discontinued in response to detecting the leak. For example, the canister purge schedule may be updated to schedule canister purges more frequently, regardless of canister loading, so that fuel vapor in the evaporative emissions fuel system and / or system is efficiently directed to the engine for combustion.Also at time t 3, a best fit curve may be fitted to the pressure increase data acquired between time t 2 and t 3. The type of expected curve for this data can be retrieved from the control store. A value for the determination coefficient (R 2) may be calculated for the adjustment and compared to a threshold value for R 2. If the expected curve does not provide an adjustment above the threshold, one or more other curves (such as polynomials of different orders, exponential curves, Gaussian curves) may be iteratively tried until a curve adjustment with an R 2- value above the threshold is achieved. Once a reliable curve fit has been achieved, the coefficients of the curve(s) and the R 2- value(s) may be transmitted to an off-board location. Additionally, the initial and final data points, as well as vehicle operating conditions, may be transmitted to the off-board location during the test, such as temperature, altitude, vehicle speed, vehicle location, fuel level, engine load, etc. At the off-vehicle location, the entire dataset may be reconstructed using the curve fit coefficients and further analyzed. The vehicle controller may receive instructions from the off-board location, opportunistically retry the EVAP system diagnostic test after a threshold amount of time, and update EVAP system leak test results and engine operations based on the retry test. Additionally, a curve fit shape and parameters may be received from the off-board location for the next EVAP system diagnostic test.Between time t 3 and t 4, the flag indicating a leak in the EVAP system may be maintained and an updated canister purge routine may be used. At time t 4, it may be inferred that the threshold period has elapsed and conditions are beneficial to repeat the EVAP system leak test. Therefore, the COV may be actuated to the second position and the ELCM pump may be activated to reduce the EVAP system pressure to the lower pressure threshold. At time t 5, based on input from the fuel system pressure sensor, it may be inferred that the EVAP system pressure has been reduced to the lower threshold pressure and the vacuum test may be initiated. To initiate the pressure increase test, the EVAP system may be isolated by moving the COV to the first position and closing the canister vent valve. In addition, the ELCM pump may be deactivated.Between time t 5 and t 6, the increase profile of the EVAP system pressure may be observed and the EVAP system pressure recorded at time t 6. Thus, the duration of the second increase test (from time t 5 to t 6) may be equal to the duration of the first increase test (from time t 2 to t 3). At time t 6, based on the input from the fuel system pressure sensor, it may be inferred that the final pressure at the end of the second increase test may be below the upper threshold. Due to the EVAP system pressure below the upper threshold, it may be inferred that there is no leak in the EVAP system and the previous test (first gain test) had resulted in an erroneous result due to external factors such as vehicle maneuvers that lead to fuel sloshing. In response to the EVAP system being robust and not having any leaks, the flag indicating a fuel system leak may be removed and engine operations may also be updated. For example, the frequency of the canister purge schedule may be reduced and the canister may be opportunistically purged based on canister loading. In this way, the EVAP system diagnostic test may be repeated based on a signal received from the off-board location, and an erroneous indication of an EVAP system leak may be updated.An example method for a vehicle including an engine includes adjusting a function to one or more segments of a diagnostic dataset for an engine component within the vehicle, and transmitting parameters of the function, and not the one or more segments of the dataset, to an off-board location. Any preceding example further comprises, additionally or optionally, estimating an output state of the engine component based on the diagnostic data within the vehicle, and updating the output state based on a signal received from the off-vehicle location, and adjusting engine operation based on the updated state, the signal based on the transmitted parameters. Any or all of the preceding examples further include, additionally or optionally, transmitting a shape of the function in addition to the parameters of the function, wherein the function is a polynomial curve. In any or all of the preceding examples, additionally or optionally, the parameters of the polynomial curve include one or more coefficients of a polynomial of the polynomial curve and a coefficient of determination (R 2) of the polynomial curve. In any or all of the preceding examples, adjusting the curve and transmitting additionally or optionally includes: selecting a first set of curves based on an expected profile of the diagnostic data, the expected profile based on the engine component for which a diagnostic is being performed, adjusting the first set of curves to the one or more segments, and in response to a curve adjustment coefficient for the first set of curves being above a threshold, transmitting the curve adjustment coefficient for the first set of curves to the off-vehicle location. In any or all of the preceding examples, additionally or optionally, the curve fit includes: responsive to the curve fit coefficient for the first set of curves being below the threshold, selecting a second set of curves based on the expected profile of the diagnostic data, fitting the second set of curves to the one or more segments, and transmitting the curve fit coefficient for the second set of curves to the off-board location. In any or all of the preceding examples, additionally or optionally, the curve fit includes: responsive to the curve fit coefficient for the first set of curves being below the threshold, iteratively selecting one or more further sets of curves based on the expected profile of the diagnostic data and fitting the one or more further sets of curves to the one or more segments until the curve fit coefficient for one of the one or more further sets of curves is above the threshold, and then transmitting the curve fit coefficient for the further set of curves to the out-of-vehicle location. In any or all of the preceding examples, additionally or optionally, the engine component includes a fuel system coupled to the engine, and wherein the diagnostic dataset includes a fuel tank pressure profile generated during an evaporative emissions leak test, and adjusting engine operation includes increasing a frequency of purging a fuel system canister to the engine. Any or all of the preceding examples further additionally or optionally include transmitting data corresponding to a start point and an end point of the dataset to the off-board location. In any or all of the preceding examples, additionally or optionally, transmitting to the off-board location includes transmitting to one of a remote server, an off-board controller, and a network cloud that is mutually coupled to the vehicle. Any or all of the preceding examples further additionally or optionally include selecting the polynomial curve based on a type of diagnostic test, wherein the selecting includes selecting a first polynomial equation for a positive pressure evaporative emissions leak test and selecting a second polynomial equation for a negative pressure evaporative emissions leak test.Another example method for a vehicle includes generating a first dataset by performing a diagnostic routine for a vehicle component, fitting a curve having an adjustment coefficient above a threshold to at least one segment of the first dataset, the curve selected based on an expected profile of the first dataset, transmitting the curve adjustment coefficient to a location external to the vehicle; and determining a diagnostic state of the vehicle component based on the generated first dataset. In the preceding example, additionally or optionally, the determination of the diagnostic state of the vehicle component within the vehicle is further based on the curve adjustment coefficient. Any or all of the preceding examples further include, additionally or optionally, transmitting a start point and end point of the first dataset and vehicle conditions to the exterior of the vehicle at a time of execution of the diagnostic routine, including engine temperature, engine load, vehicle speed, ambient temperature, altitude, and vehicle location. Any or all of the preceding examples further additionally or optionally include receiving, from outside the vehicle, an updated diagnostic state of the vehicle component, and adjusting, within the vehicle, one or more operating parameters of the vehicle based on the updated diagnostic state. In any or all of the preceding examples, additionally or optionally, the updated diagnostic state is based on a reconstructed dataset reconstructed external to the vehicle using the start point, end point, and curve fit coefficients. Any or all of the preceding examples further include, additionally or optionally, receiving a shape of a curve fitting function, generating a second dataset by repeating the diagnostic routine for the vehicle component, fitting a curve with the received shape of the curve fitting function to at least one segment of the second dataset, transmitting an updated curve fitting coefficient to the location external to the vehicle; and determining an updated diagnostic state of the vehicle component based on the generated second dataset. Any or all of the preceding examples further include, additionally or optionally, indicating fuel slosh in a fuel tank based on the diagnostic routine dataset and further based on the updated diagnostic state received from outside the vehicle.In yet another example, a fuel system for a vehicle includes a fuel tank, an evaporative emissions control (EVAP) system including a fuel vapor canister coupled to the fuel tank via a shut-off valve, a canister purge valve (CPV) disposed in a purge line between the fuel vapor canister and an engine intake manifold, a canister vent valve (CV) disposed in a vent line between the fuel vapor canister and the atmosphere, and a pressure sensor coupled to the fuel tank, a wireless communication device communicatively coupling the vehicle to an off-vehicle controller, and an on-vehicle controller disposed within the vehicle configured with computer readable instructions, storing on non-volatile memory: performing an EVAP system diagnostic test by applying vacuum with the EVAP system; isolating the EVAP system from the engine and the atmosphere by closing each of the vent valve and the purge valve; and observing an actual pressure increase profile across the pressure sensor responsive to a rate of pressure increase above a threshold; indicating degradation of the EVAP system; adjusting a frequency of opening of the CPV during engine operation based on the indication; adjusting the actual pressure increase profile using a curve profile having a coefficient of determination (R2) above a threshold, wherein the curve profile is selected from a curve profile set based on an expected pressure increase profile, and uploading each of one or more coefficients of the curve profile, the R 2, a start point, and an end point of the actual pressure increase profile with the off-board controller. In the preceding example, additionally or optionally, the indicating degradation includes an initial indication, wherein the controller includes further instructions to: based on an input received from the off-vehicle controller, update the initial indication of degradation, and further adjust a frequency of opening the CPV based on the received input. In any or all of the preceding examples, additionally or optionally, adjusting the actual pressure increase profile includes adjusting one or more curves of the curve profile set to one of the entire dataset or portions of the dataset corresponding to the actual pressure increase profile, wherein the one of the curves includes a polynomial curve, an exponential curve, and a Gaussian curve.In this way, by fitting a polynomial curve to diagnostic data generated within the vehicle and transmitting parameters of the curve and other relevant details of the test to an off-board location, it may be possible to facilitate real-time and future analysis of diagnostic data to an off-board location. By using signals received at an off-board controller from the off-board location, the results from a faulty diagnostic test may be updated and engine operations adjusted appropriately. The technical effect of transmitting only the curve fit parameters and the beginning and end points of the data to an off-board location is that faster data transmission to the off-board location can be achieved using a lower bandwidth. Additionally, due to the transfer of a smaller portion of the data, a smaller amount of memory may be occupied at the off-board location. Overall, by adjusting a curve and transmitting a smaller amount of data, the entire OBD dataset may be rendered and analyzed at an off-board location, thereby increasing the accuracy and reliability of the off-board data analysis. By updating the diagnostic test results based on data analyzed at an off-board location, vehicle performance is improved.In another representation, an example method for a system including a vehicle having an in-vehicle controller and an out-of-vehicle processing system may include, at the in-vehicle controller: adjusting a function on one or more segments of a diagnostic dataset for an engine component within the vehicle; and transmitting parameters of the function, and not the one or more segments of the dataset, to the out-of-vehicle location, and at the out-of-vehicle system, at a processor, reconstructing the one or more segments via the function and the parameters, determining degradation of one or more components within the vehicle based on the reconstructed segments, and returning, to the in-vehicle controller, a determined degradation state indication. The off-board system may further include transmitting updated calibration data for the vehicle to the off-board controller based on the transmitted parameters and / or function, wherein operation of the vehicle engine and / or the valve controller is adjusted based on the updated calibration data.It should be appreciated that the example control and estimation routines included herein may be used with various engine and / or vehicle system configurations. The control methods and routines disclosed herein may be stored as executable instructions in non-transitory memory and executed by the control system including the controller in combination with the various sensors, actuators, and other engine hardware. The specific routines described herein may represent one or more of any number of processing strategies such as event-driven, interrupt-driven, multi-tasking, multi-threading, and the like. As such, various illustrated acts, acts, and / or functions may be performed in the order illustrated, in parallel, or in some cases omitted. Likewise, the order of processing is not necessarily required to achieve the features and advantages of the example embodiments described herein, but rather is provided for ease of illustration and description. One or more of the illustrated acts, operations, and / or functions may be repeatedly performed depending on the particular strategy being employed. Further, the described acts, operations, and / or functions may graphically represent code to be programmed into non-transitory memory of the computer readable storage medium in the engine control system, in which the described acts are performed by executing the instructions in a system including the various engine hardware components in combination with the electronic controller.It should be understood that the configurations and routines disclosed herein are exemplary in nature and these specific embodiments are not to be interpreted in a limiting sense as numerous variations are possible. For example, the above technology may be applied to V6, I4, I6, V12, 4-cylinder horizontally opposed, and other engine types.

Claims

A method for a vehicle including an engine (10), comprising: adjusting (218) a function on one or more segments of a diagnostic dataset for an engine component within the vehicle; including: selecting (304) a first dataset and adjusting (306) the first dataset on the one or more segments; and transmitting (220; 320) parameters of the function, and not the one or more segments of the dataset, to an off-vehicle location; responsive to a curve adjustment coefficient for the first dataset being above a threshold, transmitting (220; 320) the curve adjustment coefficient for the first dataset to the off-vehicle location.The method of claim 1, further comprising estimating (202) an output state of the engine component based on the diagnostic data within the vehicle; and updating (224) the output state based on a signal received from the off-vehicle location, and adjusting engine operation based on the updated state, wherein the signal is based on the transmitted parameters.The method of claim 1, further comprising transmitting (220; 320) a shape of the function in addition to the parameters of the function, wherein the function is a polynomial curve, wherein the parameters of the polynomial curve include one or more coefficients of a polynomial of the polynomial curve and a determination coefficient (R 2) of the polynomial curve.The method of claim 1, wherein adjusting (306) the curve and transmitting (220; 320) includes: selecting (304) the first set of curves based on an expected profile of the diagnostic data, the expected profile based on the engine component for which a diagnostic is being performed.The method of claim 4, wherein the curve fitting further comprises: in response to the curve fitting coefficient for the first set of curves being below the threshold, selecting (304) a second set of curves based on the expected profile of the diagnostic data; fitting (306) the second set of curves to the one or more segments; and transmitting (220; 320) the curve fitting coefficient for the second set of curves to the out-of-vehicle location.The method of claim 4, wherein the curve fitting further comprises: responsive to the curve fitting coefficient for the first set of curves being below the threshold, iteratively selecting (304) one or more further sets of curves based on the expected profile of the diagnostic data and fitting (306) the one or more further sets of curves to the one or more segments until the curve fitting coefficient for one of the one or more further sets of curves is above the threshold; and then transmitting (220; 320) the curve fitting coefficient for a further set of curves to the out-of-vehicle location.The method of claim 1, wherein the engine component includes a fuel system (18) coupled to the engine (10), and wherein the diagnostic dataset includes a fuel tank pressure profile generated during an evaporative emissions leak test, and adjusting engine operation includes increasing a frequency of purging a fuel system canister (22) to the engine (10).The method of claim 1, further comprising transmitting (220; 320) data corresponding to a start point and an end point of the data set to the off-vehicle location.The method of claim 1, wherein transmitting (220; 320) to the off-board location includes transmitting (220; 320) to one of a remote server, an off-board controller, and a network cloud that is mutually coupled to the vehicle.The method of claim 7, further comprising selecting (304) the polynomial curve based on a type of diagnostic test, wherein the selecting (304) includes selecting (304) a first polynomial equation for a positive pressure evaporative emissions leak test and selecting (304) a second polynomial equation for a negative pressure evaporative emissions leak test.A method for a vehicle, comprising: generating a first dataset by performing a diagnostic routine for a vehicle component, adjusting (306) a curve having an adjustment coefficient above a threshold to a segment of the first dataset, the curve selected based on an expected profile of the first dataset; transmitting (220; 320) the curve adjustment coefficient to a location external to the vehicle; and determining a diagnostic state of the vehicle component based on the generated first dataset.The method of claim 11, wherein determining a diagnostic condition of the vehicle component within the vehicle is further based on the curve adjustment coefficient.The method of claim 11, further comprising: transmitting (220; 320) a start point and end point of the first data set and vehicle operating conditions to the area outside the vehicle at a time of execution of the diagnostic routine including engine temperature, engine load, vehicle speed, ambient temperature, altitude, and vehicle position.The method of claim 11, further comprising: receiving, from outside the vehicle, an updated diagnostic state of the vehicle component; and adjusting, within the vehicle, one or more operating parameters of the vehicle based on the updated diagnostic state.The method of claim 14, wherein the updated diagnostic condition is based on a pre-constructed dataset reconstructed outside the vehicle using the start point, end point, and curve fit coefficient, further comprising: receiving a shape of a curve fit function; generating a second dataset by repeating the diagnostic routine for the vehicle component; fitting (306) a curve having the received shape of the curve fit function to at least one segment of the second dataset; transmitting (220; 320) an updated curve fit coefficient to the location outside the vehicle; and determining an updated diagnostic condition of the vehicle component based on the generated second dataset.

Images