Abstract: A system for monitoring operation of a vehicle includes a processing device including an interface configured to receive measurement data from sensing devices configured to measure parameters of a vehicle system. The processing device is configured to receive measurement data from each of the plurality of sensing devices, and in response to detection of a malfunction in the vehicle, input at least a subset of the measurement data to a machine learning classifier associated with a vehicle subsystem, the classifier configured to define a class associated with normal operation of the vehicle subsystem. The processing device is also configured to determine whether the subset of the measurement data belongs to the class, and based on at least a selected amount of the subset of the measurement data being outside of the class, output a fault indication, the fault indication identifying the vehicle subsystem as having a contribution to the malfunction.

Abstract: A system and method for personalization of adjustable features of a vehicle. The system includes a processor and an actuator. The processor detectors key points of a person from a two-dimensional image and predicts a pose of the person. The processor translates a respective position of the key points from a two-dimensional coordinate system to a three-dimensional coordinate system based in part on the pose and measurements of distances between the key points. The processor determines a baseline configuration of an adjustable feature of the vehicle based in part on measurements between the key points in the three-dimensional coordinate system. The processor causes an actuator to adjust the adjustable feature to conform to the baseline configuration.

Abstract: A vehicle including an advanced driver-assistance system (ADAS) and operator-adjustable devices is described. Controlling the vehicle includes identifying a vehicle operator, and capturing a plurality of operator-selectable settings associated with the plurality of operator-adjustable devices for the vehicle operator. A base profile and a second profile are determined for the vehicle operator based upon the first subset associated with non-autonomous operation of the vehicle and the second subset associated with ADAS, respectively. The plurality of operator-adjustable devices are controlled to the operator-selectable settings associated with the base profile when the vehicle is operating in the non-autonomous mode, and the plurality of operator-adjustable devices are controlled to the operator-selectable settings associated with the second profile when the vehicle is being controlled at least in part by one or more of the subsystems of the ADAS.

Abstract: A method of identifying air flow faults within a cooling system of an automobile comprises measuring the temperature of coolant entering a heat exchanger for the cooling system, measuring the temperature of coolant leaving the heat exchanger, and measuring the temperature of ambient air that is flowing into the heat exchanger, calculating Actual Delta T by subtracting the temperature of coolant leaving the heat exchanger from the temperature of coolant entering the heat exchanger, calculating Expected Delta T, wherein Expected Delta T is a pre-determined value of an expected difference between the temperature of the coolant entering the heat exchanger and the temperature of the coolant leaving the heat exchanger, calculating Effective Delta T by subtracting Expected Delta T from Actual Delta T, and identifying a fault in the air flow through the heat exchanger based on the value of Effective Delta T.

Abstract: A method of diagnosing a leak in a coolant system of an automobile includes repeatedly measuring the coolant level within the coolant system at a pre-determined time interval, calculating a short term leak rate, wherein the short term leak rate is the rate of coolant leakage over a first pre-determined length of time, calculating a long term leak rate, wherein the long term leak rate is the rate of coolant leakage over a second pre-determined length of time, further wherein the second pre-determined length of time is longer than the first pre-determined length of time, identifying a coolant system leakage state based on a current coolant level within the coolant system, the short term leak rate, and the long term leak rate, and providing notification of the coolant system leakage state to an operator of the vehicle.

Abstract: A fault diagnostic system includes: memory including a fault model, the fault model including: a plurality of failure modes of a vehicle; and symptoms respectively associated with each of the failure modes; an updating module configured to: based on a data set, determine a new failure mode that is not already included in the fault model and new symptoms indicative of the occurrence of the new failure mode; modify the fault model by: adding the new failure mode to the fault model; and adding the new symptoms to the fault model in association with the new failure mode; and re-save the fault model in the memory.

Abstract: A method of identifying air flow faults within a cooling system of an automobile comprises measuring the temperature of coolant entering a heat exchanger for the cooling system, measuring the temperature of coolant leaving the heat exchanger, and measuring the temperature of ambient air that is flowing into the heat exchanger, calculating Actual Delta T by subtracting the temperature of coolant leaving the heat exchanger from the temperature of coolant entering the heat exchanger, calculating Expected Delta T, wherein Expected Delta T is a pre-determined value of an expected difference between the temperature of the coolant entering the heat exchanger and the temperature of the coolant leaving the heat exchanger, calculating Effective Delta T by subtracting Expected Delta T from Actual Delta T, and identifying a fault in the air flow through the heat exchanger based on the value of Effective Delta T.

Abstract: A system for monitoring operation of a vehicle includes a processing device including an interface configured to receive measurement data from sensing devices configured to measure parameters of a vehicle system. The processing device is configured to receive measurement data from each of the plurality of sensing devices, and in response to detection of a malfunction in the vehicle, input at least a subset of the measurement data to a machine learning classifier associated with a vehicle subsystem, the classifier configured to define a class associated with normal operation of the vehicle subsystem. The processing device is also configured to determine whether the subset of the measurement data belongs to the class, and based on at least a selected amount of the subset of the measurement data being outside of the class, output a fault indication, the fault indication identifying the vehicle subsystem as having a contribution to the malfunction.

Abstract: A method of diagnosing a propulsion system implements a top-down hierarchical examination procedure, in which the propulsion system is analyzed as a whole to determine if the propulsion system is healthy. Data from a first set of vehicle sensors is compared to a system-healthy data cluster to determine if the propulsion system is healthy or unhealthy. If the propulsion system is unhealthy, then a plurality of subsystems of the propulsion system are each analyzed at a first examination level using selective data from the sensors to identify one of the subsystems as an unhealthy subsystem. A plurality of component systems of the unhealthy subsystem are then analyzed at a second examination level using other selective data from the sensors to identify one of the component systems of the unhealthy subsystem as an unhealthy component system.

Abstract: A scheduling controller in communication with a plurality of autonomous vehicles is described, and includes an operator request compiler, a fleet state-of-health database, an environmental conditions compiler and a fleet scheduling controller. The fleet scheduling controller is configured to deploy the autonomous vehicles based upon inputs from the operator request compiler, the fleet state-of-health database and the environmental conditions compiler. A process for coordinating a fleet of autonomous vehicles includes determining states of health for the autonomous vehicles, and determining a desired autonomous vehicle use requirement from each of a plurality of operators that are associated with the autonomous vehicles. A usage schedule for each of the autonomous vehicles is determined based upon the states of health and the desired autonomous vehicle use requirements from the operators. The autonomous vehicles are deployed based upon the usage schedule.

Abstract: A vehicle including a fluidic subsystem composed of an electric motor, a motor driver and a fluidic pump that is disposed in a fluidic circuit of the vehicle is described. A controller includes an instruction set that is executable to determine operating parameters associated with the fluidic subsystem, and determine a plurality of power efficiency parameters for the fluidic subsystem based upon the operating parameters. The power efficiency parameters include a hydraulic power efficiency, an electro-mechanical power efficiency and an electric power efficiency. The controller can determine a state of health for the fluidic subsystem based upon the power efficiency parameters, and detect a fault in the fluidic subsystem when the state of health is less than a threshold state of health. The fault can be communicated to a vehicle operator.

Abstract: A method for use with a vehicle having one or more subsystems includes receiving vehicle health management (VHM) information via a controller indicative of a state of health of the subsystem. The VHM information is based on prior testing results of the subsystem. The method includes determining a required testing profile using the testing results, applying the testing profile to the subsystem to thereby control a state of the subsystem, and measuring a response of the subsystem to the applied testing profile. The method also includes recording additional testing results in memory of the controller that is indicative of a response of the subsystem to the applied testing profile. The vehicle includes a plurality of subsystems and a controller configured to execute the method.

Abstract: A perception module of a spatial monitoring system to monitor and characterize a spatial environment proximal to an autonomous vehicle is described. A method for evaluating the perception module includes capturing and storing a plurality of frames of data associated with a driving scenario for the autonomous vehicle, and executing the perception module to determine an actual spatial environment for the driving scenario, wherein the actual spatial environment for the driving scenario is stored in the controller. The perception module is executed to determine an estimated spatial environment for the driving scenario based upon the stored frames of data associated with the driving scenario, and the estimated spatial environment is compared to the actual spatial environment for the driving scenario. A first performance index for the perception module is determined based upon the comparing, and a fault can be detected.

Abstract: A method of, and a system for, controlling and predicting the health of a torque converter clutch control system is provided. The method includes determining, via a controller, rotational input and output speeds of the torque converter and a torque converter clutch slip. The method also includes determining, via the controller, whether a set of predetermined conditions are met for predicting the health of the torque converter clutch control system. The method includes gathering a plurality of initial features of the vehicle propulsion system, determining statistical information about the plurality of initial features, and selecting at least one feature of the vehicle propulsion system based on the statistical information. Furthermore, the method includes classifying the health of the torque converter clutch control system based on the selected feature or features. In some forms, principal component analysis is used to select the feature or features used for classification.

Abstract: A method of predicting the health of and controlling a hydraulic pressure actuated torque converter lock-up clutch includes determining rotational input and output speeds of the torque converter. The method also includes determining a magnitude of the hydraulic pressure. The method additionally includes determining a level of performance of the clutch across multiple torque converter operating modes using the determined input and output torque converter speeds and the determined magnitude of the hydraulic pressure. The method also includes calculating a numeric state of health (SOH) coefficient of the clutch that quantifies a relative severity of degradation of a plurality of clutch characteristics across the multiple torque converter operating modes. Furthermore, the method includes executing a control action relative to the clutch when the calculated numeric SOH coefficient for specified torque converter operating mode(s) is less than a calibrated SOH threshold.

Abstract: A method proactively transitions performance of a functional operation from a primary subsystem to a secondary subsystem within a vehicle or other system having an electronic control unit (ECU). The method includes receiving health management information via the ECU when the primary subsystem is actively performing the functional operation within the system and the secondary subsystem operates in a standby mode, wherein the health information is indicative of a numeric state of health (SOH) of the primary subsystem. The method also includes comparing the numeric SOH to a calibrated non-zero threshold SOH, and then commanding, via the ECU, a transition of the performance of the functional operation to the secondary subsystem and placing the primary subsystem in the standby mode when the numeric SOH is less than the calibrated non-zero threshold SOH. A vehicle executes the method via the ECU.

Abstract: A controller architecture for monitoring an autonomic vehicle control system includes a first controller, a second controller, a telematics controller, a third controller, a plurality of subsystem controllers, a first and a second communication bus, and a first and a second communication link. The telematics controller in communication with the first controller. The second controller includes a second processor and a second memory device. Each subsystem controller is configured to effect operation of one of a subsystem, wherein each of the subsystem controllers includes a vehicle health monitor (VHM) agent. The third controller includes a third processor and a third memory device. A first instruction set includes a prognostic classification routine based upon inputs from the VHM agents of the plurality of subsystem controllers. The telematics controller is disposed to communicate an output from the prognostic classification routine to an off-board controller.

Abstract: A vehicle including a fluidic subsystem composed of an electric motor, a motor driver and a fluidic pump that is disposed in a fluidic circuit of the vehicle is described. A controller includes an instruction set that is executable to determine operating parameters associated with the fluidic subsystem, and determine a plurality of power efficiency parameters for the fluidic subsystem based upon the operating parameters. The power efficiency parameters include a hydraulic power efficiency, an electro-mechanical power efficiency and an electric power efficiency. The controller can determine a state of health for the fluidic subsystem based upon the power efficiency parameters, and detect a fault in the fluidic subsystem when the state of health is less than a threshold state of health. The fault can be communicated to a vehicle operator.

Abstract: Methods and apparatus are provided for determining an offset detection for a fuel level sensor fault. The method includes receiving an electrical resistance reading from a potentiometer of a fuel level sensor and generating an estimated fuel level based on an established fuel usage table that references the electrical resistance reading. The fuel level sensitivity is calculated based on the change in electrical resistance readings divided by the change in the estimated fuel levels (R/F). The fuel level sensitivity is compared to a predetermined sensitivity curve to determine any necessary offset to the electrical resistance reading. Finally, the fuel usage table is updated with the offset to the electrical resistance reading.

Abstract: A thermal management system includes an electric coolant pump, power source, and controller. The pump is in fluid communication with a heat source and a radiator, and has pump sensors for determining a pump voltage, speed, and current. The battery energizes the sensors. The controller receives the voltage, speed, and current from the sensors, determines a performance of the pump across multiple operating regions, calculates a numeric state of health (SOH) quantifying degradation severity for each of a plurality of pump characteristics across the regions, and executes a control action when the calculated numeric SOH for any region is less than a calibrated SOH threshold. The pump characteristics include pump circuit, leaking/clogging, bearing, and motor statuses. A vehicle includes an engine or other heat source, a radiator; and the thermal management system. The controller may execute a prognostic method for the electric coolant pump in the vehicle.