Abstract: An electric vehicle, system and method of charging the electric vehicle. In another exemplary embodiment, a system for charging an electric vehicle is disclosed. The system includes a first battery subpack, a second battery subpack, and a processor. The processor is configured to determine a selected battery subpack from the first battery subpack and the second battery subpack for charging based on a comparison of a first state of charge of the first battery subpack a second state of charge of the second battery subpack and connect the selected battery subpack to a corresponding one of a first charge port and a second charge port.

Abstract: A vehicle, system and a method of predicting a thermal runaway event in a battery pack. The vehicle includes a battery pack having a plurality of battery cells. The system includes a sensor and a processor. The measures a parameter of a battery cell of a battery pack of the vehicle. The processor is configured to determine a charging response of the battery cell from the parameter, determine a likelihood of the thermal runaway event from the charging response, and control an operation of the vehicle to prevent the thermal runaway event based on the likelihood.

Abstract: A vehicle operates a system and method of predicting a thermal runaway event in a battery pack of the vehicle. The battery pack includes a battery cell. The sensor obtains measurements of a parameter of the battery cell at a plurality of times. The processor is configured to determine a value of at least one feature of the battery cell from the measurements of the parameter, determine a likelihood of the thermal runaway event from the value of the at least one feature, and take an action to prevent the thermal runaway event from occurring based on the likelihood.

Abstract: A system in a vehicle includes memory to store driving history and charging history of the vehicle. The system also includes a processor to obtain a predicted battery life of one or more battery packs of the vehicle based on the driving history and the charging history, obtain a targeted battery life of a user indicating a mileage goal for a specific charge capacity of the one or more battery packs, and determine a difference between the predicted battery life and the targeted battery life. The processor solves an optimization problem to determine a future charging strategy to achieve the targeted battery life and controls an onboard charging system or an external charger based on the future charging strategy or controls routing or navigation based on the future charging strategy.

Abstract: A solar loading-based system includes a memory, a solar load prediction module, and an eco-routing module. The memory is configured to store map information and environment information. The solar load prediction module is configured, based on the map information and the environment information, to (i) determine a route of a host vehicle, (ii) predict solar loading on the host vehicle along the route, and (iii) predict an amount of energy to be consumed by the host vehicle over the route based on the predicted solar loading. The eco-routing module is configured, based on the amount of energy to be consumed by the host vehicle over the route, to at least one of (i) determine whether to follow the route, or (ii) inform a user of the route and the predicted amount of energy to be consumed over the route.

Abstract: A solar loading-based system includes a memory, a disturbance prediction module, a cabin temperature estimation module and a thermal control module. The memory stores a cabin thermal load model of an interior cabin of a host vehicle and a solar load prediction model. The disturbance prediction module: receives signals indicative of states of cabin thermal actuators and comfort metrics; and predicts an effect of solar loading over a known portion of a predicted route including predicting cabin temperatures based on the solar load prediction model, the states of the cabin thermal actuators, and the comfort metrics. The cabin temperature estimation module, based on the cabin thermal load model, determines a first comfort metric based on the predicted cabin temperatures. The thermal control module controls cabin thermal actuators to adjust cabin states, including the first comfort metric, to respective target values based on the predicted effect of solar loading.

Abstract: A distributed learning system of a vehicle includes: a control module configured to: control a plant of the vehicle using a policy; send signals to a learning module including information on an impact of the control on the plant; and selectively control the plant using exploratory control; and the learning module, where the learning module is separate from the control module and is configured to selectively update the policy based on (a) the signals from the control module, (b) state parameters resulting from the control of the plant using the policy, and (c) performance feedback determined based on the control of the plant using the policy and the selective control of the plant using exploratory control, where the control module is configured to receive the exploratory control from the learning module.

Abstract: A computer for an energy management system of an electric vehicle includes a processor. The computer further includes a memory including instructions such that the processor is programmed to determine a value function V based on a plurality of actions U in a plurality of states S. The processor is further programmed to select an action associated with a highest reward value at a current state S. The action U is an HVAC subsystem variable. The state S is a traction power drawn from a rechargeable energy storage system (RESS) to operate a traction subsystem, a base power input drawn from the RESS to operate an HVAC subsystem, a nominal reference cabin heat input set-point determined by the local HVAC processor, an acceleration of the electric vehicle, a current vehicle speed, an average vehicle speed, and a calibrated average vehicle speed estimate.

Abstract: A computer for an energy management system of an electric vehicle includes a processor. The computer further includes a memory including instructions such that the processor is programmed to determine a value function V based on a plurality of actions U in a plurality of states S. The processor is further programmed to select an action associated with a highest reward value at a current state S. The action U is an HVAC subsystem variable. The state S is a traction power drawn from a rechargeable energy storage system (RESS) to operate a traction subsystem, a base power input drawn from the RESS to operate an HVAC subsystem, a nominal reference cabin heat input set-point determined by the local HVAC processor, an acceleration of the electric vehicle, a current vehicle speed, an average vehicle speed, and a calibrated average vehicle speed estimate.

Abstract: An energy management system for a vehicle is disclosed. The vehicle includes one or more power sources configured to provide power to one or more recipients. The system includes a controller configured to determine an arbitration vector based at least partially on a state vector and an initial transformation function. The arbitration vector is determined as one or more points for which the initial transformation function attains a maximum value. The controller is configured to determine a current reward based on the arbitration vector and the state vector, the current reward being configured to minimize energy loss in the power sources. The controller is configured to determine an updated transformation function based at least partially on the initial transformation function and a total reward. The controller is configured to arbitrate a power distribution based in part on the updated arbitration vector.

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: An energy management system for a vehicle is disclosed. The vehicle includes one or more power sources configured to provide power to one or more recipients. The system includes a controller configured to determine an arbitration vector based at least partially on a state vector and an initial transformation function. The arbitration vector is determined as one or more points for which the initial transformation function attains a maximum value. The controller is configured to determine a current reward based on the arbitration vector and the state vector, the current reward being configured to minimize energy loss in the power sources. The controller is configured to determine an updated transformation function based at least partially on the initial transformation function and a total reward. The controller is configured to arbitrate a power distribution based in part on the updated arbitration vector.

Abstract: A diagnostic system for a fuel injector includes a plurality of sensors to sense vehicle data. A controller includes a fuel injector diagnostic module configured to receive the vehicle data during operation of the vehicle and to selectively identify at least one of a fuel injector with a stuck armature and a fuel injector with pintle fatigue.

Abstract: A method for controlling continuous and discrete actuators (e.g., modes) in a powertrain system includes receiving preview information from a sensor(s) describing an upcoming dynamic state at a future time point, and providing control inputs for the actuators to a controller that includes the preview information. The input set collectively describes a future torque or speed output state at the future time point. The controller processes the input set via a dynamical predictive model, in real time, to determine control solutions to take at the present time point for implementing the dynamic state at the future time point. A lowest opportunity cost control solution is determined and optimized. The controller executes the optimized solution at the present time step.

Abstract: A diagnostic system for a fuel injector includes a plurality of sensors to sense vehicle data. A controller includes a fuel injector diagnostic module configured to receive the vehicle data during operation of the vehicle and to selectively identify at least one of a fuel injector with a stuck armature and a fuel injector with pintle fatigue.

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 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 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 method for controlling continuous and discrete actuators (e.g., modes) in a powertrain system includes receiving preview information from a sensor(s) describing an upcoming dynamic state at a future time point, and providing control inputs for the actuators to a controller that includes the preview information. The input set collectively describes a future torque or speed output state at the future time point. The controller processes the input set via a dynamical predictive model, in real time, to determine control solutions to take at the present time point for implementing the dynamic state at the future time point. A lowest opportunity cost control solution is determined and optimized. The controller executes the optimized solution at the present time step.