Abstract: A normality modeling and anomaly detection method for a high voltage battery system of an electrified vehicle includes obtaining a trained normality model configured to model a set of modeled parameters of the high voltage battery system based on a set of measured parameters of cells/modules of the high voltage battery system and a long short-term memory model, obtaining a trained anomaly classification model configured to determine a breakdown event of the high voltage battery system and a type of the breakdown event, detecting an anomaly condition for the high voltage battery system based on a comparison of the set of modeled parameters from the trained normality model and the set of measured parameters, and applying the trained anomaly classification model to the detected anomaly condition to determine a predicted breakdown event that will happen to the high voltage battery system and a type of the predicted breakdown event.

Abstract: A wind energy estimation and control system for an automobile includes a memory configured to store data indicative of an aerodynamic characterization of the automobile, generated offline by an external computing system, and control system configured to access the memory and to determine a speed and direction of a wind impacting the automobile, estimate a relative velocity between the automobile and a surrounding airstream based on the data indicative of the automobile's aerodynamic characterization, the wind speed, and the wind direction, estimate an angle of attack of the airstream based on the estimated relative velocity between the automobile and the surrounding airstream, estimate a longitudinal component of an aerodynamic drag force impacting the automobile based on the estimated angle of attack of the airstream, the wind speed, and the wind direction, and generate an output based on the estimated longitudinal component of the aerodynamic drag force impacting the automobile.

Abstract: An energy consumption estimation and control system for an electrified vehicle includes a memory configured to store a trained energy consumption model configured to estimate an energy consumption of the electrified vehicle, wherein the trained energy consumption model was previously trained offline using training data generated by computer-aided engineering (CAE) software and a control system configured to access the trained energy consumption model from the memory, obtain a plurality of input parameters for the trained energy consumption model based on real-time parameters of the electrified vehicle, utilize the trained energy consumption model and the plurality of input parameters to estimate the energy consumption of the electrified vehicle in real-time, and generate an output based on the estimated energy consumption of the electrified vehicle.

Abstract: A trip optimization system for a trip of an electrified vehicle from a start point to an end point includes a control system configured to determine a first optimized trip plan based on at least an initial state of charge (SOC) of a high voltage battery system of the electrified vehicle, wherein the first optimized trip plan specifies a set of stops at respective set of charging stations to recharge the high voltage battery system and, during the trip of the electrified vehicle, selectively reoptimize the first optimized trip plan based on at least one of a change in a current position of the electrified vehicle and a change in environmental conditions to obtain a second optimized trip plan, and a driver interface configured to output information to a driver of the electrified vehicle relating to the first and second optimized trip plans.

Abstract: Hydraulic circuit comprising a low-pressure circuit (6) fed by a booster pump (4) that draws from a very-low-pressure reservoir (2), characterized in that this very-low-pressure reservoir (2) is leaktight and has a device for placing the internal volume (12) under negative pressure with respect to atmospheric pressure.

Abstract: A combustion method for melting glass in which two fuels of the same nature or different natures are fed into a fusion furnace at two locations remote from each other for distributing the fuel to reduce NOx emissions. The combustion air is supplied at only one of the locations. In a method for operating a glass melting furnace, the fuel injection is distributed to reduce NOx emissions. The furnace includes a melting vessel for receiving the glass to be melted and containing a bath of molten glass, walls defining the furnace, a hot combustion air inlet, a hot smoke outlet, at least one burner for injecting a first fuel, and at least one injector for injecting a second fuel. The injector has an adjustable flow complementary relative to the flow to the burner so that up to 100% of the totality of the first and second fuels used may be injected.