Abstract: There is a need for solutions that generates a temporally dynamic prediction for a particular prediction input. This need can be addressed by, for example, processing the prediction input using each of a plurality of temporally trained machine learning models to generate a corresponding model-specific prediction inference of a plurality of model-specific prediction inferences and processing the plurality of model-specific prediction inferences using an ensemble model to generate the temporally dynamic prediction for the prediction input.

Abstract: An integrated thermal management system for a fuel cell electric vehicle is disclosed. The integrated thermal management system includes a fuel cell system, a brake resistor, a fuel cell coolant loop that includes a fuel cell radiator thermally and fluidly coupled to the fuel cell system, a brake resistor coolant loop that includes a brake resistor radiator thermally and fluidly coupled to the brake resistor, and a heat exchanger loop that includes a coolant-coolant heat exchanger thermally and fluidly coupled to the fuel cell coolant loop and the brake resistor coolant loop. In a fuel cell cooling operating mode, heat is transferred from the fuel cell system to an ambient environment through the fuel cell radiator and the brake resistor radiator.

Abstract: An exhaust duct of a fuel cell exhaust system includes a convolute duct, a resonator coupled to and in fluid communication with the convolute duct, a mid-duct coupled to and in fluid communication with the resonator, and a tail duct coupled to and in fluid communication with the mid-duct, the tail duct comprising a lower duct and an upper duct. The upper duct includes an incline duct, a transition duct, a decline duct, and a hydrogen sensor having a portion positioned within the transition duct. A first portion of an exhaust is diverted to the lower duct and a second portion of the exhaust is diverted to the upper duct and measured by the hydrogen sensor to determine hydrogen content of the exhaust.