Abstract: A system for controlling a plurality of electric axles of a vehicle is disclosed, comprising: the plurality of electric axles, one or more motor generators associated with one or more of the plurality of electric axles, and a multi-axle controller communicatively coupled to the one or more motor generators and configured to execute software to cause the multi-axle controller to: determine a power demand of the vehicle based at least in part on one or more parameters of each electric axle and current and/or future road grade; generate a performance cost function associated with one or more performance metrics, the power demand, and/or the vehicle information; determine a power distribution among the plurality of electric axles by optimizing the performance cost function; and transmit a traction command to the one or more motor generators to control the operation of the plurality of electric axles.

Abstract: This disclosure relates generally to the field of Electroencephalogram (EEG) classification, and, more particularly, to method and system for EEG motor imagery classification. Existing deep learning works employ the sensor-space for EEG graph representations wherein the channels of the EEG are considered as nodes and connection between the nodes are either predefined or are based on certain heuristics. However, these representations are ineffective and fail to accurately capture the underlying brain's functional networks. Embodiments of present disclosure provide a method of training a weighted adjacency matrix and a Graph Neural Network (GNN) to accurately represent the EEG signals. The method also trains a graph, a node, and an edge classifier to perform graph classification (i.e. motor imagery classification), node and edge classification. Thus, representations generated by the GNN can be additionally used for node and edge classification unlike state of the art methods.

Abstract: An apparatus includes a position circuit structured to monitor a position of an accelerator of a vehicle and a speed circuit structured to monitor a speed of the vehicle. The position corresponds with an associated response of a prime mover of the vehicle. The associated response includes at least one of a torque output and a power output of the prime mover. The apparatus further includes a response management circuit structured to receive an indication regarding the position of the accelerator and the speed of the vehicle; determine that the indication satisfies a remapping condition, the remapping condition including at least one of a creep condition, an obstacle condition, a deceleration condition, and a reverse condition; and dynamically remap the associated response of the prime mover of the vehicle based on the position of the accelerator in response to the indication satisfying the remapping condition.

Abstract: This invention provides a system and method for finding line features in an image that allows multiple lines to be efficiently and accurately identified and characterized. When lines are identified, the user can train the system to associate predetermined (e.g. text) labels with respect to such lines. These labels can be used to define neural net classifiers. The neural net operates at runtime to identify and score lines in a runtime image that are found using a line-finding process. The found lines can be displayed to the user with labels and an associated probability score map based upon the neural net results. Lines that are not labeled are generally deemed to have a low score, and are either not flagged by the interface, or identified as not relevant.

Abstract: This invention provides a system and method for finding patterns in images that incorporates neural net classifiers. A pattern finding tool is coupled with a classifier that can be run before or after the tool to have labeled pattern results with sub-pixel accuracy. In the case of a pattern finding tool that can detect multiple templates, its performance is improved when a neural net classifier informs the pattern finding tool to work only on a subset of the originally trained templates. Similarly, in the case of a pattern finding tool that initially detects a pattern, a neural network classifier can then determine whether it has found the correct pattern. The neural network can also reconstruct/clean-up an imaged shape, and/or to eliminate pixels less relevant to the shape of interest, therefore reducing the search time, as well significantly increasing the chance of lock on the correct shapes.

Abstract: A system for controlling an overtake maneuver of a control vehicle comprises a controller structured to determine an overtake velocity for the control vehicle traveling in a vehicle lane to overtake a front vehicle traveling ahead of the control vehicle in the vehicle lane. The controller determines an overtake time for the control vehicle to overtake the front vehicle based on the overtake velocity. The controller determines a direction of traffic in an overtake lane that is adjacent to the vehicle lane. If the direction of traffic in the overtake lane is the same as a direction of traffic in the vehicle lane, and the overtake velocity is less than or equal to an allowed velocity, the controller executes the overtake maneuver by one of adjusting a parameter of an engine and/or a transmission of the control vehicle or providing a command to an operator of the control vehicle.

Abstract: Systems and apparatuses include one or more processing circuits including one or more memory devices coupled to one or more processors. The one or more memory devices are configured to store instructions thereon that, when executed by the one or more processors, cause the one or more processors to: receive a parameter regarding operation of a first vehicle of a first platoon; compare the parameter to a first predetermined threshold; responsive to determining that the parameter satisfies the first predetermined threshold, determine an exit parameter for the first vehicle; and cause the first vehicle to exit the first platoon based on the exit parameter.

Abstract: An air handling system for a fuel cell stack includes a pneumatic storage device disposed downstream from a compressor, a flow control valve system configured to operatively couple an inlet of the pneumatic storage device to an outlet of the compressor and configured to operatively couple an outlet of the pneumatic storage device to an inlet of the fuel cell stack, and a controller configured to, in response to a power demand being greater than a threshold, cause the flow control valve to open to increase a flow rate of air from the pneumatic storage device to the fuel cell stack.

Abstract: The invention discloses a composition exhibiting enhanced bioavailability comprising tri-molecular complex of a natural compound or a natural compound containing component, a divalent or tri-valent metal ion and a phospholipid embedded in natural matrix. The composition of the invention further exhibits a sustained release profile for the natural compound or natural compound containing component. The invention further discloses a process for manufacturing the tri-molecular complex containing composition.

Abstract: This invention provides a system and method for finding line features in an image that allows multiple lines to be efficiently and accurately identified and characterized. When lines are identified, the user can train the system to associate predetermined (e.g. text) labels with respect to such lines. These labels can be used to define neural net classifiers. The neural net operates at runtime to identify and score lines in a runtime image that are found using a line-finding process. The found lines can be displayed to the user with labels and an associated probability score map based upon the neural net results. Lines that are not labeled are generally deemed to have a low score, and are either not flagged by the interface, or identified as not relevant.

Abstract: Systems and apparatuses include one or more processing circuits comprising one or more memory devices coupled to one or more processors, the one or more memory devices configured to store instructions thereon that, when executed by the one or more processors, cause the one or more processors to: determine at least one reason for a deserter to exit a first platoon; determine a deserter position within the first platoon; communicate the deserter exit to the first platoon after determination of the at least one reason for the deserter to exit the first platoon based at least in part on the deserter position; adapt a behavior of the first platoon to allow the deserter to exit the first platoon; and reconfigure the remaining vehicles from the first platoon into a second platoon.

Abstract: The present disclosure generally relates to systems and methods for implementing power a power split between a first and a second power source in a fuel cell powertrain system. The method includes receiving an input into a processor of the fuel cell powertrain system, determining an output by the processor, communicating the output by the processor to a system controller and determining a power split by the system controller. The first power source includes a fuel cell system and the second power source is selected from a battery system or an engine, and the input includes a life or health of at least one of the first power source or the second power source.

Abstract: The present disclosure generally relates to systems and methods for controlling a thermal management system of a fuel cell powertrain system.

Abstract: Downhole properties of a geological formation may be determined using nuclear magnetic resonance (NMR) measurements obtained by a moving tool. To do so, an interpretation of the NMR data obtained by the moving data may take into account a moving model, characterization, or calibration of the downhole NMR tool. Additionally or alternatively, a partial interpretation mask may exclude interpretation of certain areas of data (e.g., T1-T2 data points or diffusion-T2 data points) that are expected to be less likely to describe downhole materials of interest.

Abstract: An air handling system for a fuel cell stack includes a pneumatic storage device disposed downstream from a compressor, a flow control valve system configured to operatively couple an inlet of the pneumatic storage device to an outlet of the compressor and configured to operatively couple an outlet of the pneumatic storage device to an inlet of the fuel cell stack, and a controller configured to, in response to a power demand being greater than a threshold, cause the flow control valve to open to increase a flow rate of air from the pneumatic storage device to the fuel cell stack.

Abstract: An electronic control system is configured to control operation of a platoon including a plurality of vehicles. The electronic control system may be configured one or more of operate each of the vehicles to provide operation emulating the lowest non-platooning vehicle performance capability among the plurality of vehicles of the platoon, operate an individualized predictive cruise control (IPCC) process for each of the vehicles and a corresponding supervisory safety process for the platoon, and operate a cooperative predictive cruise control (CPCC) process for each of the vehicles and a corresponding supervisory safety process for the platoon.

Abstract: A control system for a vehicle includes an engine controller operable to determine a requested engine torque in response to a cruise control set command and a cruise control offset value, determine an engine torque command in response to the requested engine torque and a torque limit, and control operation of an engine in response to the engine torque command. The control system also includes a platooning controller operable to determine and provide to the engine controller the cruise control set command, the cruise control offset value and the torque limit effective to cause the engine controller to control the engine to provide a desired following distance between the vehicle and a second vehicle.

Abstract: A climate control system for vehicles includes an internal combustion engine that may be coupled to selectively power a first motor generator, and an air conditioning compressor that may be selectively powered by one or both of the first motor generator and a second motor generator, or by the internal combustion engine. The system may include a rechargeable battery, and a vehicle controller having a vehicle state circuit structured to determine a vehicle operating condition value and a state-of-charge value of the rechargeable battery, and a coupling determination circuit structured to provide an internal combustion engine-first motor generator coupling command in response to the vehicle operating condition value and the state-of-charge value. In response to the internal combustion engine-first motor generator coupling command being provided as coupled, the internal combustion engine may power the first motor generator.

Abstract: This invention provides a system and method for finding patterns in images that incorporates neural net classifiers. A pattern finding tool is coupled with a classifier that can be run before or after the tool to have labeled pattern results with sub-pixel accuracy. In the case of a pattern finding tool that can detect multiple templates, its performance is improved when a neural net classifier informs the pattern finding tool to work only on a subset of the originally trained templates. Similarly, in the case of a pattern finding tool that initially detects a pattern, a neural network classifier can then determine whether it has found the correct pattern. The neural network can also reconstruct/clean-up an imaged shape, and/or to eliminate pixels less relevant to the shape of interest, therefore reducing the search time, as well significantly increasing the chance of lock on the correct shapes.

Abstract: The present disclosure generally relates to a multiple receptacle fuel filling and storage system in a vehicle and/or powertrain, and a method of using the same.