Abstract: In one aspect, a power system comprises a power bus, a plurality of energy-storage modules, and a controller. Each energy-storage module is coupled to the power bus and comprises an energy-storage device configured to store energy, an electrical circuit safety device configured to detect safe power conditions in the energy-storage module and break an electrical circuit within the energy-storage module based on a detection of unsafe power conditions in the energy-storage module, and a switch configured to selectively couple the energy-storage device to the power bus. The controller is configured to monitor a state of each of the plurality of energy-storage modules and control a state of the power system based on the state of each of the plurality of energy-storage modules.

Abstract: In one aspect, a power system comprises a power bus, a plurality of energy-storage modules, and a controller. Each energy-storage module is coupled to the power bus and comprises an energy-storage device configured to store energy, an electrical circuit safety device configured to detect safe power conditions in the energy-storage module and break an electrical circuit within the energy-storage module based on a detection of unsafe power conditions in the energy-storage module, and a switch configured to selectively couple the energy-storage device to the power bus. The controller is configured to monitor a state of each of the plurality of energy-storage modules and control a state of the power system based on the state of each of the plurality of energy-storage modules.

Abstract: Systems and methods for monitoring and controlling a battery are disclosed. Systems can include a battery having an output voltage and an output current when delivering power, a load driven by power delivered from the battery, battery output voltage and current sensing circuits, and processing circuitry coupled to the battery output voltage and current sensing circuits. The processing circuitry may implement a recurrent neural network for battery state estimation.

Abstract: Systems and methods for monitoring and controlling a battery are disclosed. Systems can include a battery having an output voltage and an output current when delivering power, a load driven by power delivered from the battery, battery output voltage and current sensing circuits, and processing circuitry coupled to the battery output voltage and current sensing circuits. The processing circuitry may implement a recurrent neural network for battery state estimation.

Abstract: A vehicle can use controlled area network (CAN) buses for communications within a subsystem but connect different subsystems using Ethernet connections. For example, a network interface (NIC) of a subsystem can receive a CAN message from a CAN bus and incorporate the CAN message into a user diagram protocol (UDP) message which can be then packaged into an Ethernet packet. The UDP message may include a table of contents (TOC). The TOC may include the message ID and the length of the CAN message. Once a NIC receives the message, the receiving NIC can extract the UDP message from the Ethernet packet, parse through the TOC to identify a CAN message relevant to the control units of the receiving NIC's subsystem, extract the relevant CAN message based on the TOC, and put the CAN message onto CAN buses to be sent to destination CAN devices.