Abstract: The present approach relates generally to image-based approaches for detecting deviations from a linear movement when scanning a surface. More particularly, the approach relates to the use of linear fiducials to detect, in real-time, deviations from a linear scan path during operation of a scanning imaging system. Such linear fiducials may include both sample sites and blank regions or sites or, in certain embodiments, may utilize elongated sample sites (e.g., linear features) within the linear fiducial.

Abstract: A battery management system includes a neural network, for estimating an amount of charge stored in a battery following a recharging operation. Then, an amount of charge drawn during a discharging operation is subtracted from this estimated amount of charge to derive an estimate for the state of charge of the battery at a present time. A parameter representing the state of health of the battery may be provided as an input to the neural network, and the parameter representing the state of health of the battery may be generated by a second neural network.

Abstract: An inspection device in the form of an acoustic transducer with a number of transducer elements that are arranged in a circumferential array around substantially the whole circumference of the device, to transmit and receive acoustic signals around substantially the whole circumference of the device, typically at substantially the same time, allowing assessment of the inspected object from different perspectives without requiring moving parts on the inspection device. In some embodiments, the transducer elements are circumferentially offset to improve the resolution, and can be axially stacked along the device. Circumferential arrangement of the transducer elements in the device allows the device to transmit and receive signals around substantially its whole circumference, and thereby allows it to inspect whole pipe planar sections in real time, and without requiring rotation of the transducers, thereby avoiding moving parts.

Abstract: A battery management system includes a neural network, for estimating an amount of charge stored in a battery following a recharging operation. Then, an amount of charge drawn during a discharging operation is subtracted from this estimated amount of charge to derive an estimate for the state of charge of the battery at a present time. A parameter representing the state of health of the battery may be provided as an input to the neural network, and the parameter representing the state of health of the battery may be generated by a second neural network.

Abstract: A method of controlling a mechanical actuator using a modular map processor comprises monitoring a plurality of parameters associated with the actuator. The modular map processor generates a control signal based on the parameters for output to the actuator and modifies the control signal based on a merit function. In preferred forms the mechanical actuator is an input or output valve in a cylinder for an internal combustion engine.

Abstract: A method of controlling a mechanical actuator using a modular map processor comprises monitoring a plurality of parameters associated with the actuator. The modular map processor generates a control signal based on the parameters for output to the actuator and modifies the control signal based on a merit function. In preferred forms the mechanical actuator is an input or output valve in a cylinder for an internal combustion engine.