Colorado State University Research Foundation

Seagate Technology Incorporated

Solix Algredients, Inc.

Peter Michael Young

Yi Han

Daniel Zimmerle

Douglas C Hittle

Charles Anderson

John Christopher Morris

Guy Robert Babbitt

Christopher Wayne Turner

Kristina Weyer-Geigel

Bryan Willson

Michael Ryan Buehner

Jason Charles Quinn

Mike E Baum

David Jacob Rausen

Michael Anderson

Richard Charles Schoonover

Matthew Kretchmar

David Eli Sherman

Christopher Delnero

According to some embodiments, the present disclosure may relate to a system including a gaseous fuel consuming engine operating at an air to fuel ratio (AFR) and including a throttle valve controlling a speed of engine, and an engine controller coupled to the engine. The engine controller may be configured to obtain the speed of the engine and obtain the AFR of the engine. The engine controller may also be configured to, based on a transient event affecting the engine, coordinate modification of both the throttle valve to change the speed of the engine and trim valve to change the AFR of the engine to maintain at least one of the speed and the AFR of the engine within a threshold deviance.

Gaseous fuel consuming engine controlling systems

Photobioreactors according to embodiments of the present invention deliver nutrient gas intermittently to the photobioreactor media. In some embodiments, one or more gases are delivered according to a duty cycle or timing pattern. According to some embodiments, algae is grown in a photobioreactor using intermittent introduction of carbon dioxide. In other embodiments, carbon dioxide is supplied to algae grown in a photobioreactor in whole or in part from a head space above the media of the photobioreactor.

Systems and methods for delivery of gases to algal cultures

A neural network controller in parallel with a proportional-plus-integral (PI) feedback controller in a control system. At least one input port of the neural network for receiving an input signal representing a condition of a process is included. A first set of data is obtained that includes a plurality of output values of the neural network obtained during a training period thereof using a plurality of first inputs representing a plurality of conditions of the process. The process/plant condition signals generally define the process/plant, and may include one set-point as well as signals generated using measured systems variables/parameters. In operation, the neural network contributes to an output of the PI controller only upon detection of at least one triggering event, at which time a value of the first set of data corresponding with the condition deviation is added-in thus, contributing to the proportional-plus-integral feedback controller. The triggering event can be characterized as (a) a change in any one of the input signals greater-than a preselected amount, or (b) a detectable process condition deviation greater-than a preselected magnitude, for which an adjustment is needed to the process/plant being controlled. Also a method for controlling a process with a neural network controller operating in parallel with a IP controller is included.

Combined proportional plus integral (PI) and neural network (nN) controller

A feedback control system for automatic on-line training of a controller for a plant, the system having a reinforcement learning agent connected in parallel with the controller. The learning agent comprises an actor network and a critic network operatively arranged to carry out at least one sequence of a stability phase followed by a learning phase. During the stability phase, a multi-dimensional boundary of values is determined. During the learning phase, a plurality of updated weight values is generated in connection with the on-line training, if and until one of the updated weight values reaches the boundary, at which time a next sequence is carried out to determine a next multi-dimensional boundary of values followed by a next learning phase. Also, a method for automatic on-line training of a feedback controller within a system comprising the controller and a plant by employing a reinforcement learning agent comprising a neural network to carry out at least one sequence comprising a stability phase followed by a learning phase. Further included, a computer executable program code on a computer readable storage medium, for on-line training of a feedback controller within a system comprising the controller and a plant.

Control system and technique employing reinforcement learning having stability and learning phases

A method of configuring a discrete-time servo controller in a fixed-point digital signal processor (DSP) for controlling a servo actuator in a disc drive includes obtaining a stable, closed-loop representation of the servo controller and the servo actuator. Bounds on the controller states are derived from the stable closed-loop representation. The controller states are scaled based on the controller state bounds, and the servo controller is configured in the DSP based on the scaled controller states.

Closed-loop scaling for discrete-time servo controller in a disc drive

Growing community of inventors

Fort Collins, CO, United States of America

Peter Michael Young