Patent
Residual activation neural network
Reads0
Chats0
TLDR
In this paper, a control network (74) is provided that accurately models the plant (72), and the output of the control network provides a predicted output which is combined with a desired output to generate an error.Abstract:
A plant (72) is operable to receive control inputs c(t) and provide an output y(t). The plant (72) has associated therewith state variables s(t) that are not variable. A control network (74) is provided that accurately models the plant (72). The output of the control network (74) provides a predicted output which is combined with a desired output to generate an error. This error is back propagated through an inverse control network (76), which is the inverse of the control network (74) to generate a control error signal that is input to a distributed control system (73) to vary the control inputs to the plant (72) in order to change the output y(t) to meet the desired output. The control network (74) is comprised of a first network NET 1 that is operable to store a representation of the dependency of the control variables on the state variables. The predicted result is subtracted from the actual state variable input and stored as a residual in a residual layer (102). The output of the residual layer (102) is input to a hidden layer (108) which also receives the control inputs to generate a predicted output in an output layer (106). During back propagation of error, the residual values in the residual layer (102) are latched and only the control inputs allowed to vary.read more
Citations
More filters
Patent
Integrated alert generation in a process plant
Evren Eryurek,Craig Thomas Llewellyn,Lester David Marschall,Jon Westbrock,Stuart Harris,Scott N. Lakeville Hokeness +5 more
TL;DR: In this article, the operational status information associated with a process entity in a process plant is mapped into one of a plurality of status conditions and an alert message associated with the process entity is generated.
Patent
Remote analysis of process control plant data
TL;DR: In this paper, a system and method for analyzing a process collects process data within a process control plant and transmits the collected process data to a remote data processing facility using a process analysis tool.
Patent
Asset optimization reporting in a process plant
TL;DR: In this article, a process control system uses an asset optimization reporter to collect status information pertaining to the assets of a process plant from various data sources of the plant including, for example, data tools, data collectors, and data generators.
Patent
Integrated, advanced control blocks in process control systems
TL;DR: In this article, an advanced control block that implements multiple-input/multiple-output control, such as model predictive control, within a process control system is initiated by creating an initial control block having generic control logic and desired control inputs and control outputs communicatively connected to process outputs and process inputs.
Patent
Control system using an adaptive neural network for target and path optimization for a multivariable, nonlinear process
Naveen V Bhat,William B. Braden,Kent E Heckendoorn,Timothy J Graettinger,Alexander J Federowicz,Paul A Dubose +5 more
TL;DR: In this article, a neural network is used to model moves from current to desired values, and the neural network input values are set equal to produce a steady state controlled variable value.
References
More filters
Journal ArticleDOI
Optimization by Simulated Annealing
TL;DR: There is a deep and useful connection between statistical mechanics and multivariate or combinatorial optimization (finding the minimum of a given function depending on many parameters), and a detailed analogy with annealing in solids provides a framework for optimization of very large and complex systems.
Proceedings Article
Optimal Brain Damage
TL;DR: A class of practical and nearly optimal schemes for adapting the size of a neural network by using second-derivative information to make a tradeoff between network complexity and training set error is derived.
Book
Neural networks for control
TL;DR: This work addresses general issues of neural network based control and neural network learning with regard to specific problems of motion planning and control in robotics, and takes up application domains well suited to the capabilities of Neural network controllers.
Proceedings Article
Generalization by Weight-Elimination with Application to Forecasting
TL;DR: This work adds a term to the back propagation cost function that penalizes network complexity, called weight-elimination, and uses this procedure to predict the sunspot time series and the notoriously noisy series of currency exchange rates.
Journal ArticleDOI
Neural networks for nonlinear internal model control
Kenneth J. Hunt,D. Sbarbaro +1 more
TL;DR: In this paper, a novel technique, directly using artificial neural networks, is proposed for the adaptive control of nonlinear systems, where the ability of neural networks to model arbitrary nonlinear functions and their inverses is exploited.