US 5,859,773 A · Residual activation neural network

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.

Claims6

Dependent claims

A control network for controlling a plant having plant control inputs, the network for receiving plant control variables, measurable state variables of the plant and desired plant outputs, the measurable state variables having dependencies on both the plant control variables and unmeasurable external influences on the plant, comprising:

a control network input for receiving as network inputs the current plant control variables, the measurable state variables and desired plant outputs;
a control network output for outputting predicted plant control variables necessary to achieve the desired plant outputs;
a processing system for processing the received plant control variables through an inverse representation of the plant that represents the dependencies of the plant output on the plant control variables and the measurable state variables parameterized by an estimation of the unmeasurable external influences to provide the predicted plant control variables to achieve the desired plant outputs, said processing system including:
an estimation network for estimating the unmeasurable external influences on the plant and outputting estimated external influences;
and
means for parameterizing the inverse representation of the plant with the estimated external influences;
and
an interface device for inputting the predicted plant control variables that are output by said control network output to the plant as plant control variables to achieve the desired plant outputs.

5 more elements

Dependencies are inferred from the claim text.

Residual activation neural network

Life of this patent

Residual activation neural network

Life of this patent

Abstract

Claims6