US5559690A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Residual activation neural network
Assignee: Rockwell Automation Technologies Inc
•
Filing: 1994-09-16
•
Granted: 1996-09-24
•
Expires: 2014-09-16
Abstract
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.
Inventors
- 👤 James D. Keeler
- 👤 Eric J. Hartman
- 👤 Kadir Liano
- 👤 Ralph B. Ferguson
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-27 22:18
CPC Classifications
G; G05; G05B; G05B13/00; G05B13/02; G05B13/0265; G05B13/027; Y; Y10; Y10S; Y10S706/00; Y10S706/902; Y10S706/903; Y10S706/906
Claims Analysis
Total Claims: 11
Claim 1
Independent Claim
233 words
A network for predicting plant outputs of a plant and for receiving control variables that are used to control the plant and measurable state variables of the plant, with the measurable state variables having dependencies on the control variables and unmeasurable external influences, the control network for projecting out the dependencies of the measurable state variables on the control variables, comprising: a residual activation neural network for generating an estimation of the unmeasurable external influences on the plant and having: an input layer for receiving the control variables, an output layer for outputting predicted state variables, a hidden layer for mapping said input layer to said output layer through a representation of the dependencies of the state variables on the control variables to generate said predicted state variables, which said representation is trained on the measurable state variables, and a residual layer for determining as a residual the difference between said predicted state variables and the input state variables, said residual comprising an estimation of the unmeasurable external influences on the plant; and a main neural network having: an input layer for receiving as inputs the control variables and input signals parameterized by said residual, an output layer for outputting a predicted plant output, and a hidden layer for mapping said input layer to said output layer through a representation of the plant as a function of the control variables and said residual.
Claim 2
Dependent Claim
233 words
A network for predicting plant outputs of a plant and for receiving control variables that are used to control the plant and measurable state variables of the plant, with the measurable state variables having dependencies on the control variables and unmeasurable external influences, the control network for projecting out the dependencies of the measurable state variables on the control variables, comprising: a residual activation neural network for generating an estimation of the unmeasurable external influences on the plant and having: an input layer for receiving the control variables, an output layer for outputting predicted state variables, a hidden layer for mapping said input layer to said output layer through a representation of the dependencies of the state variables on the control variables to generate said predicted state variables, which said representation is trained on the measurable state variables, and a residual layer for determining as a residual the difference between said predicted state variables and the input state variables, said residual comprising an estimation of the unmeasurable external influences on the plant; and a main neural network having: an input layer for receiving as inputs the control variables and input signals parameterized by said residual, an output layer for outputting a predicted plant output, and a hidden layer for mapping said input layer to said output layer through a representation of the plant as a function of the control variables and said residual.
Claim 3
Dependent Claim
96 words
The network of claim 1, and further comprising: means for generating an error between the predicted plant output and a desired plant output; a latch for latching said residual in said input layer of said main neural network; and means for operating said main neural network to provide the inverse of said associated representation and back propagate said error through said main neural network from said output layer to the control variable inputs of said input layer of said main neural network to generate predicted control variable change values necessary to achieve said desired plant output.
Claim 4
Dependent Claim
70 words
The control network of claim 2, wherein said means for generating said error comprises: a predictive model neural network for providing a representation of the plant and for receiving the control variables and the measurable state variables as inputs and predicting the output of the plant as a predicted plant output; and a difference device for receiving said desired plant output and said predicted plant output and generating said error.
Claim 5
Dependent Claim
58 words
The control network of claim 2, wherein said means for back propagating error through said main neural network comprises means for back propagating error through said main neural network to define said predicted control variable change values, and iteratively summing said change values with the control variables to minimize said error in accordance with a back propagation-to-activation technique.
Claim 6
Dependent Claim
76 words
The control network of claim 1, wherein said representation stored in said residual activation network is a non-linear representation of the dependency of the state variables on the control variables and the representation in said hidden layer of said main neural network comprises a non-linear representation of the plant output as a function the measurable state variables having dependencies on both the control variables and unmeasurable external influences of the input control variables and said residual.
Claim 7
Dependent Claim
240 words
A predictive network for predicting the operation of a plant in response to receiving manipulatable control variables that are input to the plant and non-manipulatable measurable state variables output by the plant, comprising: a residual network for projecting out the dependencies of the state variables on the control variables to generate an estimation of the unmeasurable external influences on the plant and having: an input for receiving input control variables, an output for outputting predicted state variables as a function of the input control variables, a residual processing system for processing the input control variables through a representation of the dependencies of the state variables on the control variables to provide predicted state variables for output by said output, which representation was trained on the control variables as inputs and measurable state variables as target outputs, and a residual layer for determining the difference between the input measurable state variables and the predicted state variables, the difference comprising a residual, said residual comprising the estimation of the unmeasurable external influences on the plant; and a main network having: an input for receiving as inputs the input control variables and said residual, an output for outputting a predicted output representing the predicted output of the plant, and a main processing system for processing the input control variables and said residual through a representation of the plant as a function of the control variables and an input signal parameterized by said residual.
Claim 8
Dependent Claim
240 words
A predictive network for predicting the operation of a plant in response to receiving manipulatable control variables that are input to the plant and non-manipulatable measurable state variables output by the plant, comprising: a residual network for projecting out the dependencies of the state variables on the control variables to generate an estimation of the unmeasurable external influences on the plant and having: an input for receiving input control variables, an output for outputting predicted state variables as a function of the input control variables, a residual processing system for processing the input control variables through a representation of the dependencies of the state variables on the control variables to provide predicted state variables for output by said output, which representation was trained on the control variables as inputs and measurable state variables as target outputs, and a residual layer for determining the difference between the input measurable state variables and the predicted state variables, the difference comprising a residual, said residual comprising the estimation of the unmeasurable external influences on the plant; and a main network having: an input for receiving as inputs the input control variables and said residual, an output for outputting a predicted output representing the predicted output of the plant, and a main processing system for processing the input control variables and said residual through a representation of the plant as a function of the control variables and an input signal parameterized by said residual.
Claim 9
Dependent Claim
71 words
The predictive network of claim 6 wherein said input, said output and said processing system of said residual network comprise a residual neural network having: an input layer for receiving the input control variables; an output layer for outputting said predicted state variables; and a hidden layer for mapping said input layer to said output layer through a non-linear representation of the dependencies of the state variables on the control variables.
Claim 10
Dependent Claim
88 words
The predictive network of claim 6 wherein said main network comprises a main neural network having: an input layer for receiving the input control variables and said signal parameterized by said residual that is output by said residual layer; an output layer for outputting said predicted output representing the predicted output of the plant; and a hidden layer for mapping said input layer to said output layer through a non-linear representation of the plant as a function of the control variables and said signal parameterized by said residual.
Claim 11
Dependent Claim
55 words
The predictive network of claim 8 wherein said main network has the hidden layer thereof trained through back propagation as a function of known input control variables and residuals from said residual layer, said residuals generated by said residual network, and said output layer of said main network having input thereto known target predicted outputs.
References Cited (Backward Citations)
US4979126A
Cited
US4912753A
Cited
US4928484A
Cited
US4972363A
Cited
WO1990010270A1
Cited
US5111531A
Cited
US5113483A
Cited
EP0463934A1
Cited
US5353207A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1999-09-24 | 2000-03-25 | 2000-09-24 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2003-09-24 | 2004-03-25 | 2004-09-24 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2007-09-24 | 2008-03-25 | 2008-09-24 | $7700.00 | Window Closed / Lapsed |