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

• US 7,117,045 B2
• Filed: 09/09/2002
• Issued: 10/03/2006
• Est. Priority Date: 09/08/2001
• Status: Expired due to Term

• Current Assignee: Colorado State University Research Foundation
• Original Assignee: Colorado State University Research Foundation
• Inventors: Anderson, Michael, Anderson, Charles, Young, Peter M., Delnero, Christopher, Hittle, Douglas C.
• Primary Examiner(s): Knight, Anthony
• Assistant Examiner(s): Chang, Sunray
• Application Number:
  US10/238,575
• Publication Number:
  US 20030055798A1
• Time in Patent Office: 1,485 Days
• Field of Search: 700/41, 700/47, 700/48, 700/49, 700/53, 700/276, 700/277, 123/692, 123/689, 123/822, 706/15, 706/906
• US Class Current: 700/48
• CPC Class Codes: G05B 11/42 for obtaining a characteristic which is both proportional and time-dependent, e.g. P. I., P. I. D.
• CPC Class Codes: G05B 13/027 using neural networks only
• CPC Class Codes: Y10S 706/906 Process plant

Abstract

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.

Claims

1. A neural network controller in parallel with a proportional-plus-integral feedback controller in a control system, the system comprising:

at least one input port of the neural network controller for receiving an input signal representing a condition of a process;

a first set of data comprising a plurality of learned output values of the neural network controller obtained during a training period thereof using a plurality of first inputs representing a plurality of conditions of said process; and

in operation, the neural network controller to contribute to a current output, O_τ

, of the proportional-plus-integral feedback controller upon detection of at least one triggering event connected with a condition deviation represented by a change in said input signal at a time, τ

, otherwise said neural network controller does not contribute to said current output, O_τ

;

wherein said operation of the neural network controller in communication with the proportional-plus-integral feedback controller, further comprises;

(a) upon detection of said triggering event at said time, τ

, a respective one of said learned output values, O_NN, of said first set of data corresponding with said condition deviation is added to the proportional-plus-integral feedback controller current output, O_τ

, and at said time, τ

, a prior control output value, O<sub>τ

−

1</sub>, of the proportional-plus-integral feedback controller associated with a prior time, τ

−

1, does not contribute to said current output O_τ

; and

(b) the proportional-plus-integral feedback controller functioning with a proportional gain constant, K_p, and an integral gain constant, K_i, that remain unchanged during said operation.

2. The system of claim 1 further comprising a second input port for receiving a second input signal representing a second condition of said process;

and wherein said first set of data was obtained earlier-in-time, off-line, than said operation of the neural network, and said triggering event comprises a change in any one of said input signals greater-than a preselected amount.

3. The system of claim 2 wherein said plurality of first inputs comprises real input information about said process, said change is caused by an inadvertent disturbance of said process, and said preselected amount comprises a fraction of a prediction value from said first set of data corresponding to a respective of said plurality of first inputs, said fraction selected from a range comprising from 1% to 5%.

4. The system of claim 2 wherein at least one of said input signals represents a condition set-point, said change is caused by an alteration of said condition set-point, and said preselected amount comprises a fraction of a prediction value from said first set of data corresponding to a respective of said plurality of first inputs comprising said input signal for said altered condition set-point.

5. The system of claim 4 wherein said alternation is a manual alteration of said condition set-point said plurality of first inputs comprises real input information about said process, and said fraction is selected from a range comprising from 1% to 5%, and wherein and said change is a result of a detectable process condition deviation.

6. The system of claim 1 wherein said respective one of said learned output values, O_NN, at said time, τ

, is added-in as said replacement for said prior control output value, O<sub>τ

−

1</sub>, associated with said prior time, τ

−

1, according to a discrete form of the proportional-plus-integral feedback controller expression;

O_τ

=O_NN+K_pe_τ

+K_ie_τ

Δ

t

where

Oτ

=proportional-plus-integral controller output

e=error, equal to the difference between set point and measured value of controlled variable

K_p=proportional gain constant

K_i=integral gain constant

Δ

t=sampling rate, s.

7. The system of claim 6 in which said output value, O_τ

, derived by said addition of said respective one of said learned output values, O_NN, at said time, τ

, to the proportional-plus-integral feedback controller as said replacement for said prior control output value, O<sub>τ

−

1</sub>, associated with said prior time, τ

−

1, is used as a process input for said process; and

wherein and said triggering event comprises a detectable process condition deviation greater-than a preselected magnitude.

8. The system of claim 1 further comprising second, third, and fourth input ports for receiving, respectively, second, third, and fourth input signals representing a second, third, and fourth condition of said process;

and wherein said triggering event comprises a change in any one of said input signals greater-than a preselected amount, said preselected amount comprising a fraction of a prediction value from said first set of data corresponding to a respective of said plurality of first inputs.

9. The system of claim 8 wherein the neural network controller comprises a feed forward controller, said plurality of first inputs comprises real input information about said process, said first set of data being obtained on-line during said operation of the neural network, said fraction selected from a range comprising from 1% to 5%.

10. The system of claim 8 wherein the neural network controller comprises a feed forward controller, said plurality of first inputs comprises simulated input information about said process, said first set of data was obtained earlier-in-time, off-line, from said operation of the neural network, and wherein and said change is a result of a detectable process condition deviation.

11. A neural network controller in parallel with a proportional-plus-integral feedback controller in a control system, the system comprising:

a plurality of input ports of the neural network controller, each said input pod for receiving a respective input signal representing a respective condition of a process;

a first set of data comprising a plurality of learned output values of the neural network controller obtained during a training period thereof using a plurality of first inputs representing a plurality of conditions of said process; and

in operation, the neural network controller to contribute to a current output, O_τ

, of the proportional-plus-integral feedback controller upon detection of at least one triggering event, said event comprising a change in any one of said respective input signals at a time, τ

, greater-than a preselected amount indicating a condition deviation;

wherein said operation of the neural network controller in communication with the proportional-plus-integral feedback controller, further comprises;

(a) upon said detection at said time, τ

, a respective one of said learned output values, O_NN, of said first set of data corresponding with said condition deviation is added to the proportional-plus-integral feedback controller current output O_τ

, and at said time, τ

, a prior control output value, O<sub>τ

−

1</sub>, of the proportional-plus-integral feedback controller associated with a prior time, τ

−

1, does not contribute to said current output, O_τ

;

(b) otherwise, the system operates with the neural network controller making no contribution to the proportional-plus-integral feedback controller current output O_τ

; and

(c) the proportional-plus-integral feedback controller functioning with a proportional gain constant K_p and an integral gain constant K_i that remain unchanged during said operation.

12. The system of claim 11 wherein said plurality of first inputs comprises real input information about said process, said change is caused by an inadvertent disturbance of said process, and said preselected amount comprises a fraction of a prediction value from said first set of data corresponding to a respective of said plurality of first inputs, said fraction selected from a range comprising from 1% to 5%.

13. The system of claim 11 wherein the neural network controller comprises a feed forward controller, at least one of said respective input signals represents a condition set-point, said change is caused by an alteration of said condition set-point, and said plurality of first inputs comprises simulated input information about said process.

14. The system of claim 11 wherein said respective one of said learned output values, O_NN, at said time, τ

, is added-in as said replacement for said prior control output value, O<sub>τ

−

1</sub>, associated with said prior time, τ

−

1, according to a discrete form of the proportional-plus-integral feedback controller expression;

O_τ

=O_NN+K_pe_τ

+K_ie_τ

Δ

t

where

Oτ

=proportional-plus-integral controller output

e=error, equal to the difference between set point and measured value of controlled variable

K_p=proportional gain constant

K_i=integral gain constant

Δ

t=sampling rate, s.

15. A method for controlling a process with a neural network controller operating in parallel with a proportional-plus-integral feedback controller, the method comprising the steps of:

generating a first set of data comprising a plurality of learned output values of the neural network controller obtained during a training period thereof using a plurality of first inputs representing a plurality of conditions of a process;

receiving, at each of a plurality of input ports of the neural network controller, an input signal representing a respective condition of said process; and

the neural network controller operating in parallel with the proportional-plus-integral feedback controller to contribute to a current output, O_τ

, of the proportional-plus-integral feedback controller upon detection of at least one triggering event, said triggering event comprising a change in any one of said respective input signals at a time, τ

, greater-than a preselected amount indicating a condition deviation;

wherein the step of operating further comprises;

(a) upon said detection at said time, τ

, a respective one of said learned output values, O_NN, of said first set of data corresponding with said condition deviation is added to the proportional-plus-integral feedback controller current output, O_τ

, and at said time, τ

, a prior control output value, O<sub>τ

−

1</sub>, of the proportional-plus-integral feedback controller associated with a prior time, τ

−

1, does not contribute to said current output O_τ

; and

(b) the proportional-plus-integral feedback controller functioning with a proportional gain constant, K_p, and an integral gain constant, K_i, that remain unchanged during the operating.

16. The method of claim 15 wherein said step of generating further comprises using real input information about said process for said plurality of first inputs;

and said change is caused by an inadvertent disturbance of said process.

17. The method of claim 15 wherein said step of generating further comprises using simulated input information about said process for said plurality of first inputs;

said receiving further comprises at least one of said input signals representing a condition set-point;

said change is caused by an alternation of said condition set-point; and

said triggering event further comprises said preselected amount comprising a fraction of a prediction value from said first set of data corresponding to a respective of said plurality of first inputs comprising said input signal for said altered condition set-point.

18. The method of claim 15 wherein:

said training period is substantially completed prior to said step of receiving said input signals in connection with controlling said process; and

said triggering event further comprises said preselected amount comprising a fraction of a prediction value from said first set of data corresponding to a respective of said plurality of first inputs, said fraction selected from a range comprising from 1% to 5%.

19. The method of claim 15 wherein the neural network controller comprises a feed forward controller, and said contribution to said output comprises adding-in said respective one of said learned output values, O_NN, at said time, τ

, as said replacement for said prior control output value, O<sub>τ

−

1</sub>, associated with said prior time, τ

−

1, according to a discrete form of the proportional-plus-integral feedback controller expression;

O_τ

=O_NN+K_pe_τ

+K_ie_τ

Δ

t

where

Oτ

=proportional-plus-integral controller output

e=error, equal to the difference between set point and measured value of controlled variable

K_p=proportional gain constant

K_i=integral gain constant

Δ

t=sampling rate, s.

20. The method of claim 19 wherein:

said training period takes place at least on-line and during said step of receiving said input signals in connection with controlling said process; and

said output value, o_τ

, derived by said adding said value of said respective one of said learned output values, O_NN, at said time, τ

, to the proportional-plus-integral feedback controller as said replacement for said prior control output value, O<sub>τ

−

1</sub>, associated with said prior time, τ

−

1, is used as a process input for said process.