US5224203A
Expired / Lapsed
US
⏱️ 0.0 years remaining
On-line process control neural network using data pointers
Assignee: Rockwell Automation Technologies Inc
•
Filing: 1992-07-22
•
Granted: 1993-06-29
•
Expires: 2012-07-22
Abstract
Abstract An on-line process control neural network using data pointers allows the neural network to be easily configured to use data in a process control environment. The inputs, outputs, training inputs and errors can be retrieved and/or stored from any available data source without programming. The user of the neural network specifies data pointers indicating the particular computer system in which the data resides or will be stored; the type of data to be retrieved and/or stored; and the specific data value or storage location to be used. The data pointers include maximum, minimum, and maximum change limits, which can also serve as scaling limits for the neural network. Data pointers indicating time-dependent data, such as time averages, also include time boundary specifiers. The data pointers are entered by the user of the neural network using pop-up menus and by completing fields in a template. An historical database provides both a source of input data and a storage function for output and error data.
Inventors
- 👤 Richard D. Skeirik
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-25 22:11
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: 42
Claim 1
Independent Claim
124 words
A computer neural network process control method adapted for predicting output data provided to a controller used to control a process for producing a product having at least one product property, the computer neural network process control method comprising the steps of: (1) configuring the neural network by specifying at least one specified interval, and by using data pointer(s) to individually specify at least one input, at least one output, and/or at least one training input; (2) training, either on-line or off-line, the neural network to produce a trained neural network; (3) at said at least one specified interval, predicting with said trained neural network second output data using second input data; and (4) controlling the process in accordance with said second output data.
Claim 2
Dependent Claim
124 words
A computer neural network process control method adapted for predicting output data provided to a controller used to control a process for producing a product having at least one product property, the computer neural network process control method comprising the steps of: (1) configuring the neural network by specifying at least one specified interval, and by using data pointer(s) to individually specify at least one input, at least one output, and/or at least one training input; (2) training, either on-line or off-line, the neural network to produce a trained neural network; (3) at said at least one specified interval, predicting with said trained neural network second output data using second input data; and (4) controlling the process in accordance with said second output data.
Claim 3
Dependent Claim
28 words
The computer neural network process control method of claim 1, wherein said step (1) of specifying using data pointers further comprises a step of specifying a data location.
Claim 4
Dependent Claim
28 words
The computer neural network process control method of claim 1, wherein said step (1) of specifying using data pointers further comprises a step of specifying a data type.
Claim 5
Dependent Claim
31 words
The computer neural network process control method of claim 3, wherein said step (1) of specifying using data pointers further comprises a step of specifying a current value of a measurement.
Claim 6
Dependent Claim
28 words
The computer neural network process control method of claim 3, wherein said step (1) of specifying using data pointers further comprises a step of specifying an historical value.
Claim 7
Dependent Claim
29 words
The computer neural network process control method of claim 3, wherein said step (1) of specifying using data pointers further comprises a step of specifying a time averaged value.
Claim 8
Dependent Claim
28 words
The computer neural network process control method of claim 3, wherein said step (1) of specifying using data pointers further comprises a step of specifying a setpoint value.
Claim 9
Dependent Claim
29 words
The computer neural network process control method of claim 1, wherein said step (1) of specifying using data pointers further comprises a step of specifying a data item number.
Claim 10
Dependent Claim
28 words
The computer neural network process control method of claim 8, wherein said step of specifying a data item number further comprises a step of specifying a measurement number.
Claim 11
Dependent Claim
29 words
The computer neural network process control method of claim 8, wherein said step of specifying a data item number further comprises a step of specifying a control loop number.
Claim 12
Dependent Claim
30 words
The computer neural network process control method of claim 8, wherein said step of specifying a data item number further comprises a step of specifying a control loop tag name.
Claim 13
Dependent Claim
36 words
The computer neural network process control method of claim 1, wherein said step (1) of specifying using data pointers further comprises a step of specifying, for data which is time varying, an oldest time interval boundary.
Claim 14
Dependent Claim
36 words
The computer neural network process control method of claim 1, wherein said step (1) of specifying using data pointers further comprises a step of specifying, for data which is time varying, a newest time interval boundary.
Claim 15
Dependent Claim
36 words
The computer neural network process control method of claim 1, wherein said step (1) of specifying using data pointers further comprises a step of specifying, for data which is time varying, one specific point in time.
Claim 16
Dependent Claim
27 words
The computer neural network process control method of claim 1, wherein said step (1) of specifying using data pointers further comprises a step of using a template.
Claim 17
Dependent Claim
34 words
The computer neural network process control method of claim 1, wherein said step (1) of specifying using data pointers further comprises a step of specifying a high limit value and/or a low limit value.
Claim 18
Dependent Claim
42 words
The computer neural network process control method of claim 16, wherein said step (2) of training and/or step (3) of predicting further comprise a step of scaling an input data in accordance with said high limit value and/or said low limit value.
Claim 19
Dependent Claim
42 words
The computer neural network process control method of claim 16, wherein said step (2) of training and/or step (3) of predicting further comprise a stem of clamping an output data in accordance with said high limit value and/or said low limit value.
Claim 20
Dependent Claim
43 words
The computer neural network process control method of claim 16, further comprising a step of disabling step (4) of the method when the value of an input, training input, or output is above said high limit value and/or below said low limit value.
Claim 21
Dependent Claim
176 words
A computer neural network process control method adapted for predicting output data provided to a controller used to control a process for producing a product having at least one product property, the computer neural network process control method comprising the steps of: (1) configuring the neural network by specifying at least one specified interval, and by using data pointer(s) to individually specify at least one input, at least one output, and/or at least one training input; and (2) training using said data pointer(s), either on-line or off-line, the neural network to produce a trained neural network comprising the substeps of: (a) retrieving at least one first training input data with an associated first timestamp indicating an associated first input data, (b) retrieving said associated first input data, (c) predicting a first output data using said associated first input data, (d) computing a first error data in accordance with said training input data and said first output data, and (e) training the neural network to produce said trained neural network in accordance with said first error data.
Claim 22
Dependent Claim
176 words
A computer neural network process control method adapted for predicting output data provided to a controller used to control a process for producing a product having at least one product property, the computer neural network process control method comprising the steps of: (1) configuring the neural network by specifying at least one specified interval, and by using data pointer(s) to individually specify at least one input, at least one output, and/or at least one training input; and (2) training using said data pointer(s), either on-line or off-line, the neural network to produce a trained neural network comprising the substeps of: (a) retrieving at least one first training input data with an associated first timestamp indicating an associated first input data, (b) retrieving said associated first input data, (c) predicting a first output data using said associated first input data, (d) computing a first error data in accordance with said training input data and said first output data, and (e) training the neural network to produce said trained neural network in accordance with said first error data.
Claim 23
Dependent Claim
46 words
The computer neural network process control method of claim 20, further comprising the steps of: at said at least one specified interval, predicting with said trained neural network second output data using second input data; and controlling the process in accordance with said second output data.
Claim 24
Dependent Claim
28 words
The computer neural network process control method of claim 20, wherein said step (1) of specifying using data pointers further comprises a step of specifying a data location.
Claim 25
Dependent Claim
28 words
The computer neural network process control method of claim 20, wherein said step (1) of specifying using data pointers further comprises a step of specifying a data type.
Claim 26
Dependent Claim
29 words
The computer neural network process control method of claim 20, wherein said step (1) of specifying using data pointers further comprises a step of specifying a data item number.
Claim 27
Dependent Claim
36 words
The computer neural network process control method of claim 20, wherein said step (1) of specifying using data pointers further comprises a step of specifying, for data which is time varying, an oldest time interval boundary.
Claim 28
Dependent Claim
36 words
The computer neural network process control method of claim 20, wherein said step (1) of specifying using data pointers further comprises a step of specifying, for data which is time varying, a newest time interval boundary.
Claim 29
Dependent Claim
36 words
The computer neural network process control method of claim 20, wherein said step (1) of specifying using data pointers further comprises a step of specifying, for data which is time varying, one specific point in time.
Claim 30
Dependent Claim
27 words
The computer neural network process control method of claim 20, wherein said step (1) of specifying using data pointers further comprises a step of using a template.
Claim 31
Dependent Claim
34 words
The computer neural network process control method of claim 20, wherein said step (1) of specifying using data pointers further comprises a step of specifying a high limit value and/or a low limit value.
Claim 32
Dependent Claim
42 words
The computer neural network process control method of claim 29, wherein said step (2) of training and/or step (3) of predicting further comprise a step of scaling an input data in accordance with said high limit value and/or said low limit value.
Claim 33
Dependent Claim
42 words
The computer neural network process control method of claim 29, wherein said step (2) of training and/or step (3) of predicting further comprise a step of clamping an output data in accordance with said high limit value and/or said low limit value.
Claim 34
Dependent Claim
43 words
The computer neural network process control method of claim 29, further comprising a step of disabling step (4) of the method when the value of an input, training input, or output is above said high limit value and/or below said low limit value.
Claim 35
Dependent Claim
159 words
A computer neural network process control system adapted for predicting output data provided to a controller used to control a process for producing a product having at least one product property, the computer neural network process control system comprising: (a) an historical database comprising, (1) storing means for storing a first training input data with an associated first timestamp, and for storing a first input data indicated by said associated first timestamp, and (2) retrieving means, responsive to said storing means, for retrieving said first training input data and said first input data indicated by said associated first timestamp; and (b) a neural network comprising, (1) a first data pointer and a second data pointer, (2) training means, responsive to said historical database, for training said neural network in accordance with said first training input data specified by said first data pointer and said first input data specified by said second data pointer to produce a trained neural network.
Claim 36
Dependent Claim
159 words
A computer neural network process control system adapted for predicting output data provided to a controller used to control a process for producing a product having at least one product property, the computer neural network process control system comprising: (a) an historical database comprising, (1) storing means for storing a first training input data with an associated first timestamp, and for storing a first input data indicated by said associated first timestamp, and (2) retrieving means, responsive to said storing means, for retrieving said first training input data and said first input data indicated by said associated first timestamp; and (b) a neural network comprising, (1) a first data pointer and a second data pointer, (2) training means, responsive to said historical database, for training said neural network in accordance with said first training input data specified by said first data pointer and said first input data specified by said second data pointer to produce a trained neural network.
Claim 37
Dependent Claim
25 words
The computer neural network process control system of claim 33, further comprising sensor means, responsive to said historical database, for providing said first input data.
Claim 38
Dependent Claim
24 words
The computer neural network process control system of claim 34, further comprising clock means for providing an associated second timestamp to said historical database.
Claim 39
Dependent Claim
30 words
The computer neural network process control system of claim 33, wherein said first training input data includes data indicative of a past action of an human operator of the process.
Claim 40
Dependent Claim
25 words
The computer neural network process control system of claim 33, wherein said neural network comprises a software system adapted to run on a computer platform.
Claim 41
Dependent Claim
23 words
The computer neural network process control system of claim 33, further comprising output means for storing the output data in said historical database.
Claim 42
Dependent Claim
26 words
The computer neural network process control system of claim 33, wherein said first data pointer and said second data pointer are three-part pointers with additional qualifiers.
References Cited (Backward Citations)
US4193115A
Cited
US4858147A
Cited
WO1989003092A1
Cited
US4994982A
Cited
JPH01224804A
Cited
US5111531A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1996-06-28 | 1996-12-28 | 1997-06-29 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2000-06-28 | 2000-12-28 | 2001-06-29 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2004-06-28 | 2004-12-28 | 2005-06-29 | $7700.00 | Window Closed / Lapsed |