US5345539A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Radar apparatus using neural network for azimuth and elevation detection
Assignee: UK Secretary of State for Defence
•
Filing: 1991-10-30
•
Granted: 1994-09-06
•
Expires: 2011-10-30
Abstract
Abstract Radar apparatus used for point-source location, where an adaptive feed forward artificial neural network is used to calculate a position vector from image information provided by radar receiving element outputs. Where an object is sensed within a field of view of a multiple output radar, then the radar receiving sensor element outputs are processed inputs as image vectors for use in input nodes of an input node layer of the artificial neural network. Typically the neural network has the same number of input nodes as the number of sensor element outputs an array within the radar receiver. Increased accuracy of point-source location can be achieved by increasing the number of hidden layers used, and/or increasing the number of nodes within each hidden layer. Training of the artificial neural network is described for (5×1), (1×5) and (4×4) radar receiving arrays, and also for idealised and noisy data.
Inventors
- 👤 Andrew R. Webb
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-25 22:48
CPC Classifications
G; G01; G01S; G01S7/00; G01S7/02; G01S7/41; G01S7/417; G01S13/00; G01S13/88; G01S13/89; G06; G06N; G06N3/00; G06N3/02
Claims Analysis
Total Claims: 9
Claim 1
Independent Claim
83 words
Radar apparatus of multiple outputs comprising: an array of independent radar receiving sensor elements, each element for providing an output, signal processing means for providing image information in the form of data vectors which are dependent on the element outputs, means for calculating a position vector from the image information wherein said calculating means comprises an adaptive feed forward artificial neural network, said network comprising an input layer of nodes, at least one hidden layer of nodes and an output layer of nodes.
Claim 2
Dependent Claim
83 words
Radar apparatus of multiple outputs comprising: an array of independent radar receiving sensor elements, each element for providing an output, signal processing means for providing image information in the form of data vectors which are dependent on the element outputs, means for calculating a position vector from the image information wherein said calculating means comprises an adaptive feed forward artificial neural network, said network comprising an input layer of nodes, at least one hidden layer of nodes and an output layer of nodes.
Claim 3
Dependent Claim
21 words
Radar apparatus as claimed in claim 1 where the adaptive feed forward artificial neural network has one hidden layer of nodes.
Claim 4
Dependent Claim
16 words
Radar apparatus as claimed in claims 1 where the output layer of nodes has two nodes.
Claim 5
Dependent Claim
27 words
Radar apparatus as claimed in claim 1 wherein at least one layer of nodes in said neural network includes a constant output node for providing local biassing.
Claim 6
Dependent Claim
21 words
Radar apparatus as claimed in claim 1 wherein said array of independent radar receiving sensor elements is a two dimensional array.
Claim 7
Dependent Claim
21 words
Radar apparatus as claimed in claim 1, further including means for carrying out a Fast Fourier Transform on said data vectors.
Claim 8
Dependent Claim
143 words
Radar apparatus for determination of the location of a point source comprising: a two dimensional array of independent radar receiving sensor elements, each element for providing an output, signal processing means for providing image information in the form of data vectors corresponding to and dependent on each array element, and an adaptive feed forward artificial neural network for calculating a position vector from a single pass of the image information, said network comprising an input layer of nodes containing one node for each sensor in the array, a hidden layer of nodes and an output layer of two nodes, one of said two nodes in said output layer for providing data relating to azimuth and the other of said two nodes for providing information relating to elevation, with a constant output node included in each of said input layer and said hidden layer.
Claim 9
Dependent Claim
143 words
Radar apparatus for determination of the location of a point source comprising: a two dimensional array of independent radar receiving sensor elements, each element for providing an output, signal processing means for providing image information in the form of data vectors corresponding to and dependent on each array element, and an adaptive feed forward artificial neural network for calculating a position vector from a single pass of the image information, said network comprising an input layer of nodes containing one node for each sensor in the array, a hidden layer of nodes and an output layer of two nodes, one of said two nodes in said output layer for providing data relating to azimuth and the other of said two nodes for providing information relating to elevation, with a constant output node included in each of said input layer and said hidden layer.
References Cited (Backward Citations)
EP0362874A2
Cited
US5001631A
Cited
US5003490A
Cited
US5093781A
Cited
US5168550A
Cited
US4945494A
Cited
US4954963A
Cited
WO1991002323A1
Cited
US5150323A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1997-09-05 | 1998-03-07 | 1998-09-06 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2001-09-05 | 2002-03-07 | 2002-09-06 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2005-09-05 | 2006-03-07 | 2006-09-06 | $7700.00 | Window Closed / Lapsed |