Supervision of a neutron detector in a nuclear reactor
First Claim
1. A method of monitoring neutron flux detectors in a nuclear reactor with a neural network, said network comprising an input layer adapted to receive a number of input signals corresponding to values at different times of a measured signal;
- and an output layer adapted to deliver a number of state signals, said method comprising the steps of;
supplying said network with a plurality of input signals with known state signals to teach said network to identify a number of different trends of said measured signal such that said state signals indicate said trends;
supplying said network with input signals corresponding to values at different times of a measured signal from a supervised detector;
supplying said network with input signals corresponding to values at different times of measured signals from a number of reference detectors;
calculating state signals for said supervised detector and for said reference detectors; and
determining whether said supervised detector is defective based on said state signals.
2 Assignments
0 Petitions
Accused Products
Abstract
A method of monitoring neutron flex detectors in a nuclear reactor in a neural network is provided. The network comprises an input layer which receives a number of input signals corresponding to values of a measured signal at different times and an output layer which is adapted to deliver a number of state signals. The network is taught to identify a number of different trends of the measured signal such that the state signals indicate the trends, by supplying the network with a plurality of input signals which have known state signals. The network is then supplied with input signals which correspond to values of a measured signal taken at different times from a supervised detector. Also, input signals corresponding to values of measured signals taken at different times from a reference detector are supplied to the network. Next, state signals for the supervised detector and for the reference detectors are calculated and whether the supervised detector is defective is determined based on the state signals.
35 Citations
5 Claims
-
1. A method of monitoring neutron flux detectors in a nuclear reactor with a neural network, said network comprising an input layer adapted to receive a number of input signals corresponding to values at different times of a measured signal;
- and an output layer adapted to deliver a number of state signals, said method comprising the steps of;
supplying said network with a plurality of input signals with known state signals to teach said network to identify a number of different trends of said measured signal such that said state signals indicate said trends; supplying said network with input signals corresponding to values at different times of a measured signal from a supervised detector; supplying said network with input signals corresponding to values at different times of measured signals from a number of reference detectors; calculating state signals for said supervised detector and for said reference detectors; and determining whether said supervised detector is defective based on said state signals. - View Dependent Claims (2, 3, 4, 5)
- and an output layer adapted to deliver a number of state signals, said method comprising the steps of;
Specification
-
- Resources
-
Current AssigneeWestinghouse ATOM AB
-
Original AssigneeABB AB (ABB Limited)
-
InventorsTiusanen, Mika, Ocieczek, Grzegorz
-
Primary Examiner(s)Wasil, Daniel D.
-
Application NumberUS08/750,004Time in Patent Office516 DaysField of Search376/215, 376/216, 376/217, 376/254, 395/21-24, 395/907, 395/915, 364/148, 364/224.9, 364/275.2, 364/551.01, 364/924.4, 364/972.4US Class Current376/254CPC Class CodesG21C 17/108 Measuring reactor fluxY02E 30/30 Nuclear fission reactorsY10S 706/915 Power plant
