ANOMALY MONITORING DEVICE

摘要

PROBLEM TO BE SOLVED: To detect signs of anomalies and prevent the misidentification of a temporary disturbance of a target signal as an anomaly in an inspection object. SOLUTION: A signal input part 2 captures a target signal depending on the operation of a piece of equipment X. A feature extraction part 3 extracts a feature vector representing features of the target signal. A category classification part 1 comprises a competitive learning neural network whose input data is the feature vector extracted by the feature extraction part 3. A divergence computation part 4 computes as a divergence the size of a difference vector between weight vectors set in neurons of an output layer of the category classification part 1 and the feature vector depending on the operation of the piece of equipment X. A history recording part 5 records a history of the divergence computed by the divergence computation part 4. A determination part 6 determines that there is a sign of anomaly in the operation state of the piece of equipment X when the rate of change in the divergence history reaches a prescribed value for a duration. COPYRIGHT: (C)2008,JPO&INPIT