Tracking of ships’ motion and monitoring of maritime traffic can be performed with the use of distributed Kalman Filtering. However, some of the local Kalman Filters which constitute distributed estimation schemes may be based on inaccurate models of the vessel’s dynamics or kinematics and in such a case the aggregate state estimate provided by the distributed filter is unreliable. To treat this problem the paper proposes a statistical method of optimized performance for the validation of Fuzzy Kalman Filters used in ship tracking. This statistical validation test is capable of detecting the faulty local filter within the distributed estimation method, even in the case of small errors in the local model’s parameters which do not exceed 1% of the associated nominal values.
Validation of the Fuzzy Kalman Filter for ship tracking applications
SIANO, PIERLUIGI;
2015
Abstract
Tracking of ships’ motion and monitoring of maritime traffic can be performed with the use of distributed Kalman Filtering. However, some of the local Kalman Filters which constitute distributed estimation schemes may be based on inaccurate models of the vessel’s dynamics or kinematics and in such a case the aggregate state estimate provided by the distributed filter is unreliable. To treat this problem the paper proposes a statistical method of optimized performance for the validation of Fuzzy Kalman Filters used in ship tracking. This statistical validation test is capable of detecting the faulty local filter within the distributed estimation method, even in the case of small errors in the local model’s parameters which do not exceed 1% of the associated nominal values.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
