An underwater moving dipole tracking method of artificial lateral line based on intelligent optimization and recursive filter DOI
Yu Liu, Qiao Hu, Qian Yang

и другие.

Measurement Science and Technology, Год журнала: 2022, Номер 33(7), С. 075113 - 075113

Опубликована: Март 15, 2022

Abstract Inspired by the lateral line system of fish, an artificial is proposed for underwater target detection. The dipole treated as a standard and simplified target. In previous studies, most researchers focused on at fixed position trajectory tracking moving was barely considered. this paper, new method proposed. First, based instant pressure amplitude loss function, tracked particle swarm optimization (PSO). Then, PSO-tracked optimized using recursive filters such Kalman filter (KF) (PF) to reduce error. experiment result showed that when rectangular, accuracy PSO competitive compared with Gauss–Newton method. mean error distance (MED) 12.51 mm. PF better performance than KF in study, corresponding MED 7.064 main factor caused errors mismatch. simulation, mismatch not considered, highly improved.

Язык: Английский

Artificial Lateral Lines-based an Active Obstacle Recognition Strategy and Performance Evaluation for Bionic Underwater Robots DOI
Ao Li, Shuxiang Guo, Chunying Li

и другие.

IEEE Sensors Journal, Год журнала: 2024, Номер 24(16), С. 26266 - 26277

Опубликована: Авг. 15, 2024

Язык: Английский

Процитировано

2

An underwater moving dipole tracking method of artificial lateral line based on intelligent optimization and recursive filter DOI
Yu Liu, Qiao Hu, Qian Yang

и другие.

Measurement Science and Technology, Год журнала: 2022, Номер 33(7), С. 075113 - 075113

Опубликована: Март 15, 2022

Abstract Inspired by the lateral line system of fish, an artificial is proposed for underwater target detection. The dipole treated as a standard and simplified target. In previous studies, most researchers focused on at fixed position trajectory tracking moving was barely considered. this paper, new method proposed. First, based instant pressure amplitude loss function, tracked particle swarm optimization (PSO). Then, PSO-tracked optimized using recursive filters such Kalman filter (KF) (PF) to reduce error. experiment result showed that when rectangular, accuracy PSO competitive compared with Gauss–Newton method. mean error distance (MED) 12.51 mm. PF better performance than KF in study, corresponding MED 7.064 main factor caused errors mismatch. simulation, mismatch not considered, highly improved.

Язык: Английский

Процитировано

9