Tracking of a tagged leopard shark with an AUV: Sensor calibration and state estimation

Whether sensor model’s inaccuracies are a result of poor initial modeling or from sensor damage or drift, the effects can be just as detrimental. Sensor modeling errors result in poor state estimation. This, in turn, can cause a control system relying upon the sensor’s measurements to become unstable, such as in robotics where the control system is applied to allow autonomous navigation. A technique referred to as a neural extended Kalman filter (NEKF) is developed to provide both state estimation in a control loop and to learn the difference between the true sensor dynamics and the sensor model. The technique requires multiple sensors on the control system so that the properly operating and modeled sensors can be used as truth. The NEKF trains a neural network on-line using the same residuals as the state estimation. The resulting sensor model can then be reincorporated fully into the system to provide the added estimation capability and redundancy.

Download Full-text

Investigation on the Condition Evaluation Method Based on NSET Model of the Propulsion System in Large Scale Ship

Volume 13: Safety Engineering, Risk, and Reliability Analysis ◽

10.1115/imece2019-11161 ◽

2019 ◽

Author(s):

Jinxin Zhao ◽

Jian Zhou ◽

Peng Shang ◽

Yinxun Zhang

Keyword(s):

State Estimation ◽

Large Scale ◽

Evaluation Method ◽

Propulsion System ◽

Sensor Calibration ◽

Operating Characteristics ◽

Nonlinear State Estimation ◽

Condition Evaluation ◽

Wide Range ◽

Nonlinear State

Abstract The condition of the propulsion system in large scale ship directly affects the quality and safety of the ship’s operation, so it is important to evaluate the condition of the propulsion system. The Nonlinear State Estimation Technology (NSET) method is a nonparametric modeling method, which is mostly used in nuclear power plant sensor calibration, equipment monitoring, and electronic product life prediction. In this paper, the nonlinear state estimation technology (NSET) method is applied to the condition evaluation of the propulsion system. According to the operating characteristics and state parameters of the propulsion system, this paper first performs data preprocessing, and then uses the prepossessed data to perform condition evaluation by the NSET method. The model method can be connected with the database system. It has the advantages of faster evaluation speed and higher precision, and can detect possible failures of equipment system in time. This method has a wide range of adaptability.

Download Full-text