A Novel Hybrid Approach to Deal with DVL Malfunctions for Underwater Integrated Navigation Systems

TLDR

Doppler velocity logs are widely used in underwater navigation but are prone to malfunction. This study proposes a hybrid forecasting approach to maintain navigation reliability when DVLs fail. The method combines partial least squares regression and support vector regression, using current and past SINS velocities as inputs, and is trained online to predict DVL measurements during outages. Simulation results show the hybrid predictor extends DVL fault tolerance time and improves navigation accuracy and reliability.

Abstract

As a common device for underwater integrated navigation systems, Doppler velocity log (DVL) has the risk of malfunction. To improve the reliability of navigation systems, a hybrid approach is presented to forecast the measurements of the DVL while it malfunctions. The approach employs partial least squares regression (PLSR) coupled with support vector regression (SVR) to build a hybrid predictor. As the current and past calculating velocities of strapdown inertial navigation system (SINS) are taken as the predictor’s inputs, PLSR is applied to cope with the situation where there exists intense relativity among independent variables. Since PLSR is a linear regression, SVR is used to predict the residual components of the PLSR prediction to improve the accuracy. When the DVL works well, the hybrid predictor is trained online as a backup, whereas during malfunctions, the predictor offers the estimation of the DVL measurements for information fusion. The performance of the proposed approach is verified with simulations based on SINS/DVL/MCP/pressure sensor (PS) integrated navigation system. The comparison results indicate that the PLSR-SVR hybrid predictor can correctly provide the estimated DVL measurements and effectively extend the tolerance time on DVL malfunctions, thereby improving the navigation accuracy and reliability.