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.
Terrain-aided navigation is a potentially powerful solution for obtaining submerged position fixes for autonomous underwater vehicles. The application of terrain-aided navigation with high-accuracy inertial navigation systems has demonstrated meter-level navigation accuracy in sea trials. However, available sensors may be limited depending on the type of the mission. Such limitations, especially for low-grade navigation sensors, not only degrade the accuracy of traditional navigation systems, but further impact the ability to successfully employ terrain-aided navigation. To address this problem, a tightly-coupled navigation is presented to successfully estimate the critical sensor errors by incorporating raw sensor data directly into an augmented navigation system. Furthermore, three-dimensional distance errors are calculated, providing measurement updates through the particle filter for absolute and bounded position error. The development of the terrain aided navigation system is elaborated for a vehicle equipped with a non-inertial-grade strapdown inertial navigation system, a 4-beam Doppler Velocity Log range sensor and a sonar altimeter. Using experimental data for navigation performance evaluation in areas with different terrain characteristics, the experiment results further show that the proposed method can be successfully applied to the low-cost AUVs and significantly improves navigation performance.
The application of long baseline aided strap-down inertial navigation system (SINS/LBL) has been demonstrated to be an effective solution for accumulative position errors of underwater vehicles (UVs). To address the inefficient positioning when available hydrophones are few in acoustic array, a hybrid tightly-coupled SINS/LBL is presented for underwater navigation system. The system is composed of SINS, LBL and pressure sensor (PS). The hybrid positioning model based on slant range, slant-range rate, slant-range difference and slant-range rate difference is established according to the location principle of time of arrival (TOA) and time difference of arrival (TDOA) when the number of available hydrophones is two. TDOA positioning model based on slant-range difference and slant-range rate difference is adopted when the number of available hydrophones is more than two. The two tightly-coupled SINS/LBL models could be switched with each other as the number of available hydrophones changes in acoustic array. This paper used experimental data obtained from an unmanned surface vehicle (USV) to validate the navigation performance. Compared with single tightly-coupled SINS/LBL model, the proposed method can provide faster error convergence and more accurate submerged position fixes.
Detecting subsystem faults quickly is critical to the accuracy and reliability of integrated navigation systems. This paper, therefore, proposes an effective approach based on the novel test statistic to detect faults. Machine learning is introduced to estimate the innovation and its variance of local filter. The estimates combined with the actual ones are used to construct the test statistic, which is then proved to obey chi-square distribution. Thus fault detection can be realized by chi-square test. However, the special structure of the test statistic makes it sensitive to faults, even to the gradual faults. The experimental results demonstrate that the approach can detect faults quickly. Especially for gradual fault detection, the proposed test statistic has a marked superiority compared with the traditional test statistic of residual chi-square test.
To enhance the precision and reliability of integrated navigation systems, a novel fault-tolerant information fusion algorithm based on a federated filter is proposed. Decentralized filtering architecture is employed to fuse information from different navigation subsystems. The chi-square detection function and the filter innovation correlation are used as inputs to the fuzzy system, which then outputs the observation quality factor. The observation quality factor directly reflects the reliability of the measurement data and is utilized to adjust the local filter gain matrix online. Additionally, the information sharing coefficients, determined by the observation quality factors, ensure dependable fault isolation while improving the sensitivity of fault detection to gradual faults. Comparative experimental results demonstrate that the proposed method effectively detects various faults and significantly enhances the performance of the integrated navigation system during malfunctions.