“…Figure 1 shows the block diagram of the INS/DVL navigation system in the loss of GPS signals and any fault detection mechanism. Figure 1.Block diagram of the integrated navigation system with loss of fault detection and fault-tolerant mechanisms (Ansari-Rad et al., 2019a)…”
“…To check the advantages and probable disadvantages of I-eTS in the practical navigation system, the fault detection scheme is invoked by adopting the GPR model in this paper. The GPR model requires a training phase (Ansari-Rad et al, 2019a).…”
Section: Introductionmentioning
confidence: 99%
“…Despite the mentioned references, in this paper the FTS method is performed by replacing the faulty sensor with an analytical sensor (pseudo sensor) after the fault detection system finds the fault occurrence. Recently we designed an improved evolutionary TS-fuzzy (I-eTS) algorithm, with self-adaptation and online process of the system structure, to be used for reconstruction of DVL signals at moments when faults occur (Ansari-Rad et al., 2019a). This paper adopts an algorithm to reconstruct DVL signals by evolutionary TS-fuzzy (I-eTS) to improve fault tolerance for INS/DVL.…”
The inertial navigation system/Doppler velocity logger (INS/DVL) plays an important role in ocean navigation. Any DVL malfunction poses serious risks to navigation. A precise detection system is required to detect the initial moments of DVL signal malfunctions; moreover, with loss of DVL, a fault-tolerant scheme (FTS) is necessary for DVL signal reconstruction. In this paper, an evolutionary knowledge-based method, namely improved evolutionary TS-fuzzy (I-eTS), is adopted to build an artificial intelligence (AI)-based pseudo DVL to deal with long-term outage of DVL. By employing Gaussian process regression (GPR) models for fault detection, a new FTS is constructed. To verify the effectiveness of the new fault detection and fault tolerance system, navigation data is gathered by a test setup and algorithms are performed in the laboratory. In the tests, it is demonstrated that the proposed FTS leads to rapid detection of both gradual and abrupt faults, which leads to less interaction between fault detection and FTS.
“…Figure 1 shows the block diagram of the INS/DVL navigation system in the loss of GPS signals and any fault detection mechanism. Figure 1.Block diagram of the integrated navigation system with loss of fault detection and fault-tolerant mechanisms (Ansari-Rad et al., 2019a)…”
“…To check the advantages and probable disadvantages of I-eTS in the practical navigation system, the fault detection scheme is invoked by adopting the GPR model in this paper. The GPR model requires a training phase (Ansari-Rad et al, 2019a).…”
Section: Introductionmentioning
confidence: 99%
“…Despite the mentioned references, in this paper the FTS method is performed by replacing the faulty sensor with an analytical sensor (pseudo sensor) after the fault detection system finds the fault occurrence. Recently we designed an improved evolutionary TS-fuzzy (I-eTS) algorithm, with self-adaptation and online process of the system structure, to be used for reconstruction of DVL signals at moments when faults occur (Ansari-Rad et al., 2019a). This paper adopts an algorithm to reconstruct DVL signals by evolutionary TS-fuzzy (I-eTS) to improve fault tolerance for INS/DVL.…”
The inertial navigation system/Doppler velocity logger (INS/DVL) plays an important role in ocean navigation. Any DVL malfunction poses serious risks to navigation. A precise detection system is required to detect the initial moments of DVL signal malfunctions; moreover, with loss of DVL, a fault-tolerant scheme (FTS) is necessary for DVL signal reconstruction. In this paper, an evolutionary knowledge-based method, namely improved evolutionary TS-fuzzy (I-eTS), is adopted to build an artificial intelligence (AI)-based pseudo DVL to deal with long-term outage of DVL. By employing Gaussian process regression (GPR) models for fault detection, a new FTS is constructed. To verify the effectiveness of the new fault detection and fault tolerance system, navigation data is gathered by a test setup and algorithms are performed in the laboratory. In the tests, it is demonstrated that the proposed FTS leads to rapid detection of both gradual and abrupt faults, which leads to less interaction between fault detection and FTS.
“…In Reference [16], extended Kalman filter (EKF) combined with the Adams explicit formula has great accuracy and effectiveness in terms of attitudes estimation and can be well applied in underwater gliders for a long time of period. In Reference [17], EKF assisted with Takagi-Sugeno fuzzy algorithm is proposed. Under this kind of computational intelligence, INS/DVL integrated system maintains high ability of self-adaptation on system structure and parameters during the online process of state estimation and prediction.…”
It is necessary to locate the precise timing of switching into non-damping mode when the ship comes across zigzag maneuver, which helps avoid overshoot errors and maintain accuracy of ship's attitudes. In this paper, we propose a novel method to make the right decision on the damping/non-damping switch timing selection. Ship's in-motion data, collected by the gyrocompass system in advance, will first be pre-processed using wavelet denoising procedure and then treat as support vector machine (SVM) training input. Once the model is established, strapdown fiber optic gyrocompass (FOGC) can be equipped with the ability of self-judgment on when to cut off the alignment closed loops to become invulnerable and when to let it back online to remain stable by means of SVM classification schemes for switch timing recognition. Results show our method has better performance in the time of ships maneuver compared to the whole course damping network solution. Furthermore, transverse comparisons indicate our Wavelet-SVM method has better performance than BP neural network and traditional threshold method during maneuvering navigation process. INDEX TERMS Strapdown gyrocompass, alignment loops, switch timing, support vector machine, wavelet denoising.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
