Yujia Wang

Model updating and thruster fault diagnosis for underwater vehicle

As the impact of underwater vehicle dynamics modeling error on fault diagnosis system, a method using improved Elman neural network to modify underwater vehicle dynamics model in the current is proposed. The neural network parameter adjustment law under the Lyapunov stability is given. Sliding mode observer is constructed for state estimation based on the modified dynamics model. The change of state estimation residual of each DOF is analyzed when fault occurs in different thrusters of under vehicle. A thruster fault diagnosis method based on residual state fusion is presented, which has been validated through AUV sea trials data.

Neural networks modelling and generalised predictive control for an autonomous underwater vehicle

This paper investigates the application of neural networks-based generalised predictive motion control for an autonomous underwater vehicle (AUV). The modified Elman neural networks (MENNs) are used as the multi-step predictive model, and the fused identification model is proposed to improve the predictive and control precision. The MENNs online learning improves the control system adaptability to the unpredictable operating environment for AUV. Simulations on AUV yaw velocity control are concluded to illustrate the effectiveness of the proposed control scheme.

Research of intelligent condition monitoring model for AUV

An intelligent condition monitoring model for propellers and rudder of autonomous underwater vehicles (AUVs) was proposed, which was based on the FALCON with a 3-step learning algorithm. The steps of the algorithm included initialization with fuzzy C clustering, rules extraction with maximum weights matrix and parameters fine-tuning with GA. It constructed the configuration of the model, analyzed the process of the monitoring, and discussed the method of evaluation for the model. The results of the computer simulation by actual experiment data of a certain AUV shows that the condition monitoring model proposed in this article is feasible and prove that the learning algorithm for the FALCON is effective.

Fault-tolerant control based on adaptive sliding mode for underwater vehicle with thruster fault

An adaptive sliding mode backstepping fault-tolerant control is proposed for autonomous underwater vehicle(AUV) with thruster faults. Thruster faults are treated as uncertainties. Gaussian radial-basis-function networks are used to approximate these general uncertainties. In addtion, no Fault Detection and Diagnosis unit is needed in the proposed method.The controller can guarantee closed-stability regardless of thruster fault occurs or not. Due to the controlled system is strict-feedback in the traditional backstepping scheme, an improved backstepping scheme integrating with adaptive sliding mode algorithm. Finally, simulations are carried out to verify the validity of the proposed strategy.

Research on Platform and Motion Control System for a Mobile Robot

This paper presents a kind of wheeled mobile robot, which adopted the architecture of two wheels differential drive and multilayer stack mechanical structure and used a special embedded computer PC/104 as the kernel of the robot motion control system, and the good openness and expandability of this architecture will avail the further development. The traditional angular speed control of a wheeled mobile robot is achieved indirectly by the respective control of the left and the right wheels speeds. But the problem that the effect of a wheeled mobile robots angular speed control is weak arises from the great error of the actual angular speed and the demanded angular speed because of the sliding of the wheels. By the analysis of the motion model of the wheeled mobile robot, it proposes a method of a new two parameters PID motion controller which is based on the parameter distributor without the decoupling of the two motion control parameters (speed and angular speed) to overcome the problem mentioned above. The results of the experimentation of linear, circumferential and sinusoidal trajectory motions show that the controller is feasible and effective

Weak thruster fault prediction method for autonomous underwater vehicles based on grey model

When adopting the conventional grey model (GM(1,1)) to predict weak thruster fault for autonomous underwater vehicles, the prediction error is not always satisfactory. In order to solve the problem, this article develops a new weak thruster fault prediction method based on an improved GM(1,1). In the developed GM(1,1) based fault prediction method, this article mainly makes improvement in the following aspects: construction of grey background value, solution of whiting differential equation and construction of predicted sequence. Specifically, the integral operation is used in range of the two adjacent steps to obtain the grey background value at first. Second, in the solving of whiting differential equation, the point corresponding to the least difference between the accumulated generation sequence and its predicted sequence is determined, and then this special point’s value in the original sequence is considered as the initial condition of the whiting differential equation. Third, in the construction of predicted sequence, another predicted value is obtained based on the error sequence between the accumulated generating operation sequence and its predicted sequence, and then the new predicted result is used to re-adjust the accumulated generating operation sequence, so as to guarantee the re-adjustability of the fault prediction result. Finally, experiments are performed on Beaver 2 autonomous underwater vehicle to evaluate the prediction performance of the developed method.

Fault degree identification method for thruster of autonomous underwater vehicle using homomorphic membership function and low frequency trend prediction

This article presents a novel thruster fault degree identification method for autonomous underwater vehicle. The novel method is developed from the fuzzy support vector domain description method, which establishes a fault identification model first, and then estimates fault degree according to the model. When establishing fault identification model for thruster based on fuzzy support vector domain description method, it is found that the relative fitting error of the model to the actual fault degree is large, making the model accuracy poor. To reduce the relative fitting error, a homomorphic membership function method is proposed. Different from fuzzy support vector domain description method, which calculates the fuzzy membership degree of fault sample in time domain, the proposed method calculates the fuzzy membership degree in log domain. On estimating thruster fault degree by fuzzy support vector domain description method, it is obtained that the estimated fault degree lags behind the actual fault degree. To shorten the lag time, a low frequency trend prediction method is proposed. Different from fuzzy support vector domain description method, which brings the fault feature extracted from the current surge speed and control voltage into the fault identification model to calculate fault degree, the proposed method firstly forward predicts surge speed and control voltage, and then takes the fault feature extracted from the predicted surge speed and control voltage into the model to acquire fault degree. The effectiveness of the proposed methods is verified by pool experiments of the experimental prototype.

Thruster fault identification based on fractal feature and multiresolution wavelet decomposition for autonomous underwater vehicle

There exist some problems when the fractal feature method is applied to identify thruster faults for autonomous underwater vehicles (AUVs). Sometimes it could not identify the thruster fault, or the identification error is large, even the identification results are not consistent for the repeated experiments. The paper analyzes the reasons resulting in these above problems according to the experiments on AUV prototype with thruster faults. On the basis of these analyses, in order to overcome the above deficiency, an improved fractal feature integrated with wavelet decomposition identification method is proposed for AUV with thruster fault. Different from the fractal feature method where the signal extraction and fault identification are completed in the time domain, the paper makes use of the time-domain and frequent-domain information to identify thruster faults. In the paper, the thruster fault could be mapped multisource and described redundantly by the fault feature matrix constructed based on the time-domain and frequent-domain information. In the process of identification, different from the fractal feature method where the fault is identified based on fault identification model, the fault sample bank is built at first in the paper, and then pattern recognition is achieved by calculating the relative coefficients between the constructed fault feature matrix and the elements in the fault sample bank. Finally, the online pool experiments are performed on an AUV prototype, and the effectiveness of the proposed method is demonstrated in comparison with the fractal feature method.

Weak thruster fault prediction method for autonomous underwater vehicle

Conventional grey GM(1,1) method might generate much large prediction errors when predicting the trend of weak thruster fault. To solve this problem, a prediction method based on improved grey prediction model is proposed. The proposed method selects the known sequence point with the minimum prediction error as the initial condition of grey derivative model, rather than first element of the known sequence in the conventional method, so as to improve the robustness of the method to external disturbance and obtain better prediction precision. Compared with the sequence generation process of the conventional grey GM(1,1) method, this paper constructs the grey background value of exponent curve to reduce the error of grey differential equation solution, so as to reduce the prediction errors. In the proposed method, the residual series between the forecasting sequence and original one is constructed to re-predict, and the result is used to modify the predictive value of thruster fault so as to improve prediction precision. Poolexperiments are performed on a prototype AUV by simulating thruster weak fault. The comparative experiment results based on the proposed method and the conventional grey GM(1,1) method demonstrate the effectiveness of the proposed method.

Study on qualitative modeling of underwater robot

To deal with the difficulty of establishing the accurate dynamics mathematical model of the underwater robots, a qualitative modeling method of underwater robots dynamics is presented based on qualitative simulation. Considering the complexity of the working environment and particularity of the non-linear movement process of underwater robots, through determining the landmark values and distinguished time-point selection method as well as qualitative state representation in the qualitative behavior of reasoning, an approach about qualitative processing quantitative information is proposed. Moreover, the qualitative constraints in different operating modes are analyzed. As a result, the qualitative state transition sequence is determined. The water tank experiment validates the feasibility of dynamics modeling of underwater robot based on qualitative simulation.