Tang Xu-dong

A fuzzy neural networks controller of underwater vehicles based on ant colony algorithm

Owing to the characteristic of autonomous underwater vehicles (AUV) control and to solve the typical nonlinearity control system, we deduced a new fuzzy neual network control based on expert experience and ant colony algorithm. This algorithm superiority in solving combination optimization problems which consists of the rule sets and parameters of the membership functions of the continuous fuzzy controller to be slected. In order to enhance the efficiency of ant colony algorithm and prevent the precocity, the expert experience and improving ant colony algorithm are introduced in. Simulation results and applications showed that method is effective enough to make control simpler and robust and to get good control performance.

Multi-threshold image segmentation based on two-dimensional Tsallis

Image multi-threshold segmentation method based on two-dimensional Tsallis entropy is proposed by utilizing Tsallis entropy. The improved particle swarm optimization is used to search best two-dimensional multi-threshold vectors by maximising the two-dimensional Tsallis entropy. The proposed method not only considers the spatial information of pixels, but also the interaction between the object and background, the different responses in variant grey level. The experimental results show that the new algorithm is better than the tradition methods with both a better stability and a higher speed.

S Plane Control of underwater vehicle and its hybrid training algorithm

For the particular control object of automatic underwater vehicles (AUV), an S Plane Control based on the analysis of fuzzy control and combined with the form of PID control is introduced which is a simple and effective method, but parameters must be manually set for its controller. In order to improve the adaptability of AUV, the adaptive S Plane Control algorithm based on single neuron cell is proposed as well, in which parameters self adjustment come true. But the neural network has many defects, such as learning slowly, easy get into local convergence and learning results depend on initial condition. This improved method is proposed on which improved PSO algorithm is used offline first for optimizing which can avoid the phenomenon of precocity and stagnation during evolution, followed by online adjustment with single neuron cell algorithm. The feasibility and advantages of this method are demonstrated by simulation test results.

Simulation system of underwater vehicle using VC and Vega

Simulation system of automatic underwater vehicle (AUV) is very important in the whole R&D (research and development) process because of the complexity and uncertainty of the real ocean environment. Accordingly, the six freedom motion simulation system is presented, which was established by Visual C++. Secondly, establishing AUV entity model in Multigen Creator and putting it into the vision simulation system that made by Vega. At last, combining two simulation systems into an integrity one. The integrity simulation system performed well in test.

Object auto-recognition for underwater targets

The affine invariants is constructed based on region moments in order to eliminate the negative effects, which are brought by the underwater images under the influence of the lighting condition and some character of water media. Aiming at the draw backs of traditional BP neural network, such as converging slowly and tending to get into the local minimize, a new method of designing BP neural net works based on immune genetic algorithm (IGA) is proposed. The mechanisms of diversity maintaining and antibody density regulation exhibited in a biological immune system are introduced into IGA based on genetic algorithm (GA). The proposed algorithm overcome the problems of GA on search efficiency, individual diversity and premature, and enhanced the convergent performance effectively. The affine invariant features of four different objects are extracted and selected as the input of the trained neural network. The feasibility and advantages of this method are demonstrated by the experimental results.

A FNN control of underwater vehicles based on ant colony algorithm

For the particular controlled object AUV, a novel controller based on the fuzzy B-Spline neural network is presented, which embodies the merits of qualitative knowledge representation capability of fuzzy logic, quantitative learning ability of neural networks, as well as the excellent local controlling ability of B-Spline basis functions. However, to overcome the inherent deficiencies in the fuzzy neural network, including the structure hardly to be fixed, slow-speed training with the tendency to be involved in local convergence, and the quality of training results dependent upon the initial conditions of the network as well, some optimizing efforts are carried out in this investigation. The improved dual ant algorithm is employed for offline optimization, which can efficiently avoid the phenomenon of precocity and stagnation during the evolution. Meanwhile, the expert experience is introduced to simplify the number of optimizing parameters, and then the controller is further improved with the hybrid training by adopting the BP algorithm proceeding online adjustment. The simulation of the AUV motion control demonstrates the feasibility and validity of the present method.

Improved PSO-based S Plane Controller for motion control of underwater vehicle

Based on the analysis of fuzzy control, combined with the form of PID control, the S plane control has been applied. For the default that particle swarm optimization (PSO) presents the phenomenon of precocity and getting in local minima, the basic PSO algorithm is improved. The basic PSO algorithm is divided into two optimizing phase: coarse adjustment phase and fine adjustment phase. This method could improve the coordination between global and local searching ability and apt to search out global optimum quickly. The concept of chasten factor is also introduced, the optimizing ability in PSO algorithm which applied in the S plane algorithm in parameter optimization. Finally, the improved PSO algorithm is applied to the S plane motion control of underwater vehicle. The feasibility and advantages of this method are demonstrated by simulation test results.