Ship Generator Excitation System Of Artificial Neural Network Control

At present, with the increasing tonnage of ship and more and more ships propelled by electric power, the capacity of a generator in a marine power station is getting larger and larger. Because of electric propulsion technology applied by modern marines, the control system of voltage stability in vessel must be with better performance. The electric energy produced by diesel generators is not only transported to each load but also sent to vessel propulsion device in vessel with electric propulsion. The voltage of a vessel power system must be kept in reasonable range, otherwise it would affect the electrical system of a vessel greatly. The performance of excitation control of generators is the key to the voltage stability of power system in vessel electrical network.Large-scale vessel electrical network is the system which is high order, strong coupling and nonlinear. After using electric electron and transducer to regulate the rotate speed of generators, the electrical network system becomes more complicated because there are network harmonic wave, electromagnetism disturbance and so on. After rectified, the traditional PID controller is unchangeable in the whole control process. But in the practical system, when the state of system and parameters are changed, the uncertainty of the process and parameters will appear. So in modern industry control process, the traditional PID controller has not good effect. However, because of the ability of dealing with nonlinear system and fault tolerance, the artificial neural network will be a new method to deal with the uncertainty nonlinear system and control problems. On the basis of distributing memory and concurrent processing, it has the function of self-organization, self-learning and association anamnesis of information. In many aspects, ANN is similar to human in the process of handling with information. It has the ability of simulating visual thinking of human and it expresses some basic character of brain of human. But ANN is not the real description of human brain but a simulation, abstract and pre-digestion. ANN has been applied in practice.Now with the appearance of nerve cell chips and DSP used widely, ANN is used in real time control. Take the excitation control system as an object, thephase compound excitation system is firstly studied and controlled. Then two methods are designed by BP and CMAC to control the excitation system. Last, three control effects BP, CMAC, PID are compared. ANN control strategy can make the voltage of generators stable in the course of load changed, load uninstalled, electrical network fault and generator fault and so on. This project is supported by fund of science and technology development of Shanghai municipal education committee (03IK06).