Research Of Condition Monitoring For Propeller And Rudder Of Autonomous Underwater Vehicle

The research of the autonomous underwater vehicle is one of the most important parts of the naval national defence and ocean development stratagem. To guarantee the higher efficiency and reliability in the research, development, design and manufacture, and finish the motion control, mission and safely homing in the underwater experiments and actual combat, it is necessary to monitor the condition of some components in the AUV system.In this article, according to the analysis of the execution machine, motion model and sensor system in the AUV, a structure of condition monitoring system focused on the diagnosis module and based on the intelligent method is presented, which mainly constructs the models of the propellers and rudders respectively, and monitors the running condition of the AUV in cruising and hunting, and diagnoses whether there are some faults occurring in the parts that beingmonitored, and ensure the navigation security.In the constructing of the diagnosis module using the technology of the combination of the fuzzy logic and neural network, which based on the fuzzy adaptive learning control network, a simple kind of capable method for consummate the structure and performance of network is introduced, which includes the rules extraction based on the maximum weights matrix and the parameters amendment based on genetic algorithm by floating-point coding. During the monitoring of the parts condition, the output of the condition monitoring system shows the good working condition of the executing agency by fuzzily deducing from the control instruction send by the AUV's controller and motion status, and so offers the proof to complete mission and return safely. The result of the computer simulation shows that the method is feasible and the condition monitoring system is effective.