Genetic Algorithm Optimized BP-network Model and its Application in Fault Detection of Complicate Equipments

The BP nerve network has been used widely in fault detection field, but the usage of solution seeking algorithm by along gradient descent often results in low convergence speed and frequently getting into the part minimum. On the contrary, the genetic algorithm has the advantage of fast seeking speed in full-scale. Therefore, to optimize the BP nerve network, this essay adopts the auto-fit genetic algorithm. Later, the example of shipping main shafting fault detection proves that the optimized BP nerve network combined with the genetic algorithm is more adapted to complicate equipments´ fault detection.