Ship equipment fault grade assessment model based on back propagation neural network and genetic algorithm

The factors that affect the ship equipment fault grade assessment are analyzed firstly, and then the fault grade assessment model is founded on the base of back propagation neural network. The genetic algorithm is used to quantify the value of the initial weight vector of neural network. Three methods that are gradient descent back propagation algorithm, momentum gradient descent back propagation algorithm and Levenberg-Marquard back propagation algorithm are used to train the neural network. Through lots of simulation calculation, the neural network simulation algorithm which is most adaptive to this special assessment problem and has the highest precision is found. Next, the methods through which can improve the assessment precision are given. In the end, the visualization forms of the neural network model which are compiled by Matlab and VB software is researched to improve the usability of the methods.