Investigation on the State Prediction of the On-board Electromechanical BIT Based on the LM Neural Network

The method and performance for the state prediction based on the LM neural network was investigated. The way applied to the state prediction of on-board electromechanical BIT was provided. The slide oil pressure affects and reflects the run state of engine, which is adopted as the typical test data to validate the availability of LM neural network. Result shows that the state prediction and integrative analysis with the dynamic and history information can conquer such shortcomings as the low diagnose ability and high false alarm rate etc in the traditional BIT. The prediction precision is high and convergence rate is quick.