Fuzzy Modeling of Diesel Engine using Modified Self-Organizing Map Network
Jian. Zhang, Jingli Kang, Minnan Wang · Systems Analysis Modelling Simulation · 2003
This article deals with a problem of nonlinear identification of big power diesel engine 12V180ZJ equipped on locomotive. A new nonlinear fuzzy model is proposed. The model is identified as black-box model with input-output training data. A modified self-organizing map (MSOM) network is developed for generating parameters of fuzzy model. Based on the MSOM, fuzzy rules are determined automatically according to the distribution of training data in the input-output space and the given approximating error. Simulating result idicates that the nonlinear model depicts the statics and dynamics of diesel engine accurately. This nonlinear model can be used to design the control system of diesel engine, and understand its complex dynamics.