Research of Deformation Prediction Method on Large-sized Structure Component Based on Time Series Analysis

摘要

Large-sized flexible structure is widely used in industrial production areas, such as aircrafts, automobiles, ships and so on. There will be dynamic deformation in working process which will affect the normal use of structure carrier. In addition, current deformation measurement methods have certain hysteresis, so the research on deformation prediction method must be carried out to forecast deformation trend. Firstly deformation mathematical model of large-sized structure based on mechanism is analyzed. Secondly the deformation trend time series model of large-sized structure is researched. Then the Radial-Basis Function (RBF) neural network is used to complete modeling and training process, to realize short-term deformation forecasting of large-sized structure. The simulation result show that the prediction error is limited within the range of 0.02'.