English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

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' . Introduction Large-sized flexible structure is widely used in industrial production areas, such as aircrafts, automobiles, ships and so on. The detection of dynamic deformation in working process, is particularly important [1][2]. Dynamic deformation will affect the normal use of the structure carrier, therefore it is necessary to detect and predict the dynamic deformation angle, and gasp the trend of deformation in a short time [3]. With the development of real-time deformation measurement technology theory, there is more and more study on inertial device matching measurement technology. The dynamic deformation angle of large-sized flexible structure can be estimated by matching inertial parameters [4][5]. But inertial device matching technology have certain hysteresis, which cannot forecast deformation trend [6]. Because large-sized flexible structure’s deformation has the dynamic random characteristics of short changing cycle and uncertain changing trend, the linear model fitting prediction method has lower accuracy and the deformation prediction method has limitation. Radial-Basis Function (RBF) neural network can ignore the specific physical parameters in the process and system, and has the advantages of strong generalization ability [7][8].Therefore RBF neural network is used in this paper to establish large-sized structure’s deformation trend time series model, and realize short-term deformation forecasting of large-sized structure. Deformation Mathematic Model of Large-Sized Structure The deformation angle of large-sized structure can be divided into two kinds qualitatively: static deformation angle and dynamic deformation angle. Static deformation angle is not absolute constant, but its changing cycle is usually longer. So generally some structural mechanics methods can be used to model and compensate static deformation angle. While dynamic deformation angle, generated due to large-sized structure’s external force and change, has shorter changing cycle. In this paper, just the dynamic deformation prediction method is studied. Dynamic deformation has the random characteristics of short changing cycle and uncertain changing trend. In the current theory, dynamic deformation is usually considered as two-step Markov 6th International Conference on Machinery, Materials, Environment, Biotechnology and Computer (MMEBC 2016) © 2016. The authors Published by Atlantis Press 1758 process energized by white noise. Assume that dynamic deformation angle is (t) i  ( , , i x y z  ), which is independent of other direction. Deformation rate is (t) (t)     . Then the dynamic deformation model can be expressed as:

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