Tensile Behaviour and Damage Evolution of a C/SiC Minicomposite Fabricated by Chemical Vapour Infiltration

The tensile behaviour of a C/SiC minicomposite fabricated by chemical vapour infiltration was examined and the associated damage evolution was monitored by using acoustic emission (AE) technique. The microstructure of minicomposite can be characterized by a uniformly thick SiC sheath, the thin fibre coatings, and large pores due to the tendency of fibres to cluster in the minicomposite. The load-displacement curves of minicomposite show a greatly nonlinear behaviour with four distinct regimes: initial self-alignment due to relaxation of fibres followed by preexisting microcrack extension, matrix macrocrack multiplication and then saturation. All these regimes can be well characterized by the corresponding AE activities. Therefore, it is believed that such experimental results would be beneficial to the optimization of processing conditions and derivation of parameters necessary for further modelling of the thermomechanical behaviours of real C/SiC composites with more complex architectures by fabricating minicomposites in a short time.

FEATURE SELECTION FOR CHINESE CHARACTER RECOGNITION BASED ON INDUCTIVE LEARNING

Feature selection is a difficult but important issue in the field of machine learning and pattern recognition. In this paper, features for Chinese character recognition are selected by using inductive learning algorithms. The existing inductive learning method based on extension matrix requires precise consistency between positive example and negative example sets, which is very difficult to maintain in most practical cases. The traditional decision tree algorithm ID3 considers only the performance of the discriminating power while selecting features. However, in actual practice the consideration of the associated cost of feature extraction may become a significant concern. In addressing these problems we propose a modified extension matrix approach to select feature subset from the training example set with noises. A decision tree algorithm based on information gain and cost evaluation is also proposed to facilitate cost consideration. The comparative experiments show that the proposed algorithms perform better than the existing inductive learning algorithms to a certain extent.