Establishing a prediction model is a key step for the implementation of prognostic and health management. The prediction model can be used to forecast the change trend of the characteristics of the vibration signal and analyze the potential failure in the future. Taking the vibration of power plant steam turbine as an example, the full vector fusion and fault prediction were studied. Due to the fact that the evaluation of the machine fault with only one transducer may result in a fault judgement with partiality, an information fusion method based on the theory of full vector spectrum was adopted to extract the vibration feature. An autoregressive prediction model was established. The collected vibration signals with pairing channels were fused. The time sequence of the fused vectors and spectrums were used to build the prediction model. The amplitude of main vector of rotating frequency and spectrum order structure were analyzed and predicted. The uncertainty of the spectrum structure can be eliminated by the information fusion. The reliability of the fault prediction was improved. The study on vibration prediction model system laid a technical foundation for the fault prognostic research.

The present status of speech emotion recognition was introduced in the paper. The emotional databases of Chinese speech and facial expressions were established with the noise stimulus and movies evoking subjects' emtion. For different emotional states, we analyzed the single-mode speech emotion recognitions based the prosodic features and the geometric features of facial expression. Then, we discussed the bimodal emotion recognition by the use of Gaussian Mixture Model. The experimental results show that, the bimodal emotion recognition rate combined with facial expression is about 6% higher than the single model recognition rate merely using prosodic features.

This paper presents a composite kernel Relevance Vector Machine(RVM) algorithm, for enhanced classification accuracy of hyperspectral images. This paper constructs three forms of composite kernels based on properties of kernels. The spatial feature is extracted using multi-scale morphological method from the image after principal components transform. The final classification is achieved by composite kernel RVM classifier. The proposed approach is tested in experiments on AVIRIS data. Compared with spectral kernel RVM, the OA and Kappa coefficient of composite kernel RVM increased obviously. However, the training time dose not increased. Meanwhile, composite kernel RVM has ability to get high accuracy with relative small training set. The proposed method has practical use in hyperspectral imagery classification.