Search

This paper presents a hybrid method named genetic neural networks(GNN) which combines genetic algorithm(GA) with neural networks(NN). Fault diagnostic results of aero-engine vibration based on GNN are obtained by setting typical vibration fault modes, including rotor imbalance, rotor disalignment and looseness of rotors. It is shown that this method is superior to the traditional neural network in improving the accuracy and rapidity of vibration fault diagnosis.

Timing-sync Protocol for Sensor Networks (TPSN) is a widely used protocol which provides network-wide time synchronization in a sensor network. We use formal methods to study it thoroughly in this poster. First of all, we model the protocol with timed automata which can describe the workflow of TPSN in an ideal environment. However, in realistic circumstances, there are many uncertainties, for example, message loss and node dynamics. Thus, we extend our model with probabilities to describe these uncertainties. Besides verifying the system against several critical functional properties, we also show that it is also possible to evaluate the performance of TPSN by statistical model checking to estimate how it works in realistic environments.

Wavelet analysis is a popular subject in science research. In this work, the concept of biorthogonal two- direct- -ion finitely supported wavelet packs with four-scale is introduced. A new method for designing two-directional biorthogonal wavelet packs is developed and their properties is investi- -gated by means of time-frequency analysis method, matrix theory and operator theory. The decomposition relationship is established. Finally, two Riesz bases of space L2(R2) are drawn from these wavelet packs. The biorthogonal finitely supported uni-wavelet packs was generalized to two-directional biorthogonal wavelet packs.

For the purpose of color image segmentation, an unsupervised peak value searching algorithm was proposed, which was used to determine the approximate dominant color components of image. First, the local peaks of 3D color histogram within the neighborhood of 3×3 ×3 were located. The corresponding color values of local peaks were regarded as initial clustering centers, and the number of local peaks were taken as the number of clustering. In addition, taking into account of the color difference induced by local illumination, the feature vector was constructed including color and texture features. Finally, K-means clustering algorithm was applied to segment the color image. Experiment results show that the proposed method can segment the color image accurately, corresponding with the human visual. Clustering number was determined adaptively, and the problem of over-segmentation was solved effectively. The segmentation result was benefit for the following steps in the computer vision.

This paper experimentally investigates the vibration faults of rotor, such as the unbalance, the loosening and the friction, using the rotor test rig. According to the theory of fractal and chaos, the vibration signal series are reconstructed. By the calculation of correlation dimension and Kolmogorov entropy, the dynamic characteristics of the system are then reproduced. The results show that the correlation dimension and Kolmogorov entropy of friction fault are the largest, that of the loosening fault are little lower, and that of the unbalance fault are the smallest. Different faults have different range of correlation dimension and Kolmogorov entropy, and they can be used to identify the fault symptoms.

Although aeroengine vibration is mainly due to unbalance of rotating components, assembly methods and assembly parameters fluctuations also play an important role in engine vibration research. Method of principal component analysis (PCA) is put forward in this paper to study the relations between assembly parameters and engine vibration for the first time. The principle of PCA and its application in fault analysis of aeroengine vibration are presented in detail in the following content and the program of PCA is developed using platform Visual C++. Finally, the most critical assembly parameters that take the worst effect on engine vibration, including surface joint degree, bearing clearance, wear loss of bearing casing and face run-out, are achieved after calculations utilizing the program.