Fault Diagnosis Model Based on Feature Compression with Orthogonal Locality Preserving Projection

Based on feature compression with orthogonal locality preserving projection（OLPP）,a novel fault diagnosis model is proposed in this paper to achieve automation and high-precision of fault diagnosis of rotating machinery.With this model,the original vibration signals of training and test samples are first decomposed through the empirical mode decomposition（EMD）,and Shannon entropy is constructed to achieve high-dimensional eigenvectors.In order to replace the traditional feature extraction way which does the selection manually,OLPP is introduced to automatically compress the high-dimensional eigenvectors of training and test samples into the low-dimensional eigenvectors which have better discrimination.After that,the low-dimensional eigenvectors of training samples are input into Morlet wavelet support vector machine（MWSVM） and a trained MWSVM is obtained.Finally,the low-dimensional eigenvectors of test samples are input into the trained MWSVM to carry out fault diagnosis.To evaluate our proposed model,the experiment of fault diagnosis of deep groove ball bearings is made,and the experiment results indicate that the recognition accuracy rate of the proposed diagnosis model for outer race crack、inner race crack and ball crack is more than 90%.Compared to the existing approaches,the proposed diagnosis model combines the strengths of EMD in fault feature extraction,OLPP in feature compression and MWSVM in pattern recognition,and realizes the automation and high-precision of fault diagnosis.

Mathematical treatment of wave propagation in acoustic waveguides with n curved interfaces

There are some curved interfaces in ocean acoustic waveguides. To compute wave propagation along the range with some marching methods, a flattening of the internal interfaces and a transforming equation are needed. In this paper a local orthogonal coordinate transform and an equation transformation are constructed to flatten interfaces and change the Helmholtz equation as a solvable form. For a waveguide with a flat top, a fiat bottom and n curved interfaces, the coefficients of the transformed Helmholtz equation are given in a closed formulation which can be thought of as an extension of the formal work related to the equation transformation with two curved internal interfaces. In the transformed horizontally stratified waveguide, the one-way reformulation based on the Dirichlet-to-Neumann （DtN） map is then used to reduce the boundary value problem to an initial value problem. Numerical implementation of the resulting operator Riccati equation uses a large range step method to discretize the range variable and a truncated local eigenfunction expansion to approximate the operators. This method is particularly useful for solving long range wave propagation problems in slowly varying waveguides. Furthermore, the method can also be applied to wave propagation problems in acoustic waveguides associated with varied density.

Energy Efficient Access Point Selection and Signal Projection for Accurate Indoor Positioning

We propose a method to improve positioning accuracy while reducing energy consumption in an indoor Wireless Local Area Network(WLAN) environment.First,we intelligently and jointly select the subset of Access Points(APs) used in positioning via Maximum Mutual Information(MMI) criterion.Second,we propose Orthogonal Locality Preserving Projection(OLPP) to reduce the redundancy among selected APs.OLPP effectively extracts the intrinsic location features in situations where previous linear signal projection techniques failed to do,while maintaining computational efficiency.Third,we show that the combination of AP selection and OLPP simultaneously exploits their complementary advantages while avoiding the drawbacks.Experimental results indicate that,compared with the widely used weighted K-nearest neighbor and maximum likelihood estimation method,the proposed method leads to 21.8%(0.49 m) positioning accuracy improvement,while decreasing the computation cost by 65.4%.

Preconditioned method in parallel computation

The grid equations in decomposed domain by parallel computation are soled, and a method of local orthogonalization to solve the large-scaled numerical computation is presented. It constructs preconditioned iteration matrix by the combination of predigesting LU decomposition and local orthogonalization, and the convergence of solution is proved. Indicated from the example, this algorithm can increase the rate of computation efficiently and it is quite stable.

Orthogonal Discriminant Improved Local Tangent Space Alignment Based Feature Fusion for Face Recognition

Improved local tangent space alignment (ILTSA) is a recent nonlinear dimensionality reduction method which can efficiently recover the geometrical structure of sparse or non-uniformly distributed data manifold. In this paper, based on combination of modified maximum margin criterion and ILTSA, a novel feature extraction method named orthogonal discriminant improved local tangent space alignment (ODILTSA) is proposed. ODILTSA can preserve local geometry structure and maximize the margin between different classes simultaneously. Based on ODILTSA, a novel face recognition method which combines augmented complex wavelet features and original image features is developed. Experimental results on Yale, AR and PIE face databases demonstrate the effectiveness of ODILTSA and the feature fusion method.

A numerical local orthogonal transform method forstratified waveguides

Flattening of the interfaces is necessary in computing wave propagation along strati?ed waveguides in large range step sizes while using marching methods. When the supposition that there exists one horizontal straight line in two adjacent interfaces does not hold, the previously suggested local orthogonal transform method with an analytical formulation is not feasible. This paper presents a numerical coordinate transform and an equation transform to perform the transforms numerically for waveguides without satisfying the supposition. The boundary value problem is then reduced to an initial value problem by one-way reformulation based on the Dirichlet-to-Neumann (DtN) map. This method is applicable in solving long-range wave propagation problems in slowly varying waveguides with a multilayered medium structure.

The Isomorphisms of Orthogonal Groups over Local Rings

1. Introduction Since O’Meara worked out the automorphisms of orthogonal groups Ωn(V) over fields in [4] by using well-known residual space method, many results about the isomorphisms and automorphisms of orthogonal groups over integral domains have been achieved. Refer to O’Meara, Hahn for example. B. R. McDonald, in [12], determined the automorphisms of O(V) over local rings with 2 a unit by using involutions.

Research on Damage Localization of Plate-like Structure Using Mode Acoustic Emission and Matching Pursuit

Based on mode acoustic emission theory,the paper analyses the acoustic emission analog signal of thin steel plate using matching pursuit,then obtains the characteristics interpretation of the different frequency signal energy concentration degree; Combined with four-point arc positioning method,the papers researches the damage localization of the plate-like structure. Simulation experiment shows that this method can accurately detect and locate the damage. This can provide data support for further imaging research based on time reverse theory.