Li Fengping

NC Machine Tools Fault Diagnosis Based on Kernel PCA and -Nearest Neighbor Using Vibration Signals

This paper focuses on the fault diagnosis for NC machine tools and puts forward a fault diagnosis method based on kernel principal component analysis (KPCA) and -nearest neighbor (NN). A data-dependent KPCA based on covariance matrix of sample data is designed to overcome the subjectivity in parameter selection of kernel function and is used to transform original high-dimensional data into low-dimensional manifold feature space with the intrinsic dimensionality. The NN method is modified to adapt the fault diagnosis of tools that can determine thresholds of multifault classes and is applied to detect potential faults. An experimental analysis in NC milling machine tools is developed; the testing result shows that the proposed method is outperforming compared to the other two methods in tool fault diagnosis.

An online damage identification approach for numerical control machine tools based on data fusion using vibration signals

In this paper, a new approach is proposed based on data fusing with vibration signals using time-frequency parameters, probabilistic principal component analysis (PPCA) and statistical inference, for improving the accuracy and visibility of damage identification for numerical control (NC) machine tools. Time-frequency feature principal components are put forward, which extracted from eight dimensionless parameters statistically in the time and frequency domains by PPCA. The Chi-2 statistic is established according to statistical inference principle, and the feature figure of principal components is built that can acquire damage distribution of tools by measured data. An empirical analysis in NC milling machine tools is developed, and the result shows high accuracy and visibility of the proposed approach.

Laser interaction with materials and its applications in precision engineering

In this paper, laser interaction with materials and its applications in precision engineering are mainly introduced. To further explore the physics behind laser interaction with materials, it is of much significance to investigate the mechanisms in the process. First of all, it is desired to understand the characteristics and principle of laser. Laser is generated by stimulated radiation, and has excellent physical properties, such as high monochromaticity, high brightness, high directivity and high coherence. Meanwhile, it benefits much to study the dynamic process of interactions and its mechanisms. There exist both photo-chemical and photo-thermal processes when laser and materials interact. Furthermore, developing laser application in nanomaterial synthesis is also an unique area. It is worth further studying the design and fabrication of nanostructured materials. Last but not least, it is interesting to explore the specific process and characteristics of laser processing, which play an important role in advanced manufacturing. In precision engineering, the tool of laser has also been more applicable considering its great advantages in microprocessing and nanofabrication. Several case studies are introduced, which have great potential and high impact applications, such as ultrafast laser direct writing, laser micro-lens lithography, laser nanofabrication to break through optical diffraction limit and hybrid micro/nanostructures with unique functions fabricated by laser. These studies have triggered intensive research interests due to their great application prospect.

3D micro-concrete hybrid structures fabricated by femtosecond laser two-photon polymerization for biomedical and photonic applications

How to fabricate micro-scale 3D structures with an efficient method is the key issue to achieve many long-pursuit exciting goals, such as direct 3D printing to make human organs and fabrication of integrated photonic circuits. Two-photon polymerization (2PP) is more competitive than other 3D printing methods because it is the unique approach capable to acquire around 100 nm resolution to fabricate tiny structures, which are fundamental components in these applications. However, the photoresist used in this method lacks the key material properties to fulfill the requirements of such applications, including mechanical strength and light trapping efficiency. In this work, we present two hybrid methods to modify the photoresist into micro-concretes. With such modifications, the key material properties are enhanced, which transfers it into the feasible building blocks to achieve unique functionalities. These improved hybrid micro-concretes offer tunable mechanical strength, light trapping efficiency and flexible design for bio-medical devices and micro-photonic sources, which represent a new paradigm to nano-engineer the mechanical and optical properties for various applications.

Parameter Optimization for Nadaraya-Watson Kernel Regression Method with Small Samples

Many current regression algorithms have unsatisfactory prediction accuracy with small samples. To solve this problem, a regression algorithm based on Nadaraya-Watson kernel regression (NWKR) is proposed. The proposed method advocates parameter selection directly from the standard deviation of training data, optimized with leave-one-out cross- validation (LOO-CV). Good generalization performance of the proposed parameter selection is demonstrated empirically using small sample regression problems with Gaussian noise. The results show that proposed parameter optimization method is more robust and accurate than other methods for different noise levels and different sample sizes, and indicate the importance of Vapnik’s e-insensitive loss for regression problems with small samples.

Research on E-Government System Evaluation Based on Hierarchical Grey Analysis

Evaluation of e-government is the basis for improving e-government performance. An evaluation indexes system is established from interior and exterior dimensionality based on service and application. And the evaluation arithmetic is built by analytic hierarchy process (AHP) method and grey evaluation method. AHP was used to calculate the weight of indicators, grey evaluation method is used to evaluate the synthetically evaluation. Taking one e-government system as an example, the experimental results indicate that the hierarchy grey evaluation method is effective.