Data Mining Practical Machine Learning Tools and Techniques

From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article.

The Self-Organizing Map

[서평]「The Unified Modeling Language User Guide」

Artificial intelligence for fault diagnosis of rotating machinery: A review

The latest advances in electric and electronic aircraft technologies from the point of view of an "all-electric" aircraft are presented herein. Specifically, we describe the concept of a "more electric aircraft" (MEA), which involves removing the need for on-engine hydraulic power generation and bleed air off-takes, and the increasing use of power electronics in the starter/generation system of the main engine. Removal of the engine hydraulic pumps requires fully-operative electrical power actuators and mastery of the flight control architecture. The paper presents a general overview of the electrical power generation system and electric drives for the MEA, with special regard to the flight controls. Some discussion regarding the interconnection of nodes and safety of buses and protocols in distributed systems is also presented

/pdf/moving-towards-a-more-electric-aircraft-yt1pxk9bb6.pdf

Moving towards a more electric aircraft

Motor-current-signature analysis has been successfully used in induction machines for fault diagnosis. The method, however, does not always achieve good results when the speed or the load torque is not constant, because this causes variations on the motor-slip and fast Fourier transform problems appear due to a nonstationary signal. This paper proposes a new method for motor fault detection, which analyzes the spectrogram based on a short-time Fourier transform and a further combination of wavelet and power-spectral-density (PSD) techniques, which consume a smaller amount of processing power. The proposed algorithms have been applied to detect broken rotor bars as well as shorted turns. Besides, a merit factor based on PSD is introduced as a novel approach for condition monitoring, and a further implementation of the algorithm is proposed. Theoretical development and experimental results are provided to support the research.

Fault Detection in Induction Machines Using Power Spectral Density in Wavelet Decomposition

Bearing degradation is the most common source of faults in electrical machines. In this context, this work presents a novel monitoring scheme applied to diagnose bearing faults. Apart from detecting local defects, i.e., single-point ball and raceway faults, it takes also into account the detection of distributed defects, such as roughness. The development of diagnosis methodologies considering both kinds of bearing faults is, nowadays, subject of concern in fault diagnosis of electrical machines. First, the method analyzes the most significant statistical-time features calculated from vibration signal. Then, it uses a variant of the curvilinear component analysis, a nonlinear manifold learning technique, for compression and visualization of the feature behavior. It allows interpreting the underlying physical phenomenon. This technique has demonstrated to be a very powerful and promising tool in the diagnosis area. Finally, a hierarchical neural network structure is used to perform the classification stage. The effectiveness of this condition-monitoring scheme has been verified by experimental results obtained from different operating conditions.

Bearing Fault Detection by a Novel Condition-Monitoring Scheme Based on Statistical-Time Features and Neural Networks

This paper presents a novel method to diagnose demagnetization in permanent-magnet synchronous motor (PMSM). Simulations have been performed by 2-D finite-element analysis in order to determine the current spectrum and the magnetic flux distribution due to this failure. The diagnostic just based on motor current signature analysis can be confused by eccentricity failure because the harmonic content is the same. Moreover, it can only be applied under stationary conditions. In order to overcome these drawbacks, a novel method is used based upon the Hilbert-Huang transform. It represents time-dependent series in a 2-D time-frequency domain by extracting instantaneous frequency components through an empirical-mode decomposition process. This tool is applied by running the motor under nonstationary conditions of velocity. The experimental results show the reliability and feasibility of the methodology in order to diagnose the demagnetization of a PMSM.

/pdf/fault-detection-by-means-of-hilbert-huang-transform-of-the-3aqwvgpcxw.pdf

Fault Detection by Means of Hilbert–Huang Transform of the Stator Current in a PMSM With Demagnetization

This paper presents and analyzes a method for short-circuit fault detection in a permanent-magnet synchronous motor (PMSM). The study includes steady-state condition and speed transients in motor operation. The stator current is decomposed by empirical mode decomposition (EMD), which generates a set of intrinsic mode functions (IMFs). Quadratic time-frequency (TF) distributions such as smoothed pseudo-Wigner-Ville and Zhao-Atlas-Marks are applied on the more significant IMFs for fault detection. Simulations and experimental laboratory tests validate the algorithms and demonstrate that this kind of TF analysis can be applied to detect and identify short-circuit failures in PMSM.

Juan Antonio Ortega

Papers

Moving towards a more electric aircraft

Fault Detection in Induction Machines Using Power Spectral Density in Wavelet Decomposition

Bearing Fault Detection by a Novel Condition-Monitoring Scheme Based on Statistical-Time Features and Neural Networks

Fault Detection by Means of Hilbert–Huang Transform of the Stator Current in a PMSM With Demagnetization

Short-Circuit Detection by Means of Empirical Mode Decomposition and Wigner–Ville Distribution for PMSM Running Under Dynamic Condition