Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Anomaly detection is an important problem that has been researched within diverse research areas and application domains. Many anomaly detection techniques have been specifically developed for certain application domains, while others are more generic. This survey tries to provide a structured and comprehensive overview of the research on anomaly detection. We have grouped existing techniques into different categories based on the underlying approach adopted by each technique. For each category we have identified key assumptions, which are used by the techniques to differentiate between normal and anomalous behavior. When applying a given technique to a particular domain, these assumptions can be used as guidelines to assess the effectiveness of the technique in that domain. For each category, we provide a basic anomaly detection technique, and then show how the different existing techniques in that category are variants of the basic technique. This template provides an easier and more succinct understanding of the techniques belonging to each category. Further, for each category, we identify the advantages and disadvantages of the techniques in that category. We also provide a discussion on the computational complexity of the techniques since it is an important issue in real application domains. We hope that this survey will provide a better understanding of the different directions in which research has been done on this topic, and how techniques developed in one area can be applied in domains for which they were not intended to begin with.

/pdf/anomaly-detection-a-survey-1x33g9m0a3.pdf

Anomaly detection: A survey

物件導向軟體之架構(Object-Oriented Software Construction)探討

A review on machinery diagnostics and prognostics implementing condition-based maintenance

This report contains a review of the technical literature concerning the detection, location, and characterization of structural damage via techniques that examine changes in measured structural vibration response. The report first categorizes the methods according to required measured data and analysis technique. The analysis categories include changes in modal frequencies, changes in measured mode shapes (and their derivatives), and changes in measured flexibility coefficients. Methods that use property (stiffness, mass, damping) matrix updating, detection of nonlinear response, and damage detection via neural networks are also summarized. The applications of the various methods to different types of engineering problems are categorized by type of structure and are summarized. The types of structures include beams, trusses, plates, shells, bridges, offshore platforms, other large civil structures, aerospace structures, and composite structures. The report describes the development of the damage-identification methods and applications and summarizes the current state-of-the-art of the technology. The critical issues for future research in the area of damage identification are also discussed.

/pdf/damage-identification-and-health-monitoring-of-structural-3s8adkph2w.pdf

Damage identification and health monitoring of structural and mechanical systems from changes in their vibration characteristics: A literature review

Funding for this project is provided by the Department of Energy through the internal funding programs at Los
Alamos National Laboratory known as Technology Maturation Fund and Laboratory Directed Research and
Development Fund. The authors acknowledge our industrial partner for providing experimental data from roller
coaster rides in Orlando, Florida.

Online Damage Detection for Theme Park Rides

Harsh environmental and operating conditions often leave pipeline systems prone to cracks, corrosion, and other aging defects. If left undetected, these forms of damage can lead to the failure of the pipeline system, which may have catastrophic consequences. Most current forms of health monitoring for pipeline systems involve nondestructive evaluation (NDE) techniques. These techniques often require a pipeline system to be taken out of operation at regularly scheduled intervals so that a technician can perform a prescribed NDE measurement. Such a measurement also requires direct access to the pipe's exterior or interior surface. This access may require excavation if the pipe is underground and the removal of insulating layers when present. This research proposes the use of Macro-fiber composite (MFC) actuators for damage detection in pipeline structures. Because MFC actuators are durable and relatively inexpensive, they can be permanently bonded to the surface of a pipe during installation. Therefore, measurements for damage detection can be performed at any time, even while the system is still in operation. The time reversal methods use the propagation of Lamb waves to evaluate the structural health of a pipeline system. A burst waveform is used to excite Lamb waves in a pipe at an initial location using an array of MFC patches. The measured response at the actuation location is reversed in time and used as the excitation signal at the second location. The initial excitation signal is then compared to the final response signal. The performance of the time reversal methods was compared to the traditional methods of Lamb wave propagations using standard tone burst waveforms.

The use of time reversal methods with Lamb waves to identify structural damage in a pipeline system

Structural Health Monitoring and Damage Identification

The accomplishments of the Seismic Category I Structures Program for FY 1986 are reported The background leading to the FY 1986 Program Plan is summarized and the design of a new geometric configuration of a reinforced concrete shear wall test structure is described The report discusses static and seismic testing of two of these structures, a 1/4-scale, 1-in-thick shear wall model of microconcrete and a 4-in-thick shear wall prototype Results and conclusions regarding degrading stiffness characteristics, natural frequencies, and scalability of microconcrete with actual concrete are compared with past fiscal year results Possible base rotation effects for the large structure are examined analytically Finally, tentative conclusions are stated regarding the degrading stiffness and scaling of these structures and recommendations are made about future seismic testing of large structures 11 refs, 28 figs, 9 tabs

/pdf/the-seismic-category-1-structures-program-results-for-fy-13tukmtuim.pdf

The Seismic Category 1 Structures Program: Results for FY 1985

A family of mem-models, including the mem-dashpots, mem-springs, and most recently, mem-inerters, is emerging as a new and powerful way of capturing complex nonlinear behaviors of materials and systems under various types of dynamic loads involving different frequency, amplitude, and loading histories (e.g., hysteresis). Under the framework of nonlinear state-space representation and hybrid dynamical systems, mem-springs may be formulated to effectively represent an inherent degradation of material state. It is shown in this study, for the first time, how the absement (time integral of strain/displacement), a signature state variable for a mem-spring, can be connected with the damage variable, a key quantity in continuum damage mechanics. The generalized momentum (time integral of stress), on the other hand, is shown to be efficient in modeling strain ratcheting via the concept of mem-dashpot. It is also shown in this study, for the first time, how two formulations of the memcapacitive system models (for mem-springs) are special cases of the Preisach model.

/pdf/connecting-mem-models-with-classical-theories-35ic4tlvvk.pdf

Charles R. Farrar

Papers

Online Damage Detection for Theme Park Rides

The use of time reversal methods with Lamb waves to identify structural damage in a pipeline system

Structural Health Monitoring and Damage Identification

The Seismic Category 1 Structures Program: Results for FY 1985

Connecting mem-models with classical theories