Structural Damage Detection Using Supervised Nonlinear Support Vector Machine

Damage detection, using vibrational properties, such as eigenfrequencies, is an efficient and straightforward method for detecting damage in structures, components, and machines. The method, however, is very inefficient when the values of the natural frequencies of damaged and undamaged specimens exhibit slight differences. This is particularly the case with lightweight structures, such as fiber-reinforced composites. The nonlinear support vector machine (SVM) provides enhanced results under such conditions by transforming the original features into a new space or applying a kernel trick. In this work, the natural frequencies of damaged and undamaged components are used for classification, employing the nonlinear SVM. The proposed methodology assumes that the frequencies are identified sequentially from an experimental modal analysis; for the study propose, however, the training data are generated from the FEM simulations for damaged and undamaged samples. It is shown that nonlinear SVM using kernel function yields in a clear classification boundary between damaged and undamaged specimens, even for minor variations in natural frequencies.

Automatic Detection of Voltage Notches using Support Vector Machine

This paper presents a comprehensive framework for voltage notch analysis and an automatic method for notch detection using a nonlinear support vector machine (SVM) classifier. A comprehensive simulation of the notch disturbance has been conducted to generate a diverse database. Based on domain knowledge and properties of power quality disturbances (PQDs), a set of characteristic features is extracted. After feature extraction, a set of most descriptive features has been selected with decision tree (DT) algorithm, and a nonlinear SVM classifier has been trained. Finally, the detection efficiency of the trained model is presented and discussed.

Vertical-Downward Two-Phase Flow Regime Identification by Probabilistic Neural Network (PNN) and Nonlinear Support Vector Machine (SVM)

The present study proposes a new feature extraction method based on non-stationary conductivity probe signals. Two types of discriminative network models, i.e., the probabilistic neural network (PNN) and nonlinear support vector machine (SVM), are established for flow regime identification using small sample sets. The eigenvectors are composed of 16 feature quantities obtained by wavelet packet decomposition (WPD) and 8 feature quantities in the time-domain derived from the reconstructed low-frequency signals. The 8 features include maximum, minimum, standard deviation, arithmetic mean, kurtosis, peak factor, impulse factor and margin factor. The signals are normalized based on features rather than samples before flow regime identification. In the current study, WPD results show that the conductivity probe signals in two-phase flow are mostly in low frequency. The identification accuracy of the nonlinear SVM is 90.47%, which is better than 83.33% by the PNN method. This study verifies the superiority of nonlinear SVM in solving small samples and nonlinear flow regime classification problems. However, the accuracy of flow regime identification near flow regime transitional boundaries still remains questionable and needs further improvement.

Nonlinear vibration response of a complex aeroengine under the rubbing fault

Rolling bearing and squeeze film damper will introduce structural nonlinearity into the dynamic model of aeroengine. Rubbing will occur due to the clearance reduction design of the engine. The coupling of structural nonlinearity and fault nonlinearity will make the engine present rich vibration responses. This paper aims to analyze the nonlinear vibration behavior of the whole aeroengine including rolling bearing and squeeze film damper under rubbing fault. Firstly, the dynamic model of a turboshaft engine with nonlinear support and rubbing fault is established; The rolling bearing force, the oil film force and the rubbing force are introduced into a dual-rotor-casing model with six support points. Secondly, the linear part of the model is verified by the dynamic characteristics of the three-dimensional finite element model. Finally, the varying compliance vibration, the damping effect and the bifurcation mechanism are analyzed in detail in which the bearing clearance, speed ratio and rubbing stiffness are considered. Results show that the rubbing fault in the nonlinear support case will excite more significant varying compliance vibration in the low-speed region and expand the rotating speed range of the chaotic region in the high-speed region compared with that in the linear support case.

A Validated Train-Track-Bridge Model with Nonlinear Support Conditions at Bridge Approaches

A bridge approach, an essential component connecting a relatively rigid bridge and a more flexible track on subgrade soil, is one of the most common types of track transition zones. The tracks on a bridge deck often undergo significantly lower deformations under loading compared to the approach tracks. Even though there have been numerous efforts to understand and remediate performance deficiencies emerging from the differences in stiffness between the bridge deck and the approach, issues such as differential settlement and unsupported hanging crossties often exist. It is often difficult and expensive to try different combinations of mitigation methods in the field. Therefore, computational modeling becomes of vital importance to study dynamic responses of railroad bridge approaches. In this study, field instrumentation data were collected from the track substructure of US Amtrak’s Northeast Corridor railroad track bridge approaches. After analyses and model implementation of such comprehensive field data, an advanced train-track-bridge model is introduced and validated in this paper. Nonlinear relative displacements under varying contact forces observed between crosstie and ballast are adequately considered in the dynamic track model. The validated model is then used to simulate an Amtrak passenger train entering an open deck bridge to generate typical track transient responses and better understand dynamic behavior trends in bridge approaches. The simulated results show that near bridge location experiences much larger transient deformations, impact forces, vibration velocities and vibration accelerations. The validated track model is an analysis tool to evaluate transient responses at bridge approaches with nonlinear support; it is intended to eventually aid in developing improved track design and maintenance practices.

A Nonlinear Support Vector Machine Analysis Using Kernel Functions for Nature and Medicine

After the emergence of Artificial Intelligence (AI), great developments have taken place in the fields of science, economics, medicine and all other fields that use computer science. Along with the resulting developments in these fields, artificial intelligence has also solved many intractable problems, such as predicting specific serious diseases, determining future product sales, as well as analyzing and studying big data in the shortest possible time … SVM is one of the most important technologies in this field of artificial intelligence that goes into supervised methods, and which every machine learning expert should have in his/her arena. For this reason, in this article, we studied this technique and determined its advantages and disadvantages as well as its fields of application. Next, we applied this technique to three different databases, using four basis change functions, and we compared the results obtained to determine the best way to use the basis change functions.