No abstract

A method for detecting and classifying faults in an aluminum cantilever beam is proposed in this paper. The method uses features based on second-, third-and fourthorder statistics, which are extracted from the vibration signals generated by the cantilever beam. Fisher's discriminant ratio (FDR) is used for feature selection, and an artificial neural network is used for fault detection and classification. Three different degrees of faults (low, medium and high) were applied to the cantilever beam, and the proposed pattern recognition system was able to classify the faults, reaching performances ranging from 88 to 100 %. Moreover, the use of higher-order statistics-based features combined with FDR led to a compact feature space and provided satisfactory results.

In this paper, it is proposed a method to detect structural faults or damages using Higher-Order Statistics (HOS). For this, vibration signals were taken from cantilever beams. Such vibrations were generated by a DC motor with varying rotation, generating vibrations at various frequencies. Vibration signals and engine speed control were performed by an Arduino board. After the signal acquisition, parameters are extracted by means of second-, third- and fourthorder cumulants and then the most relevant ones were selected by the Fisher’s Discriminant Ratio (FDR). To fault detection, a Support Vector Machine (SVM) classifier has been designed in its One-Class version, where only oneclass knowledge is required. The results showed a good ability to represent vibration signals via HOS along with a large reduction in dimensionality given using FDR and a good generalization by means of the SVM classifier. Failure detection results showed 100% success rates.

In this article, it is proposed a method for detection of structural faults or damages using Higher-Order Statistics (HOS). Taking vibration signals measured using an accelerometer, characteristics are extracted by cumulants and selected with the Fischer's Discriminant. Subsequently, the classification is carried out with the aid of Supporting Vector Machines, aiming to determine the presence or not of faults in the structure. The method was experimentally tested in a cantilever beam, providing high detection rates. Advantages presented are low computational cost and no requirement of information about the damaged structure.