Classification of Acoustic Emissions Using Modified Matching Pursuit
- PDF / 2,299,266 Bytes
- 11 Pages / 600 x 792 pts Page_size
- 74 Downloads / 254 Views
Classification of Acoustic Emissions Using Modified Matching Pursuit Samuel P. Ebenezer Acoustic Technologies, Inc., 1620 Stapley Drive, Mesa, AZ 85204, USA Email: [email protected]
Antonia Papandreou-Suppappola Department of Electrical Engineering, Arizona State University, P.O. Box 877206, Tempe, AZ 85287-7206, USA Email: [email protected]
Seth B. Suppappola Acoustic Technologies, Inc., 1620 Stapley Drive, Mesa, AZ 85204, USA Email: [email protected] Received 31 May 2003; Revised 22 October 2003; Recommended for Publication by Kenneth Barner We propose methodologies to automatically classify time-varying warning signals from an acoustic monitoring system that indicate the potential catastrophic structural failures of reinforced concrete structures. Since missing even a single warning signal may prove costly, it is imperative to develop a classifier with high probability of correctly classifying the warning signals. Due to the time-varying nature of these signals, various time-frequency classifiers are considered. We propose a new time-frequency decomposition-based classifier using the modified matching pursuit algorithm for an actual acoustic monitoring system. We investigate the superior performance of the classifier and compare it with existing classifiers for various sets of acoustic emissions, including warning signals from real-world faulty structures. Furthermore, we study the performance of the new classifier under different test conditions. Keywords and phrases: classification, detection, acoustic emissions, time-frequency representations, matching pursuit decomposition.
1.
INTRODUCTION
1.1. Acoustic monitoring systems Acoustic monitoring systems are used in many applications to determine the integrity of structures such as buildings and bridges. The purpose of these monitoring systems is to listen for any warning signals that may indicate future catastrophic effects. This premonition of future events can provide invaluable time to prevent catastrophic failures that may follow. Figure 1 shows a typical monitoring system of structures along with a warning event [1, 2, 3, 4]. For example, in real life situations, the warning event could be the breaking sound of metals in steel bridges, the abnormal knocking sound in aircraft and automobile engines, or the breaking sound of metals in prestressed concrete structures with reinforcing metals. There are numerous reasons why it is desirable to ascertain the condition of a structure to determine if failure is imminent. The failure of a structure may result in the loss of its use which usually implies loss of revenue. In addition to
this, the replacement cost after the failure is generally much more than preventive maintenance costs. As a result of collateral expenses, the cost of structural failure may far exceed the cost of the structure itself. By monitoring for warning signals that indicate future failures, we can prevent the failure of the structure by repairing it before the failure occurs. The exact location of the distress c
Data Loading...