Feature Extraction of Acoustic Emission for Offshore Platform Structural Health Monitoring

Offshore platforms ,the important marine structures, are the basis of offshore oil exploration and development. Living in harsh environment, fatigue damage and processing defects will gradually come out, which may lead to the platform collapse. To ensure the integrity of the platform, the effective structural health monitoring technology application is necessary.
    Acoustic emission (AE) technology is potentially a promising method for crack detection in the offshore structures. The AE device could detect defects’ changes timely and effectively with exquisite sensitivity and online real-time monitoring features. It has been successfully used in foreign offshore platform monitoring, but seldom in domestic ones. As the technique is still in the research stage, a large number of research scholars from Northeast Petroleum University, Dalian University of Technology, China University of Petroleum and so on pay attention to it. It is well known that AE is proficient in data acquisition and monitoring data changes ,while not in signal processing. Signal processing plays a extremely important part in structural monitoring assessment. Without a good signal processing, the monitoring process is a failure to a certain extent.
    In this paper, we addresses an application of the Hilbert-Huang transform(HHT) and time-frequency analysis methods to characterize the AE signals released from the offshore structure model. To find the relationship between platform conditions and acoustic emission signals features changes, we use single-factor variable method to adjust the different cracks expansion conditions, such as changing the frequency of loading signal, in testing experiments.
    The AE characteristics parameters, such as energy count, ring count and duration in time domain signal, is focused on. The parameters change regularity can be explored by analyzing the variation of AE signals and platform condition changes.
    Without artificial determining of the decomposition level, the AE signal could be broken down into Intrinsic Mode Functions(IMFs) by HHT, while the wavelet (packet) transform could not. Filter out non-acoustic emission frequency band components for signal de-noising and reserve the larger IMFs by the cross-correlation analysis between each IMF and original signal. After HHT analysis, we use time-frequency analysis methods, such as Fourier transform, Wavelet transform and joint time-frequency distribution, to extract AE characteristics. It can be concluded that the joint of HHT and time-frequency analysis is an effective tool to extract the features in offshore structures, which have a certain sense in the application of acoustic emission technique.