The application of data mining and cloud computing techniques in data-driven models for structural health monitoring

S. Khazaeli; A. G. Ravandi; S. Banerji; A. Bagchi

doi:10.1117/12.2218707

1 April 2016 The application of data mining and cloud computing techniques in data-driven models for structural health monitoring

S. Khazaeli, A. G. Ravandi, S. Banerji, A. Bagchi

Author Affiliations +

Proceedings Volume 9805, Health Monitoring of Structural and Biological Systems 2016; 98052M (2016) https://doi.org/10.1117/12.2218707
Event: SPIE Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring, 2016, Las Vegas, Nevada, United States

Abstract

Recently, data-driven models for Structural Health Monitoring (SHM) have been of great interest among many researchers. In data-driven models, the sensed data are processed to determine the structural performance and evaluate the damages of an instrumented structure without necessitating the mathematical modeling of the structure. A framework of data-driven models for online assessment of the condition of a structure has been developed here. The developed framework is intended for automated evaluation of the monitoring data and structural performance by the Internet technology and resources. The main challenges in developing such framework include: (a) utilizing the sensor measurements to estimate and localize the induced damage in a structure by means of signal processing and data mining techniques, and (b) optimizing the computing and storage resources with the aid of cloud services. The main focus in this paper is to demonstrate the efficiency of the proposed framework for real-time damage detection of a multi-story shear-building structure in two damage scenarios (change in mass and stiffness) in various locations. Several features are extracted from the sensed data by signal processing techniques and statistical methods. Machine learning algorithms are deployed to select damage-sensitive features as well as classifying the data to trace the anomaly in the response of the structure. Here, the cloud computing resources from Amazon Web Services (AWS) have been used to implement the proposed framework.

Citation Download Citation

S. Khazaeli, A. G. Ravandi, S. Banerji, and A. Bagchi "The application of data mining and cloud computing techniques in data-driven models for structural health monitoring", Proc. SPIE 9805, Health Monitoring of Structural and Biological Systems 2016, 98052M (1 April 2016); https://doi.org/10.1117/12.2218707

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available