Purpose: This paper proposes an in-network vibration data processing using Wireless Sensor Network (WSN) leveraging Machine Learning (ML) for damage detection and localization. The study also presents the ML algorithms comparison that is suitable to be deployed in WSN and implemented the proposed cluster-based WSN topology on the bridge simulation test. Methods: The bridge vibration data was acquired using accelerometer-based wireless sensor nodes. The data collected are transformed using Fast Fourier Transform (FFT) to obtain fundamental frequencies and their corresponding amplitudes. The machine learning method i.e., Support Vector Machine (SVM) with linear and Radial Basis Function (RBF) kernel was used to analyze the vibration data collected from the WSN. In-network data processing and cluster-based WSN topology is implemented and the programmable wireless sensor nodes is utilized in this study. Results: The experiments were conducted using real programmable wireless sensor nodes and developed our test bed bridge which makes this work different from the previous studies. The classification and predicting results shows 97%, 96%, 97%, and 96% for accuracy, precision, recall rate, and f1-score, respectively. Conclusion: Machine learning methods can potentially be combined with the vibration WSN for bridge damage detection and localization.
Wireless Sensor Network (WSN) is small embedded devices deployed in large scale network with sensing, computing, and communicating capability. In the case of bridge structural health monitoring system, WSN has taken important role in physical measurement. This paper describes preliminary study of Agent-oriented paradigm to develop intelligent sensing in single degree of freedom bridge. The objectives of research are finding bridge condition assessment and load rating using dynamic response. Sensor node capability to compute is our consideration to develop intelligent sensing on sensor node in which signal processing with efficient resource consumption are performed. This paper is an entry point for our next research agendas: data preprocessing (in-network data processing) and intelligent agent implemented on sensor nodes.
1 September 2015 in TELKOMNIKA (Telecommunication Computing Electronics and Control)
Wireless Sensor Network (WSN) is small embedded devices deployed in large scale network with capability to sense, compute, and communicate. It combines modern sensor, microelectronic, computation, communication, and distributed processing technology. WSN has been taking an important contribution in structural health monitoring system, especially in Suramadu Bridge, one of the longest span bridges in Indonesia connecting Surabaya (East Java) and Madura Island. Due to subjected by environmental circumstance, it is necessary to implement intelligent and autonomous WSN to monitor the bridge condition, detect the bridge damage, and send warning message to bridge users when unsafe condition occurs. The multi-agent system is a promising approach to be implemented on intelligent and autonomous WSN, especially in the bridge structural health monitoring system. In this approach agents are empowered to have several intelligent learning capabilities for structural monitoring, damage detection, and prediction. This paper describes multi-agent system conceptual design that will be implemented as model of long span bridge structural health monitoring system considering system architecture and agent organization.