Real-Time Autonomous Structural Change Detection Onboard Wireless Sensor Platforms

Abstract

Real-time structural health monitoring is becoming increasingly tractable on commodity wireless sensor devices and platforms. Such algorithmic implementations must be realised in as efficient a manner as possible, in terms of memory, computation, radio communications and power efficiency. This work describes an efficient, real-time, structural change detection algorithm implemented on constrained, commodity wireless sensor nodes. The algorithm, based on the Hilbert Huang transform, initially characterises the structure and reliably signals subsequent change using a hierarchical monitoring and alert infrastructure. The system operates entirely autonomously, and algorithmic parameterisations, such as sensitivity and training period duration, can be dynamically and remotely adjusted across the air interface. The system has been evaluated on two different structures which were subject to structural change during the experiments; a Single-Degree-of-Freedom discrete dynamical system, and a 5kW wind turbine blade. The system demonstrated a highly reliable capacity to promptly detect and actuate response to structural change.