Abstract
This case study provides feasibility analysis of adapting Spiking Neural Networks (SNN) based Structural Health Monitoring (SHM) system to explore low-cost solution for inspection of structural health of damaged buildings which survived after natural disaster that is, earthquakes or similar activities. Various techniques are used to detect the structural health status of a building for performance benchmarking, including different feature extraction methods and classification techniques (e.g., SNN, K-means and artificial neural network etc.). The SNN is utilized to process the sensory data generated from full-scale seven-story reinforced concrete building to verify the classification performances. Results show that the proposed SNN hardware has high classification accuracy, reliability, longevity and low hardware area overhead.
Highlights
Earthquake is an oscillatory movement caused by the abrupt release of strain energy stored in the rocks within the crust of earth surface
Knowledge, conventional artificial neural networks (ANN) and Probabilistic Neural Networks (PNN) are widely used for structural damage detection [24,25,26] but no structural health monitoring application of Spiking Neural Networks (SNN) has been reported in the literature
K-Means used as an input for the k-means algorithm
Summary
Earthquake is an oscillatory movement caused by the abrupt release of strain energy stored in the rocks within the crust of earth surface. The structural health of buildings and other infrastructure suffers degradation due to environmental catastrophes caused by ageing, hazards and natural disasters [1]. In the event of a disaster, it is important (i) to detect and quantify the severity of damage caused by environmental disasters at an early stage; (ii) to assess the current structural health and reliability of buildings to ensure their safe use; and (iii) to estimate repair costs for damage to minimize economic losses [2]. Recent research suggests that we can build a human brain-like, fault-tolerant, energy-efficient system with learning capability to enhance the robustness, productivity and endurance of the electronic hardware systems [6,7]. This paper proposes an SHM system that is based on SNN hardware to address the challenges of longevity and reliability of the monitoring system.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call