Related Experiment Video
Updated: Aug 10, 2026
05:30
Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
Published on: September 8, 2023
Performance Evaluation of Structural Health Monitoring Anomaly Data Processing Algorithms in Resource-Constrained
Kuanjiu Lei1, Yaojie Li2,3, Shitong Hou2,3
1School of Architecture and Engineering, Xinjiang University, Urumqi 830017, China.
Sensors (Basel, Switzerland)
|July 28, 2026
Summary
This study evaluates edge computing for structural health monitoring (SHM) anomaly detection on resource-constrained devices. It assesses data processing workflows, finding key performance trade-offs for real-world infrastructure applications.
Area of Science:
- Engineering
- Computer Science
- Data Science
Background:
- Edge computing is crucial for structural health monitoring (SHM) in transportation infrastructure, enabling local data processing and low-latency decision support.
- SHM systems face challenges with data anomalies from sensor faults, transmission errors, or irregular structural behavior.
- Deploying complex SHM data-processing workflows on resource-constrained edge devices requires careful performance evaluation.
Purpose of the Study:
- To evaluate the deployment performance of an SHM anomaly data-processing workflow on resource-constrained edge devices.
- To analyze the trade-offs between different algorithms for data cleaning, response separation, and anomaly detection in SHM.
- To provide insights into the practical application of edge computing for infrastructure monitoring.
Main Methods:
- The study implemented a workflow including data cleaning (cubic spline interpolation, Laida criterion, wavelet denoising), response separation (time windows, 3σ criterion, wavelet packet decomposition), and anomaly detection (ARIMAX, SVM, RNN).
- Performance was evaluated using simulation and field monitoring data (bridge displacement, highway pavement strain).
- Key metrics included runtime, memory usage, CPU usage, and a data-processing throughput proxy.
Main Results:
- The evaluation quantified the performance and resource consumption of various algorithms on edge devices.
- Trade-offs between different data processing and anomaly detection methods were identified under typical SHM resource constraints.
- The study demonstrated the feasibility and challenges of deploying advanced SHM analytics at the edge.
Conclusions:
- The analysis provides a clear understanding of the performance characteristics and resource requirements of SHM data-processing workflows on edge devices.
- This research aids in selecting appropriate algorithms for edge-based SHM systems, optimizing for performance and resource limitations.
- The findings are critical for the effective implementation of edge computing in intelligent transportation infrastructure monitoring.