Structural Health Monitoring-Oriented Data Mining, Feature Extraction, and Condition Assessment
1School of Civil Engineering, Research Center for Structural Health Monitoring and Control, Dalian University of Technology, Dalian 116023, China
2Department of Civil Engineering, Geodesy and Geodetic Applications Laboratory, Patras University, Patras 26500, Greece
3Department of Civil Engineering, Zhejiang University, Anzhong Building, Zijingang Campus, China
4School of Civil and Resource Engineering, University of Western Australia, Crawley, WA, Australia
Structural Health Monitoring-Oriented Data Mining, Feature Extraction, and Condition Assessment
Description
Structural health monitoring (SHM) is the usage of modern sensing technologies, communication algorithms, and advanced data mining and management systems to monitor the operational environments and loadings as well as the structural responses in real time to effectively evaluate the structural health condition and safety performance and to instruct the daily structural inspection and maintenance, which is a multidiscipline and cutting-edge research field in civil engineering. In the past several decades, a great amount of long-term SHM systems have been designed and implemented worldwide on civil engineering structures such as large-scale bridges and high-rise buildings. With these SHM systems, a vast ocean of information relevant to the structural responses and behavior can be continuously obtained in real time. The measurement data are valuable in detecting structural anomalies and damage at an early stage to ensure operational safety and providing authentic information for timely assessment after disasters and extreme events.
A critical issue of great concern is how to extract the features inherent in the monitoring data for structural performance assessment targeting to life-cycle safety, reliability, durability, and sustainability. Therefore, intelligent computational methodologies and approaches such as artificial neural networks, fuzzy logic systems, and genetic algorithms are always desired. In this connection, we invite investigators to contribute original papers and review articles of the theme of SHM-oriented data mining, feature extraction, and condition assessment based on advanced mathematical methods. Potential topics include, but are not limited to:
- Data-driven structural health evaluation based on wired or wireless system
- Nature-inspired intelligent computational methods for data mining
- Damage detection and system identification by the use of real-world monitoring data
- Reliability-based structural condition/safety assessment with uncertainties
- Development of novel analytical models for structural feature extraction
- Other related
Before submission authors should carefully read over the journal’s Author Guidelines, which are located at http://www.hindawi.com/journals/mpe/guidelines/. Prospective authors should submit an electronic copy of their complete manuscript through the journal Manuscript Tracking System at http://mts.hindawi.com/submit/journals/mpe/shm/ according to the following timetable: