A case study for application of fuzzy inference and data mining in structural health monitoring

In this work, a system is designed for monitoring the structural health of bridge deck and predicting various possible damages to this section based on measuring the temperature and humidity using wireless sensor networks, and then it is implemented and investigated. A scaled model of a conventional medium-sized bridge (of 50 m length and 10 m height, and with 2 piers) is examined for the purpose of this work. This method includes installing two sensor nodes with the ability of measuring temperature and humidity on both side of the bridge deck. The data collected by the system including the temperature and humidity values is received using a LABVIEW-based software to be analyzed and stored in a database. The proposed structural health monitoring (SHM) system is equipped with a novel method using data mining techniques on the database of climatic conditions of past few years related to the location of the bridge to predict the occurrence and severity of future damages. In addition, this system has several alarm levels, which are based on the analysis of bridge conditions by the fuzzy inference method, so it can issue proactive and precise warnings and alarms in terms of place of occurrence and severity of possible damages in the bridge deck to ensure the total proactive maintenance (TPM). Very low costs, increased efficiency of the bridge service, and reduced maintenance costs make the SHM system a practical and applicable one. The data and results related to all mentioned subjects are thoroughly discussed, and the accuracy and reliability of the SHM systems are evaluated. The results obtained show that this system is qualified to be used as a SHM system in a sample hypothetical bridge.