Multi-Agent Data Fusion System Based on Multiple–FPGA Parallel Computing Architecture

The multi-agent system concepts appeared recently and it is extremely distributed in all research areas to solve problems by many agents cooperation. In some applications, quick, accurate, and complete data is highly required for supporting decision making in order to reduce the decision cycle and to minimize the loss. Multi-agent data fusion has been used for such applications where the process of integration of multiple data and knowledge is turned into a consistent, accurate, and useful representation. The benefit of using multi-agent data fusion is that it can use for large structural, collect as much data as possible using different kinds of sensors with low cost. This paper presents a multiagent cooperation system using a real time processor based on FPGA which is used as parallel processing to speed up the processing, measuring the time and the amount of data being processed. This makes real-time or near-real-time damage detection possible. The proposed multi-agent data fusion system is evaluated by a bridge aluminum structure monitoring experiment in which strain distribution are monitored by a set of sensors.