No abstract

On March 11, 2011, the greatest earthquake ever recorded in Japan (Magnitude 9.0) occurred with an epicenter off the coast of the Sanriku area. More devastating than the earthquake was the damage caused by the massive Pacific coast tsunamis in the Tohoku and Kanto areas. These injuries were exacerbated by the failure of the Fukushima Daiichi nuclear plant as a result of the earthquake and tsunami inhibiting the cooling of the nuclear reactors. As recently as October, 2011, the Great East Japan Earthquake had resulted in 300,000 total or partially collapsed buildings (National Police Agency), nearly 20,000 victims identified as dead or missing, and, at its peak crisis time, nearly 400,000 evacuees from the area (Ministry of Economy, Trade and Industry). The national government calculated a damage of 16 to 25 trillion yen which does not include the impact of the nuclear accident, an unprecedented catastrophe that exceeded the damages from the Great Hanshin-Awaji Earthquake of 9.9 trillion yen, making it more than twice as large.

The fuel cell is regarded as a highly efficient, low-pollution power generation system. In particular, Solid Oxide Fuel Cell (SOFC) has a high generation efficiency. However, a crucial issue in putting SOFC to practical use is the establishment of a technique for evaluating the deterioration. We previously developed a technique by which to measure the mechanical damage of SOFC using the Acoustic Emission (AE) method. In the present paper, we applied the kernel Self-Organizing Map (SOM), which is an extended neural network model, to produce a cluster map reflecting the similarity of AE events. The obtained map visualized the change in occurrence patterns of similar AE events, revealing four phases of damage progress. The methodology of the present study provides a common foundation for a comprehensive damage evaluation system and a damage monitoring system.

No abstract