“…Up to now, the most established approaches, which have been put into or of potential for practical applications, can be grouped into two categories: the expert system-based [1][2][3][4][5] or the analytic model-based methods [6][7][8][9][10][11][12][13]. In addition, Artificial Intelligent methods such as Petri Nets [14,15], Artificial Neural Network [16][17][18], rough set (RS) [19], and Bayesian networks [20], have also been proposed for diagnosis of fault sections.…”