Improved decision tree construction based on attribute selection and data sampling for fault diagnosis in rotating machines

Intelligent fault diagnosis of synchronous generators

“…Seera et al developed a hybrid intelligent model using fuzzy min max (FMM) neural network and the random forest (RF) ensemble (FMM-RFE) for condition monitoring of induction motors using the motor current signature analysis (MCSA) method under noisy and noise-free environments (Seera et al, 2014). In (Karabadji et al, 2014), an improved unpruned decision tree was constructed by combining the attribute selection and data reduction process to overcome the decision tree size and over-fitting problems for machine fault diagnosis.…”

A dynamic ordered concept lattice based algorithm for early diagnosis of NPP faults

“…The numbers of failures and disruptions are now increasing with the complexity of equipment installed in the industrial field causing immediate shut-down of a machine, and/or undermining proper functioning of an entire production system (Karabadji et al, 2014). In general, 99 accidents were reported at NPP from 1952 to 2009; including: most and recent serious NPP accidents of the Fukushima Daiichi nuclear disaster (2011), Chernobyl disaster (1986), Three Mile Island accident (1979), and the SL-1 accident (1961) (Sovacool, 2008(Sovacool, , 2010Friedman, 2011;Inoue et al, 2012;Cilliers, 2013;chwartz, 2004;Lv et al, 2013).…”

Research on Big Data Attribute Selection Method in Submarine Optical Fiber Network Fault Diagnosis Database

“…It brings people convenience while also the network virus [1][2] affecting network security. According to the real-time performance of submarine optical fiber network fault diagnosis [3][4][5], a big data attribute selection method based on rough set of submarine optical fiber network fault diagnosis database is proposed [6]..…”