|ijphm_16_004.pdf||834.4 KB||April 22, 2016 - 1:27am|
In the 2015 PHM Data Challenge Competition, the goal of the competition problem was to diagnose failure of industrial plant systems using incomplete data. The available data consisted of sensor measurements, control reference signals, and fault logs. A detailed description of the plant system of interest was not revealed, and partial fault logs were eliminated from the dataset. This paper presents a fault log recovery method using a machine-learning-based fault classification approach for failure diagnosis. For optimal performance, it was critical to be able to utilize a set of incomplete data and to select relevant features. First, physical interpretation of the given data was performed to select proper features for a fault classifier. Second, Fisher discriminant analysis (FDA) was employed to minimize the effect of outliers in the incomplete data sets. Finally, the type of the missing fault logs and the duration of the corresponding faults were recovered. The proposed approach, based on the use of an incomplete-data-trained FDA classifier, led to the second-highest score in the 2015 PHM Data Challenge Competition.