A Probabilistic Machine Learning Approach to Detect Industrial Plant Faults
This addresses the need for automatic data-driven fault detection in industrial plants, but it is incremental as it applies existing classification methods to this domain.
The paper tackled fault detection in industrial plants by proposing a machine learning algorithm that predicts fault start and end times using classification methods like penalized logistic regression, random forest, and gradient boosted tree, achieving first place in the Prognostics and Health Management Society 2015 Data Challenge.
Fault detection in industrial plants is a hot research area as more and more sensor data are being collected throughout the industrial process. Automatic data-driven approaches are widely needed and seen as a promising area of investment. This paper proposes an effective machine learning algorithm to predict industrial plant faults based on classification methods such as penalized logistic regression, random forest and gradient boosted tree. A fault's start time and end time are predicted sequentially in two steps by formulating the original prediction problems as classification problems. The algorithms described in this paper won first place in the Prognostics and Health Management Society 2015 Data Challenge.