False alarm reduction in drilling process monitoring using virtual sample generation and qualitative trend analysis

Liang Cao, Bhushan Gopaluni

Abstract: Process monitoring is essential for ensuring the safety of geological drilling processes, but most existing monitoring systems suffer from false alarms. This study is motivated by the fact that many false alarms are generated from dynamic changes in signals under normal conditions. A new process monitoring method is proposed by analyzing the relationship between the input and output signals of a drilling normal behavior model, enabling a fault detection decision by checking their qualitative trends at the change point. The main novelties of this study are: (i) a data-driven normal behavior model describing the fault-free operating condition is proposed to output expected healthy virtual samples; (ii) a new alarm generation strategy is designed for reducing false alarms in drilling processes based on change point detection and qualitative trend analysis. Industrial case studies demonstrate the effectiveness and practicability of the method.