Decision Fusion Scheme Based on Mode Decomposition and Evidence Theory for Fault Diagnosis of Drilling Process

Data-driven fault diagnosis methods have been widely applied at present. In actual processes, there usually exist multiple failure modes, the data frequency spectrum varies in different failure modes, which would bring challenges for feature extraction and subsequent fault diagnosis. In this paper, a decision fusion scheme based on mode decomposition and evidence theory is proposed for fault diagnosis during drilling. The raw data are decomposed into multiple series with different center frequencies, the decomposed series are reconstructed to several groups. For each group, the diagnosis model is established, thus, several local diagnostic results are obtained. Then, all local diagnostic results are fed into the evidence theory-based decision fusion model. Meanwhile, a confidence matrices-based weight adjustment method is designed to enhance the reliability of fused results. An industrial case study based on the actual drilling data verifies that the proposed method is beneficial to improve the diagnostic effect during drilling.