IGES-RCI: Improved Greedy Equivalence Search and Recursive Causal Inference for Industrial Equipment Failure Prediction

Abstract

Predicting equipment failures plays a pivotal role in minimizing maintenance costs and boosting production efficiency within the industrial sector. This paper introduces a novel approach that integrates Causal Inference with predictive modeling to enhance prediction accuracy, tackling key challenges such as noise interference, insufficient causal validation, and missing data. We first validate the causal connections identified by the Greedy Equivalence Search algorithm using conditional mutual information to strengthen the reliability of the causal graph. An information bottleneck strategy is then employed to isolate essential causal features, effectively filtering out irrelevant noise and refining the causal structure. Crucially, in the actual prediction phase, we propose a recursive causal inference-based imputation method to handle missing data, leveraging the causal graph to iteratively infer and fill gaps, thereby improving data completeness and prediction accuracy. Experimental results demonstrate that the proposed method significantly outperforms existing approaches, exhibiting superior accuracy and robustness in managing complex industrial datasets.