Transformer-augmented deep Q-network-based risk-informed maintenance policy for partially observable systems under combined degradation and random shock effects

Key Points

• The risk-informed maintenance policy improves performance in systems facing combined degradation and random shock effects.
• The framework integrates transformer-augmented deep Q-networks for better learning from system states and uncertainties.
• Analysis reveals that using this method enhances predictive accuracy for maintenance needs over traditional approaches.
• Implications suggest that implementing this policy may lead to more reliable operations in complex systems.