Wei Cheng

Aeroengine noise is a critical factor affecting flight safety and passenger comfort. During engine operation, the main noise components are discrete tonal noise and broadband random noise. When analyzing noise characteristics through acoustic signals, the superposition of tonal and broadband noise, along with background noise, makes it challenging to extract tonal noise for feature extraction. To address this issue, a tonal noise component extraction method based on a structured sparse model with enhanced low-rank property is proposed. By recognizing the cyclostationarity of tonal noise in time-frequency domain, a sparse and low-rank model is constructed to separate tonal components from broadband noise. The solution derivation process is conducted by a Moreau Envelope Alternative Direction Method of Multipliers algorithm to improve the convergence. The proposed method is verified by acoustic signal sampled from a full-scale aeroengine and fan which is undergoing bird ingestion to simulate abnormal condition.

Prognostics and Health Management (PHM) has emerged as a critical discipline in modern industrial systems, integrating condition monitoring, degradation prediction, and maintenance optimization to prevent catastrophic failures while minimizing operational costs. However, current PHM methodologies predominantly treat Remaining Useful Life (RUL) prediction and maintenance planning as sequential rather than coupled processes. To address this limitation, this paper proposes an integrated framework that bridges prognostic prediction with operational decision-making through predictive-driven dynamic coordination. The technical contribution is twofold: (1) A probabilistic residual convolutional network architecture incorporating Gaussian distribution modeling is developed to quantify prediction uncertainty through RUL probability distributions; (2) A multi-agent reinforcement learning paradigm is formulated to dynamically optimize maintenance scheduling and spare parts inventory control based on real-time prognostic updates and system status. Through the dual-agent mechanism of MARL, maintenance decisions and spare parts ordering are dynamically adjusted based on real-time RUL distributions, balancing cost efficiency and reliability. This empirical validation quantitatively establishes the operational advantages of synergizing uncertainty-aware prognostics with adaptive resource allocation in PHM systems.