Remaining useful life (RUL) prediction is a core task in the prognostics and health management (PHM) of mechanical systems, which helps to guide preventive maintenance to improve the reliability of industrial systems. However, current models struggle to effectively model the ’implicit operating conditions’ changes caused by the coupling of degradation in multiple components when faced with complex machinery. Therefore, in this paper, we propose a multi-channel integrated network based on state space models, called the LT-Mamba network, which models operating conditions while providing deep interpretability. Specifically, we introduce a Mamba model based on state space models (SSM) to enhance the model’s perception and fitting capabilities for ’implicit operating condition’ variations. Additionally, we augment the Mamba model’s global observation capabilities with a trend auxiliary attention mechanism(TAAM) and LSTM to increase sensitivity to changes in degradation rates. Finally, we conduct life prediction by integrating features extracted from various models. We conducted benchmark experiments using the C-MAPSS dataset and the Milling dataset. The results demonstrate that the proposed method outperforms the existing methods.

Aero-engine defects often exhibit micro-scale and high-frequency characteristics under complex metallic textures, which makes precise segmentation difficult. Most existing pixel-level methods rely on spatial-domain modeling and lack frequency-domain decoupling. As a result, high-frequency details are easily hidden by low-frequency background information. In addition, repeated downsampling weakens the representation of fine-grained structures, leading to inaccurate boundary localization and limited robustness. To address these issues, a spectrum-driven hierarchical learning network is proposed for aero-engine defect segmentation. First, a dual-band spectral module is constructed using the discrete cosine transform to separate high-frequency and low-frequency components, providing stable and physically meaningful frequency-domain priors for the network. Second, a detail-guided module is designed where high-frequency features adaptively guide skip connections, compensating information loss during encoding and improving boundary recovery. Furthermore, a low-frequency-driven region-aware modeling module is developed. The internal defect regions, boundary areas, and background regions are modeled hierarchically. A dynamic hyper-kernel generation mechanism performs region-sensitive convolutional modeling, improving adaptation to complex structural variations. Extensive experiments on the Turbo19 and NEU-Seg datasets demonstrate that the proposed method produces accurate defect boundaries and achieves mIoU scores of 89.82% and 91.44%, improving over the second-best method by 5.22% and 4.42%, respectively.