Reliable tool condition monitoring under high-noise and different milling conditions requires robust signal preprocessing and adaptive feature extraction. This study proposes a tool wear prediction framework that integrates Adaptive Variational Mode Decomposition (AVMD) with a two-stage Convolutional Block Attention Module (CBAM). AVMD uses signal spectral features to guide a directed search for decomposition parameters, reducing reliance on manually specified settings. The reference architecture processes reconstructed multi-sensor signals through multiscale convolution and a DenseNet–BiLSTM network, with two CBAM stages for feature recalibration. The first CBAM follows multiscale convolution and precedes DenseNet, while the second follows BiLSTM. Using the selected configurations, within-tool evaluations achieve R2 values of 0.9399–0.9573 on TC18 titanium-alloy milling data and 0.9907–0.9929 on the public PHM 2010 dataset. Exploratory cross-tool evaluations on PHM 2010 yield R2 values of 0.8954–0.9599 under fixed cutting conditions. t-distributed stochastic neighbor embedding and Shapley additive explanations are used to visualize feature representations and assess feature contributions to model predictions. The results demonstrate the potential of the framework for multi-sensor tool wear estimation in the evaluated machining scenarios.
Accurate ship trajectory prediction is vital for intelligent maritime traffic management, yet conventional hybrid models often fail to balance local feature extraction, long-term dependency capture, and flexible feature weighting when processing AIS data. This paper proposes an MSC-BiLSTM-ATTENTION model that integrates trajectory clustering and an adaptive attention mechanism into a unified framework. Its fundamental advance over existing incremental hybrid architectures is twofold. First, a K-means clustering step groups trajectories with similar motion patterns before model training, effectively reducing the impact of data heterogeneity on prediction accuracy. Second, the deep learning backbone synergizes multi-scale convolution (MSC)—which captures local features at multiple temporal granularities via parallel kernels—with a bidirectional LSTM (BiLSTM) for forward–backward dependency learning, and an adaptive self-attention mechanism that dynamically optimizes feature weights to amplify critical navigation information. Extensive experiments on AIS data from the Gulf of Mexico and the U.S. Atlantic Coast, covering four seasons, benchmark the model against attention-enhanced architectures including Transformer, CNN-BiLSTM-ATTENTION, and DenseNet-BiGRU-ATTENTION across two distinct regions. The proposed model achieves significant improvements in predicting longitude, latitude, speed over ground, and course over ground, reducing MAE by over 76.9% and RMSE by over 65.3% compared with the strongest baseline. Ablation studies confirm that the synergy of all three modules is essential. The results demonstrate the model’s effectiveness and its practical value for intelligent maritime supervision, navigation risk warning, and waterborne traffic management.