Estimating the Remaining Useful Life (RUL) of aircraft engines plays a vital role in the field of prognostics and health management. In multi-dimensional time series regression tasks, accurately capturing both time series features and sensor features, as well as integrating these two types of features, poses a significant challenge for RUL prediction. The sensor features represent the weights of each sensor on the RUL prediction results. To overcome this challenge, we introduce a hybrid model based on a dual-attention mechanism. Initially, a temporal feature extraction block is applied to map the time-step dimension into a hidden representation space, facilitating the capture of complex temporal dynamics. These patterns are then refined using a multi-head self-attention mechanism. Subsequently, a sensor feature extraction block is applied to capture sensor-specific characteristics. Each sensor sequence is treated as a separate channel, compressed to derive sensor weights, and integrated to form global features that fuse temporal and sensor-level representations. Finally, RUL is estimated via a regression layer. The proposed method is demonstrated to be effective on the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset. Compared with the state-of-the-art CTNet model, the proposed method achieves 7% and 9% gains in RMSE and Score, respectively, on the FD001 dataset.
3 January 2025 in Flexible Services and Manufacturing Journal
Disassembly lines are widely utilized to disassemble end-of-life products. Most of the research focuses on the complete disassembly of obsolete products. However, there is a lack of studies on profit and on carbon emission saved. Hence, this study considers the multi-objective partial disassembly line balancing problem with AND/OR precedence relations to optimize profit, saved carbon emission and line balance simultaneously. Firstly, a multi-objective mixed-integer programming model is formulated, which could optimally solve the small number of instances with a single objective. Meanwhile, an improved multi-objective artificial bee colony algorithm is developed to generate a set of high-quality Pareto solutions. This algorithm utilizes two-layer encoding of the task permutation vector and the number of selected parts, and develops two-phase decoding to handle the precedence relation constraint and cycle time constraint. In addition, the modified employed bee phase utilizes the neighborhood operation, and the onlooker phase utilizes the crossover operator to achieve a diverse population. The modified scout phase selects a solution from the Pareto front to replace the abandoned individual to obtain a new high-quality solution. To test the performance of the proposed algorithm, the algorithm is compared with the multi-objective simulated annealing algorithm, the original multi-objective artificial bee colony algorithm and the well-known fast non-dominated genetic algorithm. The comparative study demonstrates that the proposed improvements enhance the performance of the method presented, and the proposed methodology outperforms all the compared algorithms.
Remaining useful life (RUL) prediction is critical for improving reliability and supporting predictive maintenance in aero-engine systems. However, existing methods have limitations in jointly modeling the spatial correlations between multi-sensor signals and the temporal evolution characteristics of the degradation process. Hence, this study develops a knowledge-enhanced spatiotemporal framework for system-level aero-engine RUL prediction. Firstly, a graph based on the Pearson correlation coefficient (PCC) is constructed from monitoring data to capture data-driven dependencies among sensors. Afterwards, a thermodynamic-cycle-mechanism prior is incorporated into the PCC-based graph through the Hadamard product, forming a knowledge-enhanced graph that emphasizes physically meaningful sensor relationships. Subsequently, an enhanced graph attention module is designed to extract discriminative spatial representations from the knowledge-enhanced graph. Furthermore, relational representations between adjacent time steps are constructed to capture implicit temporal correlations and local degradation dynamics. Finally, a dual-stream GRU with an attention mechanism is employed to model the fused feature stream and relational feature stream for RUL prediction. Experiments on the CMAPSS and N-CMAPSS datasets demonstrate that the proposed method achieves competitive and overall superior performance compared with nine state-of-the-art methods. KESTF achieves the best average RMSE/Score of 12.83/580 on CMAPSS and 5.94/3468 on N-CMAPSS, validating its effectiveness and robustness.