Accurate and stable predictions of the state-of-health (SOH) of lithium-ion batteries are essential for effective battery management and extending battery lifespan. Two major issues exist in current lithium battery capacity prediction models. First the original data captured from temperature, voltage, and current sensors contains a large number of noises, which negatively impacts prediction accuracy. Second, the SOH of lithium-ion batteries is significantly influenced by factors such as current temperature, charge and discharge rates, and voltage. These rapid changing factors can be captured more effectively using short-term dependence rather than long-term dependence. However, the short-term dependence of capacity degradation is not fully captured, and the coupling relationships among multivariable sequences, along with the inaccurate capacity predictions resulting from frequency information, are not adequately addressed. In this paper, we propose a frequency-domain enhanced trans-variate short-term dependence recognition framework, FE-STDR, to solve these two problems and predict the SOH of lithium batteries. The FE-STDR framework comprises two modules including stacked denoising autoencoder (SDAE) and FEformer. SDAE module removes noise captured during the original battery data acquisition and capacity cycles, automatically extracting high-level features to capture complex battery state patterns through its multi-layer denoising structures. The FEformer module introduces a frequency enhanced channel attention mechanism to integrate frequency information into the framework while considering short-term frequency dependence in lithium battery data. The results indicate that the root mean square error of the proposed framework is reduced by 6.53%, 11.78%, and 7.34%, respectively, compared to the baseline models: long short-term memory, Transformer, and AE-GRU. The prediction accuracy proves that the proposed FE-STDR is superior, enabling accurate forecasting of the degradation trajectory of lithium battery SOH.
Ant colony optimization (ACO) has garnered significant attention because of its wide application in route planning problems. Nevertheless, ACO requires a long time to calculate when tackling complex issues. Parallelization emerges as an effective strategy to improve algorithm execution efficiency, and especially in large-scale computations, parallelization technology can significantly reduce execution time. In this study, we propose an ant colony algorithm (Sunway ant colony optimization, SWACO) based on a second-level parallel strategy and tailored to the hardware characteristics of Sunway many-core processors. The first level involves process-level parallelism, in which the initial ant colony is divided into multiple child ant colonies according to the number of processors, with each child ant colony independently performing computations on each island. The second level is thread-level parallelism, utilizing the computing power of the slave core to accelerate path selection and pheromone updates of the ants, thereby effectively improving algorithm execution efficiency. The experimental results demonstrate that, across multiple TSP datasets, the SWACO algorithm significantly reduces computation time, achieving an overall speedup ratio by 3–6 times, and maintains the gap within 5%. A substantial acceleration effect was achieved.
6 February 2026 in Expert Systems with Applications