With the rise of data engineering-driven automatic annotation strategies, deep learning has demonstrated remarkable performance and strong competitiveness in intelligent fault diagnosis. However, the inherent limitations of automatic annotators inevitably introduce noisy labels, which in turn hinder the generalization and accuracy of diagnostic models. Although numerous Learning with Noisy Labels (LNL) methods attempt to alleviate the impact of label noise through sample selection or label correction, most rely heavily on model predictions to guide training. This self-reinforcing mechanism frequently leads to confirmation bias, especially under high-noise conditions, thereby limiting their e... More >

Facing the challenges of low efficiency and poor quality in UAV 3D path planning within large-scale airspace complex environments, this paper introduces a divide-and-conquer approach, proposing a dual-layer path planning method based on multi-source information fusion. The method decomposes traditional path planning into two steps: heading planning and trajectory planning, ensuring both planning efficiency and path quality. This method segregates the solution process into two distinct stages: heading planning and path planning, thereby ensuring the planning of both efficiency and path quality. Firstly, the path planning phase is formulated as a multi-objective optimization problem, taking in... More >