Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 2 appraisals
PloS one
Risk assessment of civil aviation cabin safety incidents based on the CNN-LSTM-Attention model
Against the backdrop of the thriving global civil aviation industry, cabin safety, which is a crucial link in civil aviation safety systems, has prompted an increasingly urgent need for intelligent risk management. This study constructs an integrated framework of "deep text mining-intelligent risk assessment" and proposes a hybrid CNN-LSTM-Attention model for cabin safety incident classification. Using 8,280 global cabin abnormal event reports from 2004-2024, the model achieves 95.01% accuracy and an F1 score of 94.17% on the test set, substantially outperforming benchmark approaches. Compared with XGBoost (89.45% accuracy, 88.98% F1), the proposed model improves accuracy by 5.56% and the F1 score by 5.19%, demonstrating superior capability in extracting deep semantic features and identifying key risk patterns. The framework also establishes a "text feature-risk mechanism-hazard level" mapping system, enabling more interpretable risk quantification. The findings provide an effective technical path for intelligent early warning of cabin safety risks and offer methodological support for data-driven decision-making in civil aviation safety management.
30 May 2026
Read appraisal →PloS one
Trajectory planning method for pipeline installation robots based on AS-DTRRT
Pipeline installation robots install pipelines on both sides of mine roadways using robotic arms; the geometric shape and length of the pipelines affect the movement trajectory of the robotic arms, and the working environment is complex and changeable. Aiming at the issues of the mechanical arm's long motion trajectory, low installation efficiency, and pipeline collision vulnerability during installation, a trajectory planning method based on the improved dual-tree RRT algorithm (AS-DTRRT) is proposed. Taking the pipeline installation robot with a 6-degree-of-freedom Cartesian coordinate robotic arm as the research object, the Artificial Potential Field method is introduced to guide the growth direction of new nodes in the path of the dual-tree RRT algorithm; aiming at the problem that the Artificial Potential Field method is prone to falling into local optimality, an adaptive step-size dynamic environment bias strategy is proposed, which automatically adjusts the step size according to the environmental conditions of the position where the new node is located to further improve the path search capability. This study analyzes the influence of pipeline geometry and length on the robotic arm's working space, proposes a pipeline collision avoidance strategy considering the working environment, and applies quintic polynomial interpolation to plan the trajectory of collision-free paths while considering joint speed and acceleration constraints. Simulations and platform experiments comparing AS-DTRRT with RRT*, D-RRT, Bi-RRT*, and A-RRT validate the method's feasibility, demonstrating that AS-DTRRT outperforms the four algorithms by reducing actual runtime by 20.22%, 15.48%, 4.69%, and 16.47% and shortening average path lengths by 21.17%, 13.78%, 6.85%, and 9.24% respectively. The proposed method enhances search efficiency and reduces path lengths, providing an effective approach for trajectory planning of pipeline installation robots.
24 May 2026
Read appraisal →