To address multi-UAV task allocation and dynamic obstacle avoidance in post-disaster scenarios, this paper proposes a hierarchical GOAPF-MARL (Goal-Oriented Artificial Potential Field Guided Multi-Agent Reinforcement Learning) framework. In the perception layer, a task model is built to couple casualty level and disaster scale, forming a unified task weight W and enabling more accurate demand representation under varying conditions. For upper-layer allocation, an improved SADCK-Medoid method is used with the Balanced Residual Capacity (BRC) metric to enable nonuniform UAV deployment across five rescue regions. In the execution layer, a Goal-Oriented Artificial Potential Field (GOAPF) is embedded into multi-agent reinforcement learning (MARL), improving navigation around buildings, debris, and expanding fire zones while enhancing coordination and decision stability in complex scenes. Simulation results demonstrate improved efficiency and robustness compared with baseline methods under both ideal and challenging settings.
Lipeng Zhang, Junjie Liu, Yuehui Ji et al.· 2026 IEEE 27th China Confere...· 0 citations
The Factory Acceptance Test (FAT) of Process Control Systems (PCS) on offshore platforms traditionally relies on manual channel-by-channel verification, which is time-consuming, error-prone, and heavily dependent on human factors. This paper presents an automated channel testing system that significantly improves testing efficiency and reliability. The system integrates a programmable logic controller (PLC) as the signal generation and acquisition unit, a custom-designed rapid connection interface for direct terminal block access, and a Java-based software platform utilizing OPC communication and MySQL database. The software automatically parses engineering configurations, executes test sequences, compares measured values against expected ranges, and generates comprehensive test reports. A case study on a 520-channel DCS system demonstrates that the proposed system reduces testing time from approximately 8 person-hours to less than 2 person-hours while eliminating manual recording errors. Furthermore, we extend the evaluation to three additional projects with varying scales (150-1500 channels), showing consistent efficiency gains. The system also supports flexible test point selection (e.g., 3-point or 5-point method) and provides statistical analysis of channel accuracy. This work not only automates a tedious industrial task but also lays the foundation for intelligent testing in digital oilfield environments.
To address the issues of insufficient feature extraction and low localization accuracy in distribution network fault diagnosis, this study proposes a fault classification and localization method based on APC-SVM and PC-AZOA. The model performs a simultaneous decomposition of three-phase signals using multivariate variational modal decomposition and employs the energy entropy of each model component as the feature vector; During the classification stage, the method integrates electrical and physical constraints, introducing three-phase energy imbalance and variance into the support vector machine ’ s parameter optimization process for the first time to dynamically adjust the penalty factor and kernel parameters; finally, a traveling wave propagation time error model is constructed, and an adaptive zebra optimization algorithm constrained by physical information is proposed. By innovatively embedding prior physical knowledge into the search space constraints, the method effectively suppresses invalid searches and improves convergence efficiency. Experimental results show that the model achieves a classification accuracy of up to 98.4% with a positioning error below 1%, demonstrating both high precision and high efficiency.
Dahua Li, Xinrui Yang, Yu Song et al.· 2026 IEEE International Conf...· 0 citations