基于协同式专家系统及多智能体技术的电网故障诊断方法

提出一种利用多智能体技术和协同式专家系统进行电网故障诊断的方法。该方法将智能体模型作为框架,并结合专家系统的特点对系统单元结构进行改进和细化,然后提出适用于故障诊断的整个协同式专家系统的结构体系。整个系统由7个子系统组成,分别完成复杂故障的协同快速诊断、畸变信息和不确定性信息的评价,以及实时给出调度处理建议的任务。在解决关联性故障分析问题时,该协同式专家系统克服了单一专家系统的局限性,文中利用功能协同增强了对复杂故障实时诊断的推理能力;利用区域协同可以对跨区域故障进行诊断。通过实例对系统的工作流程进行了说明并验证了协同诊断方法的正确、有效,该方法适合用于实时故障诊断系统。

A New Fault Diagnosis Approach of Power Grid Based on Cooperative Expert System and Multi-agent Technology

A new fault diagnosis approach is presented which is based on multi-agent technology and the cooperative expert system. In the proposed approach, the unit of the cooperative expert system is designed according to the modified agent models and the real-time expert system, and the structure of the whole system is also presented. The whole system is composed of seven sub-systems which are capable of finishing different tasks such as fast diagnosis of complex fault, handling distorted and uncertain information and offering the operational advices et al. The main point of this system is the fact that it is able to overcome the deficiency of the common expert system for the diagnosis of the complex and correlative faults. The cooperation in function can assist in enhancing the reasoning ability, and the regional cooperation can assist in diagnosing the fault expanding from one district to another. The simulation results show that the system works successfully and efficiently in the case of practical power grid and fits for the realization of real-time fault diagnosis.