Automated Classification and Analysis of Power System Disturbance Waveforms Using a Neural Network Approach

9412764 Lubkeman这个拟议项目的目标是调查和开发一种方案，利用人工神经网络(ANN)和基于案例的推理(CBR)方法的组合，进一步实现电能质量研究中电力扰动的监测、记录和诊断的自动化。拟议的研究是：(A)制定一项使记录器的数据收集过程自动化的方案--这涉及用于对捕获的波形进行分类的人工神经网络方法和用于有效存档数据的基于规则的关系数据库设计，以及(B)调查基于案例的推理方法在帮助诊断干扰方面的适用性。这项研究代表着使用刚刚兴起的最先进的人工智能技术朝着智能诊断和测量工具的方向迈出了一步。这将是对目前记录仪的重大改进，提供了对干扰的测量和诊断的进一步自动化。***

9412764 Lubkeman The objective of this proposed project is to investigate and develop a scheme to further automate the monitoring, recording, and diagnosis of power disturbances for power quality studies, using a combination of artificial neural network (ANN) and case- based reasoning (CBR) approaches. The proposed research is (a) to develop a scheme to automate the data collection process of recorders--this involves an ANN methodology for the classification of waveforms that are captured and a rule-based relational database design for the effective archival of data, and (b) to investigate the applicability of a case-base reasoning approach towards aiding the diagnosis of disturbances. This research represents a step in the direction of intelligent diagnostic and measurement tools using state-of- the-art artificial intelligence technologies which are just emerging. It would be a significant improvement over present-day recorders, providing for further automation of the measurement and diagnosis of disturbances. ***