Reactor Diagnostics Via Neural Net (Research Planning Grant for Women Scientists and Engineers)

通过神经网络进行反应堆诊断（女科学家和工程师研究规划补助金）

• 批准号: 9111145
• 负责人: shahla keyvan
• 金额: $ 2.3万
• 依托单位: Missouri University of Science and Technology
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 1991
• 资助国家: 美国
• 起止时间: 1991-08-01 至 1993-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9111145&HistoricalAwards=false
• 关键词: Reactor; Diagnostics; Via; Neural; Net

Neural networks offer a flexible, general purpose approach to building the complex highly nonlinear models that are required for a complex system such as a nuclear power plant. Recent developments in learning algorithms for neural networks provide alternatives to the traditional pattern recognition techniques for analysis of diagnostics. This research planning grant involves a comprehensive bench mark test for feasibility study for nuclear reactor signal analysis via a neural network approach. The test consists of a comparison between equipment degradation monitoring by traditional time series analysis versus a neural network approach.

神经网络提供了一种灵活的通用 建立复杂的高度非线性 复杂系统所需的模型，例如 核电站 最近的事态发展 神经网络的学习算法提供了 传统模式识别的替代方法 诊断分析技术。 这项研究计划拨款涉及一个全面的 核反应堆可行性研究基准试验 通过神经网络方法进行信号分析。 测试 包括设备之间的比较 传统时间序列退化监测 分析与神经网络方法。