油液监控诊断专家系统中光谱特征信息的提取与建立

油液检测手段主要有常规理化性能检验、油料光谱分析、铁谱分析和颗粒计数四种，其目的在于控制油液的性能变化，控制设备状态变化和诊断设备故障，分析零件失效。进行信息提取主要目的是为了建立专家系统所必需的知识库，所以要求信息提取，真实准确，并能够提供相应的数学模型，以便于信息的提取和识别。本文对油液检测手段中的油料光谱分析进行描述，以获得专家系统所必需的知识信息。

Information Extraction and Knowledge-Base Establishment in Expert System for Oil Monitoring and Diagnosis

There are four means in oil analysis, including routine performance analysis, spectral analysis, ferrographic analysis and particle size analysis in order to control and evaluate the condition of used oil and equipments We can analyze the reason of fault of equipments First, we must pick up and establish timely, accurately and largely feature information from the oil used in these equipments Second, we must put these feature information into repository and establish relevant mathematics model This paper discusses and solves these problems