基于Vague集相似度量的柴油机磨损类故障诊断的研究

Fault Diagnosis of Wear Type in Diesel Engine Based on Similarity Measures between Vague Sets

柴油机磨损类故障诊断中的一种有效方法是运用油液分析技术，它通过对磨粒的形状、尺寸等参数的分析，实现磨损部位、磨损程度的确定．通常我们只知道磨粒的部分信息，要识别出它究竟属于何种磨粒，需要丰富的经验．因此，研究磨粒识别方法是故障诊断中的关键技术．针对模糊集的推广形式——Vague集，描述了Vague集的含义与相似度量，并提出一种Vague集的相似度量在柴油机磨损类故障诊断中的新方法．在磨损类故障诊断中，Vague集之间的相似度量是评价检测样本磨粒模式接近标准样本磨粒模式的度量，相似度量值越大，检测样本磨粒模式接近标准样本磨粒模式越好，从而根据相似度量值确定磨损故障的类型．通过实例阐明Vague集之间的相似度量在故障诊断中的可行性和合理性，这种方法能给故障诊断以理论依据．

An effective method for the fault diagnosis of wear type in diesel engine is the analysis technology of oil liquid. Position and degree of wear arc,, determined by analyzing the shape and size parameters of wearing particles. Usually, we have wearing particles. We need enough experience to recognize which type the wearing particle is. Therefor, recognition of wearing particles is a key technology in the fault diagnosis. The meaning and similarity measures of vague sets are described as a generation of Zadeh＇ s fuzzy sets vague sets. A new method of the fault diagnosis of wear type based on similarity measures between vague sets was presented. Thesimilarity between the detecting sample pattern of wearing particles and the standard sample pattern of wearing particles are evaluated in the fauhdiagnosis of wear type by means of measuring the similarity between vague sets. The greater the measure is, the better is the similarity between the detecting sample pattern and the standard sample pattern. Then, the type of wear fault is determined according to the value of the similarity measure. Examples explaining the feasibility and reasonability are provided. The method may form the basis of fault diagnosis.