论文部分内容阅读
概念格是根据数据集中对象与属性之间的二元关系建立的一种概念层次结构,生动简洁地体现了概念之间的泛化和特化关系。利用概念格的这一特性,提出利用概念格理论进行故障诊断时的属性约简。为验证属性约简的正确性,将约简结果送到神经网络中进行故障诊断,诊断结果表明:利用概念格理论所得到的核心属性和相对必要属性可以对现有故障类型进行正确辨识,降低了故障诊断参数的维数,有利于加快诊断算法的运算速度。
Concept lattice is a conceptual hierarchy based on the binary relationship between objects and attributes in data set, which vividly and concisely reflects the generalization and specialization of concepts. By using this feature of concept lattice, the attribute reduction of fault diagnosis using concept lattice theory is proposed. In order to verify the correctness of the attribute reduction, the result of the reduction is sent to the neural network for fault diagnosis. The diagnostic results show that the existing fault types can be correctly identified and reduced by using the core attributes and the relative essential attributes obtained by the concept lattice theory The dimension of the fault diagnosis parameters helps speed up the operation of the diagnostic algorithm.