|
| 摘要: |
| 详细介绍了利用粗糙集的基本理论构造变压器的多变量故障决策树的具体过程．考虑了属性间的关联性，避免了生成决策树时故障特征的重复检测，适用于大量样本的自动处理，具有较好的自组织性和自适应性。通过粗糙集分辨矩阵确定多变量检测特征的选取．将相对泛化的概念用于构造多变量检验，采用知识粗糙度作为选择决策树属性的度量．方便有效地解决了构造多变量故障决策树的关键问题。与传统的信息熵算法相比．基于知识粗糙度的决策树计算量大大减少．且可能得到最优的故障树。故障实例分析表明，该方法有效地简化了决策树．减少了故障信息的冗余性．诊断效率高．结果易于被人理解。 |
| 关键词: 电力变压器 故障诊断 粗糙集理论 知识粗糙度 多变量决策树 |
| DOI： |
| 分类号:TM401 |
| 基金项目: |
|
| Application of knowledge roughness-based multivariate decision tree in transformer fault diagnosis system |
|
LI Jing-hua LI Ran
|
| Abstract: |
| The construction of multivariate decision fault tree by rough set theory for transformer is introduced. It considers the correlations among attributes and avoids repeated detecting the fault symptoms during the decision tree generation. With good self-adaptability and self-organization,it is suitable for auto-processing of large samples. Furthermore,it uses discernibility matrix of rough set to select symptoms,checks multivariate using generalization concept and chooses attributes according to the knowledge roughness. Thus the key problems in building multivariate tree are solved effectively. Compared with entropy,computations of knowledge roughness-based decision tree are reduced greatly and the tree may be optimum. The result of practical fault examples shows that the proposed method simplifies the decision tree and reduces the redundancy of fault diagnosis information with high efficiency,and easy to be understood. |
| Key words: transformer fault diagnosis rough set theory knowledge roughness multivariate tree |
