基于安全的多故障分类器设计

Design of Safety Multi-Fault Classification

为解决常用多故障分类器未考虑到各个故障造成的后果严重性问题,提出了基于故障优先级和核函数的聚合技术,采用这个方法生成1个基于最优二叉树的多故障分类器。该分类器利用核函数具有将非线性问题线性化的特点,生成了聚类函数,再通过各个故障的安全优先级生成最优二叉树,最后将此分类器应用于挖掘机的故障诊断中。应用及实测结果表明,此分类器不但能够保证故障诊断的正确率,而且可以让可能产生较严重后果的故障得到优先诊断。

In order to solve the problem of some existing methods of SVM muhi2class classification, a new multi2class classification based on Huffman binary tree was put forward. This classification uses Kernel function which can transfer non-linear into linear to get the clustering functions, and to build a Huffman binary tree based on every fault~ priority. This method has been used in the fault diagnosis system of excavator. The result shows that this classification can not only find the faults, but also find the more important faults at first.