本论文围绕核算法在故障智能诊断中的应用，对故障诊断中不确定信息的处理、故障诊断实时性的实现、核函数的选择和参数优化、多类故障诊断、早期故障的发现以及样本数据的压缩等几个方面进行了较为系统深入的研究，为核算法应用于故障诊断提供了理论依据，促进了故障诊断技术的发展。-This paper provides the theoretical foundations for the applications of kernel algorithmto fault diagnoses though the deep and systematical study on the pplication of kernelalgorithm to intelligent fault diagnosis,the processing of the uncertain information in thediagnosis,the real-time realization of fault diagnoses,the choice of kernel function andparameter optimization,multiple classes of fault diagnoses,and incipient fault diagnosis,andthe sample data compaction.Thus,it promotes the development of fault diagnoses technique.The main tasks and the innovations works are as the follows.