Abstract: The nonlinear feature extraction (Kernel Principal Component Analysis（KPCA） and kernel Independent Component Analysis (ICA)) was used to eliminate the uncorrelated component from input data, and reduce dimension in the paper. Kernel principal component analysis adopted a kernel function to map input data into feature space and calculate linear PCA. Kernel independent component analysis extracted independent component by linear ICA transformation in the KPCA whitened space. The extracted features were taken as the input of Least Square Support Vector Machine (LSSVM) classifier. Incorporating nonlinear feature extraction into LSSVM served as a new method for intelligent fault diagnosis. The proposed method was applied to the fault diagnosis of lubricating oil process for a petro-plant. The effectiveness of the proposed method is verified.

Key words: kernel independent component analysis, kernel principal component analysis, least square support vector machines, fault diagnosis

摘要： 提出利用非线性特征提取（核主成分分析（KPCA）和核独立成分分析）消除数据的不相关性，降低维数。核主成分分析利用核函数把输入数据映射到特征空间，进行线性主成分分析计算提取特征；核独立成分分析在KPCA白化空间进行线性独立成分分析（ICA）变换提取独立成分。提取的特征作为最小二乘支持向量机分类器的输入，构建融合非线性特征提取和最小二乘支持向量机的智能故障分类方法。研究了该方法应用到某石化企业润滑油生产过程的故障诊断中的有效性和可行性。

关键词: 核独立成分分析, 核主成分分析, 最小二乘支持向量机, 故障诊断