This paper proposes a novel batch process monitoring method that is based on Kernel Entropy Independent component analysis(KEICA).The main idea of KEICA is to carry out an independent component analysis in the kernel entropy space to extract the non-linear and non-Gaussian characteristics of a batch process.The KEICA algorithm is whitened kernel entropy component analysis(KECA).Unlike other kernel feature extraction methods,this method chooses the principal component vectors according to the maximal Renyi entropy rather than judging by the top eigenvalues and eigenvectors of the kernel matrix simply,with a distinct angle-based structure.The sum of the squared independent socres(I2)statistic and the squared predction error(SPE)statistic of residual are adopted as monitoring statistics,for online monitoring of batch processes.However,the both monitoring statistics are lower-order statistics,which is only sensitive to amplitude.Higher-order cumulants analysis(HCA)is an up-to-date method that utilizes higher-order cumulants rather than lower-order to achieve the process monitoring.The proposed method is applied to penicillin fermentation process.Application demonstrate the superiority of KEICA over KICA and KPCA.