This paper proposes a novel locally linear back-propagation based contribution(LLBBC)for nonlinear process fault diagnosis.As a method based on the deep leing model of auto-encoder(AE),LLBBC can deal with the fault diagnosis problem through extracting nonlinear features.When the on-line fault diagnosis task is in progress,a locally linear model is firstly built at the current fault sample.According to the basic idea of reconstruction based contribution(RBC),the propagation of fault information is described by using back-propagation(BP)al-gorithm.Then,a contribution index is established to measure the correlation between the variable and the fault,and the final dia-gnosis result is obtained by searching variables with large contri-butions.The smearing effect,which is an important factor affect-ing the performance of fault diagnosis,can be suppressed as well,and the theoretical analysis reveals that the correct diagnosis can be guaranteed by LLBBC.Finally,the feasibility and effective-ness of the proposed method are verified through a nonlinear nu-merical example and the Tennessee Eastman benchmark process.