The Fault detection and diagnosis for sensors is important for the performance of the rock drilling jumbo seriously. The kernel principal component analysis (KPCA) effectively captures the nonlinear relationship of the process variables, which computes principal component in high dimensional feature space by means of integral operators and nonlinear kernel functions. The KPCA method was used in diagnosing for four common sensor faults. At first its fault was detected by Q statistic, secondly its fault was identified by T2 contribution percent change. The simulation and the practical result shows the KPCA method has good performance for complex control system in sensor fault detection and diagnosis.