Wireless sensors are increasingly adopted in mechanical systems to acquire and wirelessly transmit sensed information for machine condition monitoring. For wireless sensors on spindle, the reliability of the sensors system at high rotary speed is the key factor to guarantee the validity of monitoring. How to identify sensor failure accurately and timely is essential to enhance reliability of monitoring system. To address this issue, a novel method based on the BNs was presented to distinguish sensor failure from other transmission errors. The method described causal relationships of factors inducing sensor failure by graph theory and deduced sensor failure by Bayesian statistical techniques. Experiments carried on NC machining center prove the validity of this approach.