Wireless sensor networks (WSN) can be widely used in various applications including structural health monitoring and environmental monitoring. They are measuring quantities like temperatures, displacements, accelerations or pressures based on a large number of sensor nodes. The latter are devices that integrate computation, communications and sensing capabilities. The measurements are processed to estimate the state of the monitored system. However, to ensure the reliability of the state estimate, the quality of the measurements has to be guaranteed. Indeed, the sensors are often placed in harsh environment which can induce faults. Therefore, before using the measurements recorded by the WSN, one should make sure that the measurements are fault free. The aim of this work is to design and implement distributed monitoring algorithm requiring limited computational resources while being robust with respect to environmental and operational changes.