Automatic Fault Detection in Temperature Sensor Network Based on Kalman Filter and Online Fault Recovery Using Genetic Algorithm

Sensors have a great role in industry and science. Thus fault detection and mitigation in sensors is of special importance. In this paper، a network of temperature sensors is considered to measure the temperature of an area. The weighted average of sensors is considered as the final output for more reliability. Some of sensors are considered to provide redundancy for fault mitigation. Kalman filter detects fault and Genetic algorithm changes system such that the fault is mitigated. In this paper، bias fault، scaling fault، high noise fault and hard fault are considered and this system is resistant and effective for a variety of faults.