Application of fault detection using distributed sensors in smart cities

Abstract This paper proposes a multi-sensor fault detection algorithm based on intelligent sensing systems. The algorithm establishes equations considering physical constraints and then uses the constraints between adjacent nodes to calculate the Kalman filter estimation value with state constraints, for fault diagnosis and data checking. The sensor structure propose herein is distributed, and the algorithm assumes the form of sensor network nodes, each node having its own processing system, without any central nodes or central communication facilities. Therefore, the proposed algorithm is fully distributed, enabling independent calculations between multiple measurement nodes. This paper discusses the algorithm derivation process in detail, as well as the verification of the parallelism, accuracy, and stability of the algorithm through software simulation and hardware testing.