RESUMEN
A nuclear power plant (NPP) consists of an enormous number of components with complex interconnections. Various techniques to detect sensor errors have been developed to monitor the state of the sensors during normal NPP operation, but not for emergency situations. In an emergency situation with a reactor trip, all the plant parameters undergo drastic changes following the sudden decrease in core reactivity. In this paper, a machine learning model adopting a consistency index is suggested for sensor error detection during NPP emergency situations. The proposed consistency index refers to the soundness of the sensors based on their measurement accuracy. The application of consistency index labeling makes it possible to detect sensor error immediately and specify the particular sensor where the error occurred. From a compact nuclear simulator, selected plant parameters were extracted during typical emergency situations, and artificial sensor errors were injected into the raw data. The trained system successfully generated output that gave both sensor error states and error-free states.
RESUMEN
The use of Unmanned Aerial Vehicles (UAVs) has increased significantly in recent years. On-board integrated navigation sensors are a key component of UAVs' flight control systems and are essential for flight safety. In order to ensure flight safety, timely and effective navigation sensor fault detection capability is required. In this paper, a novel data-driven Adaptive Neuron Fuzzy Inference System (ANFIS)-based approach is presented for the detection of on-board navigation sensor faults in UAVs. Contrary to the classic UAV sensor fault detection algorithms, based on predefined or modelled faults, the proposed algorithm combines an online data training mechanism with the ANFIS-based decision system. The main advantages of this algorithm are that it allows real-time model-free residual analysis from Kalman Filter (KF) estimates and the ANFIS to build a reliable fault detection system. In addition, it allows fast and accurate detection of faults, which makes it suitable for real-time applications. Experimental results have demonstrated the effectiveness of the proposed fault detection method in terms of accuracy and misdetection rate.
RESUMEN
In this paper, the sensor fault detection problem considering the drilling disturbances is studied for the dynamic point-the-bit rotary steerable system. Firstly, the DPRSS is modeled as a linear system with the drilling disturbances, including unknown inputs, measurement noises, and model perturbations. Then, a finite-frequency zonotopic fault detection observer is proposed. The finite-frequency range H- performance and the P-radius criterion are considered to design the observer gains such that the residuals are sensitive to sensor faults and robust against the drilling disturbances simultaneously. Subsequently, the calculation method of minimum detectable faults is presented for the proposed sensor fault detection mechanism. Finally, simulations and experiments are presented to illustrate the effectiveness of the proposed methods.
RESUMEN
Kalman filter and its different variants are commonly used as optimal methods for fault detection in various types of system components. In this paper, a newly introduced type of aforementioned filters, called modal Kalman filter, is extended and utilized in order to estimate the states of nonlinear systems, for sensor fault detection purposes, in a class of nonlinear certain systems. This method, in contrast to the extended Kalman filter, which employs only the linear term of Taylor expansion, retains higher-order terms; as a result, the estimation error will reduce accordingly. Practicality and effectivity of this method, and its superiority over Kalman filter, in terms of accuracy and promptness of sensor fault detection, are also verified with simulation results.