Employing adaptive fuzzy computing for RCP intelligent control and fault diagnosis (original) (raw)
Related papers
Neuro-fuzzy systems for fault detection and isolation in nuclear reactors
10th IEEE International Conference on Fuzzy Systems. (Cat. No.01CH37297), 2001
This work presents an application of recurrent neuro-fuzzy systems to fault detection and isolation in nuclear reactors. In the adopted framework, a fuzzification module is linked to an inference module, which is actually a neural network adapted to the recognition of the dynamic evolution of process variables. Two different approaches to the neural network inference module are tested over data simulated by a commissioned simulator for the detection and isolation of a number of security related faults in a nuclear reactor.
Safety Improvement of Nuclear Power Reactor Using Soft Computing Techniques
are large in scale and complex, they are expected to be operated with high levels of reliability and safety. Hence to increase plant safety, to achieve, maintain system stability and assure satisfactory in order to meet the increasing demands for automated system and to detect and diagnose system failures and malfunctions. When a plant malfunction occurs, a great data influx is occurred. This paper proposes a support system based on neuro fuzzy approach conjunction with Genetic Algorithm that assist alarming and diagnosis system. Throughout this framework Neurofuzzy fault diagnosis system is employed to diagnosis the fault of nuclear reactors. Hence to overcome weak points of both neuro learning and linguistic based approaches by which the integrated system will inherit the strength of both approaches and to optimize the Neurofuzzy outcomes using Genetic Algorithm resulting to show the efficiency is obtained by GA is greater and the inaccurate information of the alarming system also compared with Neurofuzzy diagnosis system.
USING NEURAL NETWOK IN FAULT DIAGNOSIS of NUCLEAR POWER REACTORS
2000
In this paper, artificial neural networks (ANNs) are used in fault diagnosis of a nuclear power reactor (NPR). The Multilayer Neural Networks (MNNs) are used as a fault detection system, and this type of networks are learned using error back propagation training algorithm (EBPTA). The neural fault diagnosis system (NFDS) is used to identify reactor cooling pump (RCP) faults. To
Applying Neurofuzzy Computing for Safety Improvement of Nuclear Power Reactor
Nuclear Power Reactors (NPRs) are large in scale and complex, so the information from local fields is excessive, and therefore plant operators cannot properly process it. When a plant malfunction occurs, a great data influx is occurred, so the cause of the malfunction cannot be easily or promptly identified. A typical NPR may have around 2,000 alarms in the Main Control Room (MCR) in addition to the display of analog data. During plant transients, hundreds of alarms may be activated in a short time. Hence, to increase the plant safety, this paper proposes a support system based on neurofuzzy that assists alarming and diagnosis systems. Throughout this framework the neurofuzzy fault diagnosis system is employed to fault diagnosis of nuclear reactors. To overcome weak points of both linguistic and neuro learning based approaches, integration between the neural networks and fuzzy logic has been applied by which the integrated system will inherit the strengths of both approaches.
2021
The detection of incipient faults of the current fault diagnosis systems in Nuclear Power Plants is inherently limited. Active research in machine learning algorithms like Adaptive Neuro-Fuzzy Inference System (ANFIS) is providing promising results in the prediction of faults. This paper explored four different configurations of Adaptive Neuro-Fuzzy Inference System (ANFIS) methodology in a bid to come up with a superior model that not only had a high sensitivity in the detection of incipient faults but also had superior prediction capabilities. The data-driven ANFIS schemes were used to predict a sensitive fault signature and to evaluate the models, Small Break Loss of Coolant Accident (SBLOCA) transient events were modeled in Qinshan I Nuclear Power Plant. Coefficient of determination, normal probability plot of residuals and mean absolute percent error were used to assess the competencies of the estimation of the models.
Fault detection and analysis in nuclear research facility using artificial intelligence methods
AIP Conference Proceedings, 2016
In this article, an online detection of transducer and actuator condition is discussed. A case study is on the reading of area radiation monitor (ARM) installed at the chimney of PUSPATI TRIGA nuclear reactor building, located at Bangi, Malaysia. There are at least five categories of abnormal ARM reading that could happen during the transducer failure, namely either the reading becomes very high, or very low/ zero, or with high fluctuation and noise. Moreover, the reading may be significantly higher or significantly lower as compared to the normal reading. An artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) are good methods for modeling this plant dynamics. The failure of equipment is based on ARM reading so it is then to compare with the estimated ARM data from ANN/ ANFIS function. The failure categories in either 'yes' or 'no' state are obtained from a comparison between the actual online data and the estimated output from ANN/ ANFIS function. It is found that this system design can correctly report the condition of ARM equipment in a simulated environment and later be implemented for online monitoring. This approach can also be extended to other transducers, such as the temperature profile of reactor core and also to include other critical actuator conditions such as the valves and pumps in the reactor facility provided that the failure symptoms are clearly defined. Keywords: fault detection and analysis (FDA), transducer and actuator, artificial neural networks (ANNs), adaptive neuro-fuzzy inference system (ANFIS), area radiation monitor (ARM), online fault detection
Neurofuzzy Computing aided Fault Diagnosis of Nuclear Power Reactors
Proceedings of the 7th ICEENG Conference, 2010
Abstract: Nuclear Power Reactors (NPRs) are large in scale and complex, so the information from local fields is excessive, and therefore plant operators cannot properly process it. When a plant malfunction occurs, there are data influxes, so the cause of the malfunction cannot ...
Control Engineering and Applied Informatics, 2014
Safe and reliable control of a nuclear reactor with sufficient accuracy has been a challenging task. The objective of this work is to evaluate and validate a Fuzzy Logic Controller (FLC) scheme for a Pressurized Heavy Water Reactor (PHWR) that not only provides a safe and reliable operation but also a fast, accurate and robust reactor control, especially under transient conditions. For evaluating an FLC, a 22 nd order Single-Input Single-Output (SISO) model of the PHWR has been selected. We consider Xenon and Iodine dynamics, fuel and coolant temperature feedbacks and delayed and photo neutron concentrations in the model. The Mamdani inference engine type FLC is selected here. Due to the very stringent requirement on control system to be rugged and safe in a nuclear power plant, the controller is simulated, evaluated and validated for the three practical case scenarios; (i) step power change, (ii) reactivity disturbance, and (iii) loss of grid scenario. The results show that the controller performs well in terms of safety, reliability and robustness.
Artificial Neural Network Model for Fault Diagnosis of Rotating Machine in ETRR-2 Research Reactor
Arab Journal of Nuclear Sciences and Applications (Print), 2022
This article characterizes vibration signals using Artificial Neural Network (ANN) method to develop an effective and reliable feature sets for detecting and diagnosing faults in a centrifugal pump (ETRR-2 research reactor core coolant pumps). In this paper, a modular ANN are used for modeling the ETRR-2 research reactor core coolant pumps vibration monitoring. The input and the output signals of the vibration transducer are used as input source data for the ANN model. The amplitudes and frequency domain are inputted to the ANN separately from the vibration data. It is noted that the features statistical have good results based on frequency and amplitudes domains. The ANNs are used to detect the misalignment, unbalance severity, looseness bearing, and anti-fraction. The results are very useful for maintenance making decision. This methodology can be used for the research reactor coolant pumps. Hence, it may turn out to be a powerful tool for early detection of pump fault.