Fault detection and diagnosis of an industrial steam turbine using fusion of SVM (support vector machine) and ANFIS (adaptive neuro-fuzzy inference system) classifiers
Department of Instrumentation and Automation, Petroleum University of Technology, Tehran, Iran Energy
(Impact Factor: 4.84).
12/2010; 35(12):5472-5482. DOI: 10.1016/j.energy.2010.06.001
The subject of FDD (fault detection and diagnosis) has gained widespread industrial interest in machine condition monitoring applications. This is mainly due to the potential advantage to be achieved from reduced maintenance costs, improved productivity and increased machine availability. This paper presents a new FDD scheme for condition machinery of an industrial steam turbine using a data fusion methodology. Fusion of a SVM (support vector machine) classifier with an ANFIS (adaptive neuro-fuzzy inference system) classifier, integrated into a common framework, is utilized to enhance the fault detection and diagnostic tasks. For this purpose, a multi-attribute data is fused into aggregated values of a single attribute by OWA (ordered weighted averaging) operators. The simulation studies indicate that the resulting fusion-based scheme outperforms the individual SVM and ANFIS systems to detect and diagnose incipient steam turbine faults.
Available from: Mohsen Hadian
- "Most of the studies reported in literature on fault diagnosis using neural networks or support vector machine involve chemical systems with a separator as one of its components (Hussain et al., 2013; Rusinov et al., 2013; Salahshoor et al., 2010). This process is selected because it reveals the most common features appearing in industrial processes. "
[Show abstract] [Hide abstract]
ABSTRACT: There are different approaches for Process Fault Diagnosis (PFD) ranging from analytical to statistical methods, such as artificial intelligence. Support vector machine (SVM) is a relatively novel machine learning method which can be used to handle fault classification due to its good generalization ability. The PFD based on Multi Label SVM approach (MLSVM) overcomes the difficulties of the Mono Label Artificial Neural Network (MLANN) approach including the needs for a large number of data points with difficult data gathering procedure and time consuming computation. However, the existing MLSVM approach has a lower classification performance. In this paper the objective is to improve the diagnosis performance of MLSVM approach while maintaining its advantages. Therefore, a novel MLSVM approach based on multiple regulation parameters is proposed for simultaneous fault classification in a Dew Point process. The performance of the proposed MLSVM approach is compared against other classifiers approaches including MLANN and MLSVM with single regulation parameter tuning. The classification performance of the proposed approach is close to MLANN approach and superior than MLSVM with single regulation parameter. However, MLSVM has other advantages in comparison with the MLANN approach including requirement of smaller number of data, easy data gathering and lower computational burden.
Journal of Natural Gas Science and Engineering 03/2015; 23. DOI:10.1016/j.jngse.2015.01.043 · 2.16 Impact Factor
Available from: Man Gyun Na
- ", , , ,  ,   , , ,  , ,  "
[Show abstract] [Hide abstract]
ABSTRACT: As condition-based maintenance (CBM) has risen as a new trend, there has been an active movement to apply information technology for effective implementation of CBM in power plants. This motivation is widespread in operations and maintenance, including monitoring, diagnosis, prognosis, and decision-making on asset management. Thermal efficiency analysis in nuclear power plants (NPPs) is a longstanding concern being updated with new methodologies in an advanced IT environment. It is also a prominent way to differentiate competitiveness in terms of operations and maintenance costs.
Nuclear Engineering and Technology 12/2014; 46(6):737-752. DOI:10.5516/NET.04.2014.720 · 0.77 Impact Factor
Available from: Milos Manic
- "ANNs have been applied to nuclear reactor monitoring in , . In , the fusion of Support Vector Machines (SVM) and Adaptive Neuro-Fuzzy Inference System (ANFIS) was used for fault detection and diagnosis in industrial steam turbines. Many other related CI-based approaches for plant monitoring can be found in literature. "
[Show abstract] [Hide abstract]
ABSTRACT: Resiliency and improved state-awareness of modern critical infrastructures, such as energy production and industrial systems, is becoming increasingly important. As control systems become increasingly complex, the number of inputs and outputs increase. Therefore, in order to maintain sufficient levels of state-awareness, a robust system state monitoring must be implemented that correctly identifies system behavior even when one or more sensors are faulty. Furthermore, as intelligent cyber adversaries become more capable, incorrect values may be fed to the operators. To address these needs, this paper proposes a fuzzy-neural data fusion engine (FN-DFE) for resilient state-awareness of control systems. The designed FN-DFE is composed of a three-layered system consisting of: 1) traditional threshold based alarms; 2) anomalous behavior detector using self-organizing fuzzy logic system; and 3) artificial neural network-based system modeling and prediction. The improved control system state-awareness is achieved via fusing input data from multiple sources and combining them into robust anomaly indicators. In addition, the neural network-based signal predictions are used to augment the resiliency of the system and provide coherent state-awareness despite temporary unavailability of sensory data. The proposed system was integrated and tested with a model of the Idaho National Laboratory's hybrid energy system facility known as HYTEST. Experiment results demonstrate that the proposed FN-DFE provides timely plant performance monitoring and anomaly detection capabilities. It was shown that the system is capable of identifying intrusive behavior significantly earlier than conventional threshold-based alarm systems.
Cybernetics, IEEE Transactions on 10/2014; 44(11):2065-2075. DOI:10.1109/TCYB.2014.2323891 · 3.47 Impact Factor
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.