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; Department of Control Engineering, Islamic Azad University South Tehran branch, Iran
Energy 01/2010; DOI: 10.1016/

ABSTRACT 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.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Resilient control systems in critical infrastructures require increased cyber-security and state-awareness. One of the necessary conditions for achieving the desired high level of resiliency is timely reporting and understanding of the status and behavioral trends of the control system. This paper describes the design and development of a fuzzy-neural data fusion system for increased state-awareness of resilient control systems. The proposed system consists of a dedicated data fusion engine for each component of the control system. Each data fusion engine implements three-layered alarm system consisting of: 1) conventional threshold-based alarms, 2) anomalous behavior detector using self-organizing maps, and 3) prediction error based alarms using neural network based signal forecasting. The proposed system was integrated with a model of the Idaho National Laboratory Hytest facility, which is a testing facility for hybrid energy systems. Experimental results demonstrate that the implemented data fusion system provides timely plant performance monitoring and cyber-state reporting.
    Resilient Control Systems (ISRCS), 2011 4th International Symposium on; 09/2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: Fault prediction based on particle filter approach is designed for dead reckoning investigation hybrid system, it utilizes a group of weighted particles to evaluate the system state, meanwhile, the fault state distribution and fault probability density distribution are calculated. Therefore, we can predict the fault probability and the fault type, furthermore, the broken-down time step can be assessed. The experimental results show that fault prediction based on particle filter can estimate the fault type for dead reckoning investigation hybrid system effectively.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Fault detection and diagnosis have an effective role for the safe operation and long life of systems. Condition monitoring is an appropriate way of the maintenance technique that is applicable in the fault diagnosis of rotating machinery faults. A unique flexible algorithm is proposed for classifying the condition of centrifugal pump based on support vector machine hyper-parameters optimization and artificial neural networks (ANNs) which are composed of eight distinct steps. Artificial neural networks (ANNs), support vector classification with genetic algorithm (SVC-GA) and support vector classification with particle swarm optimization (SVC-PSO) algorithm have been considered in a flexible algorithm to perform accurate classification in the manufacturing area. SVC-GA, SVC-PSO and ANN have been used together due to their importance and capabilities in classifying domain. Also, the superiority of the proposed hybrid algorithm (SVC with GA and PSO) is shown by comparing its results with SVC performance. Two types of faults through six features, flow, temperature, suction pressure, discharge pressure, velocity, and vibration, have been classified with proposed integrated algorithm. To test the robustness of the efficiency results of the proposed method, the ability of proposed flexible algorithm in dealing with noisy and corrupted data is analyzed.
    Applied Soft Computing. 03/2013; 13(3):1478–1485.