Early fault detection in transient conditions for a steam power plant subsystem using support vector machine

ARTICLE INFORMATION ABSTRACT Original Research Paper Received 27 June 2016 Accepted 21 September 2016 Available Online 22 October 2016 In this study, an application of support vector machine (SVM) for early fault detection in a Benson type once-through boiler is presented. Thermal conditions disruption inside the boiler during load changes is the main reason for level changes of the start-up vessel. Because of complexity of the system’s dynamics, first the effective variables on increasing the level of start-up vessel were identified based on experimental data from a power plant unit. Then, the dimension of input variables was reduced by selecting appropriate features. Experimental results show that the hotwell surfaces’ temperature could be considered as the most appropriate indicator for steam quality deterioration. By comparing the extracted features from healthy and unhealthy conditions, appropriate fault model was developed using SVM with radial basis function (RBF) as the kernel. The performance of fault detection system was evaluated with respect to the similar faults at two different time periods that happen in a steam power plant. The obtained results show the accuracy and feasibility of the proposed approach in early detection of faults during the unit’s load variations. Advantage of the proposed technique is the prevention of false alarm in power plants’ boilers as load changes.