Abstract
The environmental ever demanding improvement along with the increasing demand of electricity attracted researchers in designing efficient, accurate and robust models. Such models are used mainly to predict the energy output of combined steam and gas turbine mechanisms. The applicability of these systems depends on their sustainability. It is inevitable to predict the combined mechanisms output energy in order to produce more trustworthy mechanisms. Since the acceptability of the aforesaid turbine systems is judged in terms of their profitability, the output energy prediction plays a vital role. In machine learning, the neural network (NN) based models has been proven to be a trustworthy in critical prediction tasks. However, the traditional learning algorithms in the NNs suffer from premature convergence to local optima while finding the optimum weight vectors. Consequently, the present work proposed a Cuckoo Search (CS) supported NN (NN-CS) and a Particle Swarm Optimization (PSO) supported NN (NN-PSO) to efficiently predict the electrical energy output of the combined cycle gas turbines. In the current study, five features are extracted, namely the ambient temperature, relative humidity and ambient pressure in gas turbines and exhaust vacuum from a steam turbine. The results established the improved performance of the CS based NN compared to the multilayer perceptron feed-forward neural network (MLP-FFN) and the NN-PSO (particle swarm optimization) in terms of root mean squared error. Proposed NN-CS achieved an average of 2.58% the mean square error (RMSE).
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.