Performance analysis of novel air pollution forecasting system design in a Turkish cement plant via neural and neuro-fuzzy soft computing

ABSTRACT

Cement is an indispensable raw material of civil construction works although manufacturing methodology with massive energy and heat transfer impacts to environment and human health adversely. Tracking of flue gas emissions continuously and investing online supervisory control systems is mandatory to comply with instructions of regulations and standards imposing to monitor, control, and limit air pollutants, and sustainability. In this study, sulfur dioxide content in effluent gas of Turkish cement factory, located in Kocaeli, is modeled using 9 input parameters and 3 alternative forecasting systems are investigated to solve complex environmental engineering problem. Demanding neuro-fuzzy-based soft computing, ANFIS (Adaptive neural fuzzy inference system), artificial intelligence tool, ANN (Artificial neural networks), and statistical method, MLR (Multiple linear regression), are applied and output data is compared using RMSE (Root mean squared error) term and R² (Coefficient of determination). Prediction outputs reveal that proposed ANFIS air pollution forecasting system is found highly successful and promising with accurate R² and RMSE rates, 0.95, and 1.603, respectively. Further, offline-online simulator or expert modeler using the ANFIS forecasting software is recommended to be combined with existing plant control systems to measure efficiency as future study.

KEYWORDS:

• Artificial Neural Networks
• cement process
• fuzzy
• prediction
• sulfur dioxide

Additional information

Notes on contributors

Yasin Tunckaya

Yasin Tunckaya joined Honeywell as Service Contract Manager in 2017. He is holding B.S degree in Electronics & Communications Engineering from Yildiz Technical University, M.S. and Ph.D. degrees in Electrical-Electronics Engineering from Bulent Ecevit University and Sakarya University, Turkey respectively.  He previously worked for Erdemir, Gama Power Systems and Calik Enerji in the fields of automation, maintenance,  instrumentation & control and EPC project engineering.