Modelling evaporator in organic Rankine cycle using hybrid GD-LSE ANFIS and PSO ANFIS techniques

Abstract

Internal combustion engines (ICEs) are likely to be used in heavy-duty applications for many years and it is important to continue improving their efficiency. One approach is to recover waste heat from the exhaust of heavy-duty diesel engines (HDDEs) using waste heat recovery (WHR) technologies. WHR based on Organic Rankine Cycle (ORC) is a promising technology, which offers potential to reduce the fuel consumption of HDDEs by transferring the wasted thermal energy to alternative useful electrical or mechanical energy. In the ORC, the evaporator is considered the most critical component, because it has a high thermal inertia. Previous numerical models of evaporator are computationally expensive due to non-linearity of evaporator governing equations and cannot be deployed for real-time control applications. This study uses an Adaptive Network-based Fuzzy Inference System (ANFIS) modelling technique to provide efficient control-oriented evaporator models for prediction of heat source and refrigerant temperatures at the evaporator outlet. Hybrid gradient decent, least square estimate (GD-LSE) and particle swarm optimization (PSO) algorithms for training the ANFIS model have been investigated and show that training ANFIS using the PSO method results in an improvement in accuracy. Furthermore, the systematic and adaptive approach of the ANFIS modelling technique makes the procedure of evaporator modelling less dependent on expert knowledge, reducing the modelling effort.