This study investigates the applicability of Adaptive Neuro-Fuzzy Inference System (ANFIS) technique to predict the performance of a non-buoyant body typed wave energy converter. The non-buoyant body typed wave energy converter is a novel device which uses a water filled container as front end interface instead of a traditional buoyant buoy. A lab scale experimental investigation on the energy conversion efficiency of the device and its heave response were carried out on a small scale model and found that the results were competitive when compared with a buoy typed wave energy converter.
Soon after the experimental validations, mathematical model of the device was developed and tested for predicting the device behavior during various wave conditions. To test the viability of a soft computing tool to predict the behavior of a non-buoyant body typed wave energy converter, Adaptive Network-based Fuzzy Interface System was selected due to its predictive ability in uncertain environment. Further, four ANFIS models were developed, trained and validated with the recorded data and applied to predicting the heave response in various wave conditions.
The validation results confirm the applicability of the developed ANFIS models for predicting the device behavior over a wide range of wave parameters. The study demonstrates that the ANFIS model is capable of predicting the device behavior with a high degree of accuracy at minimum time. Once modeled, the ANFIS model can be used on behalf of the experimental setup to carryout further experiments to perform the optimization process.