Application of AHP-DEMATEL and GMDH Framework to Develop an Indicator to Identify Failure Probability of Wave Energy Converter

Abstract

The objective of the present study is to develop an extensive indicator which can represent the probability of failure of the wave energy converters.The objective was accomplished by the adaptation of a two-step methodology. In the first step, MCDM methods were used to estimate the priority values of the factors relevant to the probability of failure of the converter. In the second step, GMDH model was implemented to predict the values of the indicators which are directly proportional to the probability of failure of the converter. The significant parameters were identified by their consideration in different case studies and their influence on converter efficiency. The soft-computation methods like AHP-DEMATEL and GMDH were used to find the relative priority values of the parameters and to develop an automatic framework for estimation of the indicator. The indicator was made directly proportional to the ability of the converter to failure probability of wave energy in a specific location. The results from the multi-method estimation model were validated with the help of Multi Linear Regression Equation and some real time case analysis. With an accuracy of above, 99% the ensemble MCDM-ANN model depicts a reliability which ensures the author of its wide application for the real benefits like cost reduction and efficiency maximization of converters in the utilization of the potential energy of the locations.The model has the potential to become a tool with which engineers can easily identify the failure tendency of wave energy converters in specific locations.