Design of a Reconstruction for Specific Wear Rate of Epoxy Composites with Various Compositions Content of Polytetrafluoroethylen (PTFE), Graphite, Short Carbon Fibers (CF) and Nano-TiO2 via Adaptive Neuro-fuzzy Inference System (ANFIS)

Enhancements of the wear resistance of epoxy resins using various fillers is challengeable and traditional procedure. This procedure provides good bed to create more useful resins in their vast applications. To reduce the adhesion, internal lubricants such as polytetrafluoroethylen (PTFE) and graphite flakes are currently incorporated. Short carbon fibers (CF) are used to increase the creep resistance and strength of the epoxy matrix used. In this paper first we slightly demonstrate novel modeling methods such as ANN,FNN and ANFIS and then we present prediction model for specific wear rate of epoxy composites with various composition such as mention fillers via adaptive neuro-fuzzy inference system (ANFIS).nowadays, computational methods such as ANN has been briefly consider as applicable tools in modeling point of view. ANN has shown exceptional performance as regression tools, especially when used for pattern recognition and function estimation. They are highly non-linear, and can capture complex interactions between input/output variables in a system without any prior knowledge about the nature of these interactions. Fuzzy System (FS) is representation of prior knowledge into a set of constraints (network topology) to reduce the optimization search space. ANFIS present integrate performance of NN and FS. We gain good result that show ANFIS is powerful tool in modeling specific wear rate. Mean of squared error (MSE) for test sets of this study obtained 0.2302.

کلیدواژه ها:

Keywords: specific wear rate ، epoxy composites ، ANN ، ANFIS