Intelligent modeling of carbonized wood-silicon dioxide filled natural rubber composite for outer shoe sole manufacturing

Abstract

Large amount of wood dust is created as a byproduct of woodworking activities. Every year, there is an increase in wood dust generation, which severely pollutes the environment. Consequently, it becomes imperative to use wood dust in the production of useful products. A Carbonized Wood-Silicon Dioxide Filled Natural Rubber Composite (CWSDFNRC) was therefore created in this work using a compression molding method. The friction and compression properties of the composites were determined. Modeling of the composite's mechanical and friction characteristics was done using artificially intelligent techniques including Response Surface Methodology (RSM), Artificial Neural Network (ANN), and Adaptive Neuro-Fuzzy Inference System (ANFIS). The novel material was thermally analyzed using Dynamic Mechanical Analysis (DMA), Differential Scanning Calorimetry (DSC), Thermogravimetric Analysis (TGA), and Differential Thermal Analysis (DTA). The effectiveness of RSM, ANN, and ANFIS was demonstrated by relevant error indices. The optimization method revealed the ideal level of fitness at particle size, carbonization temperature, filler content, curing temperature, curing pressure, and curing time of 150 μm, 214 °C, 51 phr, 150 °C, 3 Pa, and 10 min respectively. These fitness conditions gave an optimal value of 17.63 MPa for compressive strength and a friction coefficient of 0.96. The novel material's characteristics contrasted well with those of comparable materials described in the literature, suggesting that it has the potential to be used in the manufacture of outer shoe soles and other elastomeric applications.

Keywords

• RSM
• ANN
• ANFIS
• DMA
• NBI
• Outer shoe sole