Performance Evaluation of an Improved ANFIS Approach Using Different Algorithms to Predict the Bonding Strength of Glulam Adhered by Modified Soy Protein–MUF Resin Adhesive

Despite studies on the potential replacement of synthetic resins by bio-based adhesives such as proteins in recent years, there is still no reliable method for estimating strength wood products made using combined parameters literature. This limitation due to nonlinear relationship between and components. In present research, application artificial intelligence techniques was studied predict bonding glulam adhered protein containing different ratios MUF (melamine–urea–formaldehyde) resin with F-to-U/M molar at press temperatures. For this purpose, ANFIS model used basic mode or ant colony optimization (ACOR), particle swarm (PSO), differential evaluation (DE) genetic algorithms (GA) develop an optimal trained based experimental results. Comparison obtained results showed ability above methods estimate a manner. Although alone combination other not able achieve ideal performance prediction strength, GA offered excellent compared ANFIS. Hence, developed ANFIS-GA introduced best technique solve problems laminated products. addition, model, precise attempt show nature produce determine optimum limit.