Multi-objective optimization of tool wear, surface roughness, and material removal rate in finishing honing processes using adaptive neural fuzzy inference systems

Honing processes are usually employed to manufacture combustion engine cylinders and hydraulic cylinders. Honing provides a crosshatch pattern that favors the oil flow. In this paper, Adaptive Neural Fuzzy Inference System (ANFIS) models were obtained for tool wear, average roughness Ra, cylindricity and material removal rate in finishing honing processes. In addition, multi-objective optimization with the desirability function method was applied, in order to determine the process parameters that allow minimizing roughness, cylindricity error and tool wear, while maximizing material removal rate. The results showed that grain size and tangential velocity should be at their minimum levels, while density, pressure and linear velocity should be at their maximum levels. If only roughness, cylindricity error and tool wear are considered, then low grain size, low pressure and low linear velocity are recommended, while density and tangential velocity vary, depending on the optimization algorithm employed. This work will help to select appropriate process parameters in finishing honing processes, when roughness, cylindricity error and tool wear are to be minimized.

Automated summary

In this paper, ANFIS models and multi-objective optimization were used to study tool wear, roughness, cylindricity, and material removal rate in finishing honing processes. The study found that low grain size, pressure, and linear velocity are recommended for minimizing roughness, cylindricity error, and tool wear. The evaluation of density and tangential velocity depends on the optimization algorithm employed.