Purpose
– The surface energy per unit area of material is known to be proportional to the thermal energy at the melting point of the material. The purpose of this paper is to employ the values of the melting points of metals to develop a model that estimates the average surface energies of metals. Average surface energy estimator (ASEE) was developed with the aid of computational intelligence technique on the platform of support vector regression (SVR) using the values of the melting point of the materials as the descriptor.
Design/methodology/approach
– The development of ASEE which involves 12 data set was conducted by training and testing SVR model using test-set-cross-validation technique. The developed model (ASEE) was used to estimate average surface energies of 3d, 4d, 5d and other selected metals in the periodic table. The average surface energies obtained from ASEE are in good agreement with the experimental values and with the values from other theoretical models.
Findings
– The accuracy of this developed model coupled with its adoption of descriptor that can be easily obtained makes it a viable alternative in circumventing the difficulty experienced in experimental determination of average surface energies of materials.
Originality/value
– Modeling of ASEE has never been reported in the literature. Meanwhile, the use of ASEE will help circumvent the difficulties involved in the experimental determination of average surface energies of materials.
Component-Based Software System using Computational Intelligence Technique for Reliability Prediction
