@article{MAKHILLJEAS201813415536,
    title = {Improving Mechanical Properties and Wear Resistant of Waste (High Strength Low
Alloy Steels Cans) by Carburization using Genetic Algorithm},
    journal = {Journal of Engineering and Applied Sciences},
    volume = {13},
    number = {4},
    pages = {867-873},
    year = {2018},
    issn = {1816-949x},
    doi = {jeasci.2018.867.873},
    url = {https://makhillpublications.co/view-article.php?issn=1816-949x&doi=jeasci.2018.867.873},
    author = {Hayder,Nabil and},
    keywords = {Corrosion,carburization,automatically,genetic,prediction,microstructure},
    abstract = {Recycling of iron and its alloys is the operation of re-melting iron so as to reuse in the production
stage. High Strength Low Alloy Steel (HSLAS) is widely utilized in industrial applications such as in bridges,
appliances, containers, buildings, highways tools and vehicles. This research deals with recycling of high
strength low alloy steel from beverage cans by cans collecting, sorting and melting these cans to develop this
processes, using casting technique for preparing alloy after the carburization to the base alloy so as to use in
the fabrication of applications which need wear and corrosion resistance. The mechanical, physical and
chemical tests carried out in this research involve hardness, surface roughness, wear, corrosion, microstructure,
XRD and chemical composition analysis. The results showed that there were an improvement in mechanical
properties of the alloy which was achieved by carburization. In comparison with the base metal, the hardness,
improved by 152% with the carburization, enhance of compression strength and the surface roughness
enhanced by 40%. Furthermore, the corrosion resistance and wear rate enhanced by 287 and 87%, respectively.
Genetic algorithm was used to develop model for prediction and optimization of the hardness, surface
roughness, wear rate and corrosion resistance after the carburization. According to the results obtained from
practical tests, it has been able to identify the best alloy which is coded as A as well as determine the optimal 510
alloy automatically based on the conception of optimization represented genetic algorithms which represented
the chromosome number of 76, 19 and 16 for 1X, 2X, multi X-crossover, respectively. The mean absolute relative
errors of the predict values of hardness, surface roughness wear rate and corrosion rate equal to 0.267, 0.311,
1.19, 0.047%, respectively as compared with the experimental values.}
    }